Compare commits

..

360 Commits

Author SHA1 Message Date
Dax Raad
7ca8334a8b fix webfetch tool when returning html as text 2025-06-19 10:43:54 -04:00
Dax Raad
f1a2b2eba4 support token caching for anthropic via openrouter 2025-06-19 10:32:14 -04:00
adamdottv
4b132656df feat(tui): copy share url to clipboard 2025-06-19 09:06:25 -05:00
Dax Raad
26bab00dab remove opencode_ prefixes from tool names. unfortunately this will break
all old sessions and share links. we'll be more backwards compatible in
the future once we're more stable.
2025-06-19 09:59:44 -04:00
adamdottv
568c04753e feat(tui): expand input to fit message 2025-06-19 08:45:27 -05:00
Dax Raad
4a06e164d2 ensure session.info is synced when shared 2025-06-19 09:41:11 -04:00
adamdottv
c57b52c300 fix: include schema in converted toml config 2025-06-19 06:02:02 -05:00
Guillermo Antony Cava Nuñez
0b8f48f17f Fixes tool tip layering (#199) 2025-06-19 00:23:29 -04:00
Dax Raad
3862184ccb hooks 2025-06-19 00:20:03 -04:00
Frank
8619c50976 Update SST 2025-06-18 23:38:06 -04:00
Josh
bb6b56b72a fix: incorrect command on main screen for exiting application (#201) 2025-06-18 23:19:43 -04:00
Dax Raad
1252b65166 stop loading models.dev format from global config 2025-06-18 23:08:51 -04:00
Dax Raad
6840276dad docs: update README 2025-06-18 23:03:54 -04:00
Dax Raad
bd8c3cd0f1 BREAKING CONFIG CHANGE
We have changed the config format yet again - but this should be the
final time. You can see the readme for more details but the summary is

- got rid of global providers config
- got rid of global toml
- global config is now in `~/.config/opencode/config.json`
- it will be merged with any project level config
2025-06-18 23:01:19 -04:00
Dax Raad
e5e9b3e3c0 rework config 2025-06-18 23:01:19 -04:00
Frank
1e8a681de9 Render version 2025-06-18 22:26:51 -04:00
Jay V
a834bedc17 ignore: share copy link 2025-06-18 20:18:10 -04:00
Dax Raad
6a3392385e support global config 2025-06-18 18:56:52 -04:00
Jay V
6a00e063c4 ignore: share logo 2025-06-18 18:33:51 -04:00
Jay V
73a0ce2b7d ignore: share 2025-06-18 18:22:19 -04:00
Jay V
4d1afd01fa ignore: share 2025-06-18 18:21:44 -04:00
Jay V
801d5f47bd ignore: share favicon 2025-06-18 18:10:22 -04:00
Jay V
b6caae9708 ignore: share 2025-06-18 18:01:34 -04:00
adamdottv
183ca64ef9 feat(tui): show provider next to model 2025-06-18 16:09:49 -05:00
adamdottv
8c32cfe829 chore: tui style tweaks 2025-06-18 15:59:58 -05:00
Jay V
73dcc88da1 ignore: share 2025-06-18 16:54:33 -04:00
Jay V
14bded65dc ignore: share 2025-06-18 16:54:33 -04:00
adamdottv
87d1d3fb62 fix(tui): file completion quirks 2025-06-18 15:51:26 -05:00
Frank
e054454109 Api: only return session messages 2025-06-18 16:20:34 -04:00
Dax Raad
a6142cf975 ignore: types 2025-06-18 16:20:03 -04:00
Jay V
69332e5fa3 ignore: share 2025-06-18 16:15:22 -04:00
Jay V
20201ba3c4 ignore: share 2025-06-18 16:15:11 -04:00
Dax Raad
658067186a ignore: share page stuff 2025-06-18 16:13:33 -04:00
adamdottv
ac777b77cf fix(tui): modal visuals 2025-06-18 15:12:24 -05:00
Dax Raad
5944ae2023 share types 2025-06-18 15:34:13 -04:00
Jay V
2f10961ba8 ignore: share 2025-06-18 15:32:40 -04:00
adamdottv
fae97978a3 chore: cleanup logs 2025-06-18 14:18:46 -05:00
Dax Raad
3423415e49 docs: improve keybinds configuration format in README
Update keybinds configuration example to use proper TOML table syntax instead of dot notation for better readability and standard TOML formatting.

🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-18 15:10:46 -04:00
adamdottv
1d0bfc2b2a fix(tui): help dialog sorting 2025-06-18 14:06:20 -05:00
adamdottv
bd46cf0f86 feat(tui): configurable keybinds and mouse scroll 2025-06-18 13:56:51 -05:00
Dax Raad
d4157d9a96 ctrl+c should gracefully clean up pending sessions 2025-06-18 14:11:49 -04:00
Jay V
6e4ef585d8 ignore: share error styles 2025-06-18 14:10:14 -04:00
Dax Raad
e05c3b7a76 fix panic when invalid config 2025-06-18 14:03:16 -04:00
Dax Raad
f99904bc1c track version on session info 2025-06-18 13:40:36 -04:00
Jay V
b796d6763f ignore: share page styles 2025-06-18 12:53:48 -04:00
Dax Raad
c1250abdf8 implemented diff trimming 2025-06-18 11:20:40 -04:00
Dax Raad
ebe51534a1 allow setting options in global provider store 2025-06-18 11:06:16 -04:00
Dax Raad
b8bbee4718 fix issue with provider cache 2025-06-18 10:56:23 -04:00
Dax Raad
8f852b396f fix deploys 2025-06-18 10:47:07 -04:00
Dax Raad
ae4d089c06 remove call to npm causing noticible delay when starting chat 2025-06-18 10:35:41 -04:00
Dax Raad
5110fbdaf9 fix issue when running opencode in empty directory 2025-06-18 10:29:09 -04:00
Dax Raad
e6ddb474fc ignore: sync 2025-06-18 08:36:25 -04:00
SBSTN
0dc71774ce Add Everforest Theme (#170) 2025-06-18 05:55:38 -05:00
Dax Raad
b470466e30 integrate cache read/write data 2025-06-17 20:51:39 -04:00
Jay V
d1f9311931 ignore: share page polish 2025-06-17 20:26:12 -04:00
Dax Raad
1c58023df9 improve anthropic oauth token caching and authentication handling
🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-17 13:23:15 -04:00
Dax Raad
4e0aa58b7e ignore: fix 2025-06-17 13:04:26 -04:00
Dax Raad
23ee34b35f state 2025-06-17 12:29:28 -04:00
Dax Raad
674c9a5220 support disabling providers from automatically being added 2025-06-17 12:23:04 -04:00
Dax Raad
54c86ed43a docs: readme 2025-06-17 12:17:45 -04:00
Dax Raad
676d75ee75 docs: update README 2025-06-17 12:14:38 -04:00
Dax Raad
70dc0a12f2 docs: readme 2025-06-17 12:12:33 -04:00
Dax Raad
d579c5e8aa support global config for providers 2025-06-17 12:10:44 -04:00
Dax Raad
ee91f31313 fix issue with tool schemas and google 2025-06-17 11:27:07 -04:00
Dax Raad
57b3051024 fix agent getting caught in summary loop 2025-06-17 10:50:03 -04:00
Dax Raad
ae5cf3cc23 ci: fix 2025-06-17 10:38:01 -04:00
Dax Raad
68e1b3c46c Fix TypeScript compilation errors and consolidate version handling
🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-17 10:27:49 -04:00
adamdottv
2d68814abc feat: better collapsed tool call visuals 2025-06-17 08:35:18 -05:00
adamdottv
a5da5127fa chore: consolidate chat page into tui.go 2025-06-17 07:09:04 -05:00
Dax Raad
b5a4439704 Add autoshare configuration and improve run command UI
Enables automatic session sharing via global config or flag, enhances UI with logo display and provider/model info positioning.

🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-17 01:45:32 -04:00
Dax Raad
9c5616521d do not autoupgrade snapshot builds 2025-06-17 01:18:32 -04:00
Dax Raad
3fe163416d autoupgrade 2025-06-17 01:05:05 -04:00
Dax
d054f88130 Improve upgrade command with installation method detection (#158) 2025-06-17 00:07:17 -04:00
Jay
b929b4f4b9 docs: Update README.md 2025-06-16 21:01:38 -04:00
Jay V
4c0c83b02d docs: readme 2025-06-16 20:10:19 -04:00
adamdottv
d6d45bdc63 feat: share and init commands 2025-06-16 15:58:52 -05:00
Dax Raad
13a83721b0 ci: fixed ci issue 2025-06-16 16:58:25 -04:00
Dax Raad
f0edffbae9 docs: readme 2025-06-16 16:53:43 -04:00
Dax Raad
8131bee49a ignore: logs 2025-06-16 16:02:45 -04:00
Dax Raad
b5f44ae13f docs: update readme 2025-06-16 15:42:35 -04:00
Miles Till
0d23f2a7fd fix: incorrect lipgloss version (#131) 2025-06-16 14:35:46 -05:00
Dax Raad
ac096d84ad remove windows builds 2025-06-16 15:11:14 -04:00
Dax Raad
fcaf0e6dbf opencode auth login: validation on provider id and better error messages 2025-06-16 15:09:49 -04:00
Dax Raad
19e259d90d docs: readme 2025-06-16 15:04:32 -04:00
Dax Raad
2c9fd1e776 BREAKING CHANGE: the config structure has changed, custom providers have an npm field now to specify which npm package to load. see examples in README.md 2025-06-16 15:02:25 -04:00
Dax Raad
63996c4189 limit to 4 system prompts cached 2025-06-16 14:51:59 -04:00
adamdottv
c7bb7ce4de fix: include cached tokens in tui 2025-06-16 12:59:38 -05:00
adamdottv
c8eb1b24c3 feat: believe it or not, even faster tui init 2025-06-16 12:34:34 -05:00
adamdottv
b9f894f1e9 feat: even faster tui init 2025-06-16 12:24:18 -05:00
adamdottv
7c0d10a4ce feat: faster tui init 2025-06-16 11:54:55 -05:00
Dax Raad
06af406146 properly track cache token counts 2025-06-16 12:43:22 -04:00
Dax Raad
0e3458b112 fix cache-control 2025-06-16 12:07:01 -04:00
adamdottv
2d15c683e0 fix: default provider and model 2025-06-16 10:51:01 -05:00
adamdottv
3c94d26570 chore: remove status service 2025-06-16 10:45:19 -05:00
Dax Raad
1a553e525f enable prompt caching for anthropic 2025-06-16 11:41:54 -04:00
adamdottv
3c4e966216 fix: spinner background color 2025-06-16 10:03:44 -05:00
Dax Raad
0721620ed8 docs: readme 2025-06-16 10:44:48 -04:00
Thomas Meire
9fc6734f32 ignore: remove log files and add them to gitignore (#138) 2025-06-16 09:30:07 -04:00
Jacob
e1733a423d fix: typo and literal wording in packages/opencode/AGENTS.md (#134) 2025-06-16 08:18:29 -05:00
Dax Raad
d42e3db7e0 docs: update README 2025-06-15 21:43:20 -04:00
Dax Raad
cdb26f6d83 docs: readme 2025-06-15 21:39:02 -04:00
Dax Raad
fe05edaa79 enhance ripgrep files function with query filtering and limit support
🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-15 21:26:32 -04:00
Dax Raad
7d174767b0 first pass making system prompt less fast 2025-06-15 20:25:04 -04:00
George Potoshin
c5eefd1752 Fix: Improve Help UI Readability (Issue #99) (#117) 2025-06-15 18:38:44 -05:00
adamdottv
77a6b3bdd6 fix: background color rendering issues 2025-06-15 15:07:05 -05:00
Pierre B.
7effff56c0 fix: spelling, grammar and typos (#121) 2025-06-15 14:23:18 -05:00
Dax Raad
e30fba0d3c Improve LSP server initialization with timeout handling and skip failed servers
🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-15 13:52:57 -04:00
Dax Raad
7fbb2ca9a6 ignore: add timer log helper 2025-06-15 13:33:24 -04:00
Dax Raad
230d0a1510 fix postinstall script for node 2025-06-15 13:11:11 -04:00
Pierre B.
46ff2c0ae0 chore: ignore intellij, vscode (#122) 2025-06-15 10:40:34 -05:00
adamdottv
b8a89dab0f fix: background color rendering issues 2025-06-15 05:57:15 -05:00
szymon
7351e12886 remove .DS_Store (#112) 2025-06-15 05:34:46 -05:00
Dax Raad
38879dee2d beginning of upgrade command 2025-06-14 22:05:41 -04:00
Dax Raad
c4ff8dd205 revert ctrl+d - conflicts with page down 2025-06-14 21:29:02 -04:00
Dax Raad
0e035b3115 fix aborting issue 2025-06-14 21:23:57 -04:00
Dax Raad
b855511d9a fix issue with follow up tool calls and cancelation 2025-06-14 21:03:44 -04:00
Dax Raad
783faf554d fix issue continuing session after aborted 2025-06-14 20:24:50 -04:00
nitishxyz
bfd4269d7d Add Ayu dark theme (#109) 2025-06-14 20:08:31 -04:00
Berr
25f78b053b fix: improve browser opening error handling in AuthLoginCommand (#111) 2025-06-14 20:07:41 -04:00
Dax Raad
87f260ee17 sync 2025-06-14 20:04:41 -04:00
Dax Raad
12931a869d ci: ignore commits 2025-06-14 18:59:05 -04:00
Dax Raad
f759e1804d docs: typo 2025-06-14 18:58:27 -04:00
Rohan Godha
c9b4564d36 tui: fix help dialog background (#110) 2025-06-14 18:57:15 -04:00
Conor O'Brien
d097c546db nit: update commands displayed on home to match commands available (#108) 2025-06-14 18:56:44 -04:00
Gal Schlezinger
adb54521b4 make ctrl+d quit too, just like shells (#105) 2025-06-14 18:56:34 -04:00
Dax Raad
2ea0399aa7 docs: use ollama example 2025-06-14 18:55:39 -04:00
Dax Raad
fa1266263d downgrade to ai sdk v4.x 2025-06-14 18:44:08 -04:00
Gal Schlezinger
fe109c921e add focus tracking for tui so cursor will hide when not in focus (#103) 2025-06-14 14:53:43 -05:00
Dax Raad
37bb8895fe docs: readme 2025-06-14 14:52:02 -04:00
Dax Raad
89b95be4de docs: provider config 2025-06-14 14:45:59 -04:00
Dax Raad
eaf295bac7 docs: faq 2025-06-14 14:39:13 -04:00
Mantena Rama Raju
27d3cec477 typo (#94) 2025-06-14 14:36:29 -04:00
Dax Raad
574d494c3c Enhance provider system with dynamic package resolution and improved logging
- Add npm registry lookup for AI SDK packages with fallback support
- Enhance error logging with cause information
- Add timing deltas to log output for performance monitoring

🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-14 14:35:33 -04:00
Albert Ilagan
0239761f31 tui: remove quit dialog (#97) 2025-06-14 12:47:34 -05:00
Dax Raad
a53f9165e9 doc: remove dev script 2025-06-14 13:05:23 -04:00
Dax Raad
ffc231bd8b docs: contributing 2025-06-14 12:45:26 -04:00
Dax Raad
3cf4ef56fb sync 2025-06-14 12:32:41 -04:00
Dax Raad
c738e26438 docs: mcp 2025-06-14 12:25:26 -04:00
Dax Raad
9c6aa82ac1 docs: config schema 2025-06-14 12:22:07 -04:00
Dax Raad
ef74d97491 ci: update publish script 2025-06-14 12:13:59 -04:00
Dax Raad
af892e5432 docs: readme 2025-06-14 12:13:46 -04:00
Dax Raad
d7aca6230d naming fixes 2025-06-14 01:54:28 -04:00
Dax Raad
0f9c2c5c27 Add flag system and auto-share functionality
- Add Flag module for environment variable configuration
- Implement OPENCODE_AUTO_SHARE flag to automatically share new sessions
- Update session creation to conditionally auto-share based on flag

🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-14 01:51:04 -04:00
Dax Raad
6a261dedb4 Improve logging and simplify fzf implementation
- Refactor fzf search to use Bun's $ syntax for cleaner command execution
- Add request/response duration logging to server middleware
- Set default service name for logging to improve log clarity

🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-14 01:51:04 -04:00
Alireza Bahrami
ec928d88b5 fix(install): check if the path export command already exists (#28) 2025-06-13 23:28:33 -04:00
Dax Raad
59a5f120c0 Clean up workflows and enhance file discovery tools to include dot files
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-13 23:24:46 -04:00
Dax Raad
ce07f80b19 sync 2025-06-13 17:42:56 -04:00
Dax Raad
168fd9b2e3 screenshot 2025-06-13 17:42:14 -04:00
Dax Raad
df13b155f9 disable autoshare 2025-06-13 17:30:17 -04:00
Dax Raad
eeed5b8718 sync 2025-06-13 17:24:45 -04:00
Dax Raad
148ef90210 sync 2025-06-13 17:23:22 -04:00
adamdottv
67023bb007 wip: refactoring tui 2025-06-13 15:56:33 -05:00
Dax Raad
a316aed4fe sync 2025-06-13 16:47:15 -04:00
Dax Raad
9f7c0bd599 sync 2025-06-13 16:46:48 -04:00
Dax Raad
c7e1068f90 sync 2025-06-13 16:45:58 -04:00
Dax Raad
e2052d790b sync 2025-06-13 16:43:53 -04:00
Dax Raad
d3b2763c14 commit and push 2025-06-13 16:42:31 -04:00
Dax Raad
c6492de7ac sync 2025-06-13 16:37:58 -04:00
Dax Raad
d8fa0fb50c sync 2025-06-13 16:29:57 -04:00
Dax Raad
18ab8faa1d reset readme 2025-06-13 16:26:34 -04:00
Dax Raad
f35ce180e2 ci 2025-06-13 16:23:38 -04:00
Dax Raad
2bee48a9bc homebrew 2025-06-13 16:17:27 -04:00
adamdottv
10ddd654cf wip: refactoring tui 2025-06-13 11:27:05 -05:00
adamdottv
61396b93ed wip: refactoring tui 2025-06-13 11:18:46 -05:00
adamdottv
62b9a30a9c wip: refactoring tui 2025-06-13 10:47:51 -05:00
adamdottv
5706c6ad3a wip: refactoring tui 2025-06-13 09:57:54 -05:00
adamdottv
e8e03c895a wip: refactoring tui 2025-06-13 09:44:09 -05:00
adamdottv
38667682a7 wip: refactoring tui 2025-06-13 09:19:51 -05:00
adamdottv
d7d5fc39fb wip: refactoring tui 2025-06-13 08:30:57 -05:00
adamdottv
0caf25adee wip: refactoring tui 2025-06-13 08:30:56 -05:00
Dax Raad
37febc6873 do not strip aur package 2025-06-13 08:27:17 -04:00
adamdottv
4169f0c412 wip: refactoring tui 2025-06-13 07:01:26 -05:00
adamdottv
b7f06bbc1f wip: refactoring tui 2025-06-13 06:56:12 -05:00
adamdottv
1b8cfe9e99 wip: refactoring tui 2025-06-13 06:49:59 -05:00
adamdottv
97837d2d23 wip: refactoring tui 2025-06-13 06:23:12 -05:00
Dax Raad
9abc2a0cf8 load API keys 2025-06-13 00:53:46 -04:00
Dax Raad
9fb47bc855 Enhance auth command with dynamic provider selection
- Add support for dynamically loading providers from ModelsDev
- Prioritize anthropic as recommended provider
- Add "other" provider option for manual entry
- Include special handling for amazon-bedrock with AWS config guidance
- Expand provider selection UI to show up to 8 providers

🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-13 00:33:54 -04:00
Dax Raad
73e9fb53d5 sync 2025-06-13 00:06:15 -04:00
Dax Raad
f03637b1fc Refactor AI SDK provider loading to use BunProc.install
Simplifies provider installation by using BunProc.install() instead of manual path construction and file system checks.

🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 23:50:26 -04:00
Dax Raad
2c376c5abc bedrock loader 2025-06-12 23:39:52 -04:00
Dax Raad
442e1b52ad Update provider configuration and server handling
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 23:10:03 -04:00
Thomas Meire
e8c3abc369 Update error message to say opencode instead of sst (#81) 2025-06-12 18:38:59 -04:00
Dax Raad
c8648baba2 ci 2025-06-12 18:30:19 -04:00
Dax Raad
7b3a799856 ci 2025-06-12 18:21:08 -04:00
Dax Raad
9356b6c35a sync 2025-06-12 18:14:04 -04:00
Dax Raad
29a6603a89 Update CLI run command and session handling
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 18:07:31 -04:00
Dax Raad
a454ba8895 subagent 2025-06-12 18:07:31 -04:00
Jay V
5eae7aef0e updating logo 2025-06-12 17:30:24 -04:00
adamdottv
1031bceef7 wip: refactoring tui 2025-06-12 16:04:45 -05:00
adamdottv
653965ef59 wip: refactoring tui 2025-06-12 16:00:26 -05:00
adamdottv
ca0ea3f94d wip: refactoring tui 2025-06-12 16:00:25 -05:00
adamdottv
98bd5109c2 wip: refactoring tui 2025-06-12 16:00:25 -05:00
adamdottv
78f65e4789 wip: refactoring tui 2025-06-12 16:00:25 -05:00
adamdottv
75dd2f75aa wip: refactoring tui 2025-06-12 16:00:25 -05:00
adamdottv
fe86e58bbb wip: refactoring tui 2025-06-12 16:00:24 -05:00
adamdottv
ae339015fc wip: refactoring tui 2025-06-12 16:00:24 -05:00
adamdottv
cce2e4ad75 wip: refactoring tui 2025-06-12 16:00:24 -05:00
Dax Raad
a1ce35c208 ci 2025-06-12 14:15:44 -04:00
Dax Raad
69d6709a19 sync 2025-06-12 14:11:01 -04:00
Dax Raad
52ec134b2d Update publish workflow to support snapshot releases on dontlook branch
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 14:10:29 -04:00
Dax Raad
db88bede05 sync 2025-06-12 14:06:06 -04:00
Dax Raad
d4d218d7d6 Update index.ts
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 13:59:42 -04:00
Dax Raad
3e086e3ab9 sync 2025-06-12 13:49:43 -04:00
Jay V
2f5faae34b fix share page edit 2025-06-12 13:42:10 -04:00
Dax Raad
e3ad6a0698 do not output bunproc 2025-06-12 13:39:03 -04:00
Dax Raad
b536b45536 Fix AUR SSH key path handling in publish script
Quote and trim AUR_KEY environment variable to handle paths with spaces and multiline content properly.

🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 13:37:12 -04:00
Dax Raad
81c245035f Simplify BunProc.which() to use process.execPath directly
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 13:32:31 -04:00
Dax Raad
dda7059e57 update bun integration
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 13:29:14 -04:00
Dax Raad
0cca75ef48 sync 2025-06-12 13:19:24 -04:00
Dax Raad
ee1f55dbe2 token 2025-06-12 13:17:06 -04:00
Dax Raad
2fa50190e5 skip nil values 2025-06-12 13:13:34 -04:00
Jay V
662b6b1258 share page handle undefined 2025-06-12 13:11:34 -04:00
Dax Raad
f0dbe40522 sync 2025-06-12 13:04:01 -04:00
Dax Raad
41c54f629c sync 2025-06-12 12:48:38 -04:00
Dax Raad
4503201b15 npm token 2025-06-12 12:09:13 -04:00
Dax Raad
120151ee38 sync 2025-06-12 11:58:41 -04:00
Dax Raad
4d2e556713 sync 2025-06-12 11:57:57 -04:00
Dax Raad
54a5d3a9eb sync 2025-06-12 11:56:52 -04:00
Dax Raad
22dc6b6ec9 sync 2025-06-12 11:56:06 -04:00
Dax Raad
b5c6ddcd04 tweak 2025-06-12 11:55:07 -04:00
Dax Raad
e03ad6c42e sync 2025-06-12 11:18:17 -04:00
Dax Raad
33457d8472 sync 2025-06-12 11:02:51 -04:00
Dax Raad
888105e60f sync 2025-06-12 11:00:37 -04:00
Dax Raad
b7b490f67c Add postinstall script and update session/release configuration
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-12 00:50:49 -04:00
Dax Raad
f6ed59bf45 Refactor external tools organization and add file search API endpoint
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-11 23:59:51 -04:00
Dax Raad
83991bee88 Add search function to fzf and move version constant to namespace level
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-11 23:58:13 -04:00
Dax Raad
29142eb940 add title temp 2025-06-11 19:09:08 -04:00
Dax Raad
aab47714c9 sync 2025-06-11 19:00:09 -04:00
Dax Raad
9b2b610920 sync 2025-06-11 18:45:18 -04:00
Dax Raad
468cec545a sync 2025-06-11 18:19:21 -04:00
adamdottv
3c82fb6818 wip: refactoring tui 2025-06-11 12:05:54 -05:00
adamdottv
8a2f370eda wip: refactoring tui 2025-06-11 11:58:25 -05:00
Dax Raad
636133e6cb sync 2025-06-11 12:58:06 -04:00
Dax Raad
6cf8784ecf sync 2025-06-11 12:44:21 -04:00
adamdottv
95d5e1f231 wip: refactoring tui 2025-06-11 11:43:28 -05:00
Dax Raad
979bad3e64 sync 2025-06-11 12:35:20 -04:00
Dax Raad
300d0474a3 sync 2025-06-11 11:41:10 -04:00
Dax Raad
d4379c8c93 turn on tool call streaming 2025-06-11 11:36:12 -04:00
Jay V
a9b230f419 share page scroll anchor 2025-06-11 09:43:52 -05:00
Dax Raad
07cffebc8f fix bash 2025-06-11 00:37:43 -04:00
Dax Raad
f1de1634d6 Standardize styling in auth commands by replacing Bun.color with UI.Style constants
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-11 00:34:55 -04:00
Dax Raad
8d8663399d sync 2025-06-11 00:27:46 -04:00
Dax Raad
83eb61fd5f Refactor authentication system to consolidate auth flow and remove provider-based commands
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-11 00:21:46 -04:00
Dax Raad
b8e7d06356 sync 2025-06-10 22:18:27 -04:00
Dax Raad
4543765e3a fix rendering 2025-06-10 19:37:25 -04:00
Dax Raad
28f5cbbfe9 Fix shutdown handling, error management, and process lifecycle issues
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-10 18:58:47 -04:00
Dax Raad
ca3c22dc12 fix bunfile bug 2025-06-10 18:23:19 -04:00
Dax Raad
49110f7412 sync 2025-06-10 18:10:30 -04:00
Dax Raad
14dcf43246 add abort signals 2025-06-10 17:56:05 -04:00
Dax Raad
84e4afc0bd webfetch spoof browser 2025-06-10 16:39:06 -04:00
Dax Raad
1cc8e9a36d kill 2025-06-10 16:35:02 -04:00
Dax Raad
43b429db93 lsp 2025-06-10 16:29:35 -04:00
Dax Raad
6248c1e720 merge deep config 2025-06-10 16:19:02 -04:00
Frank
772e1851c0 Share: render url on frontend 2025-06-10 15:50:42 -04:00
Dax Raad
5ab2ff9589 onboarding progress 2025-06-10 15:43:14 -04:00
Dax Raad
a0062d4661 fix share link 2025-06-10 13:36:47 -04:00
Dax Raad
ef7f1f0761 sync 2025-06-10 13:30:13 -04:00
Dax Raad
96b5a079ff Update LSP client/server and CLI scrap command functionality
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-10 13:30:13 -04:00
Jay V
0e58f488df moving share urls 2025-06-10 11:52:02 -05:00
Dax Raad
fa7416687b Enhance ripgrep error handling and utility functions
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-10 11:06:01 -04:00
Jay V
c3ab370344 share page fix 2025-06-10 09:33:28 -05:00
Dax Raad
bb60aa3060 sync 2025-06-10 10:14:03 -04:00
Dax Raad
34fa8cadd6 Improve ripgrep error handling with structured error types
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-10 10:14:03 -04:00
Frank
edd459ec00 Share: og image 2025-06-09 23:37:32 -04:00
Frank
177875f624 ssr sync 2025-06-09 23:07:29 -04:00
Dax Raad
fdaa7f287c aborted toolcalls should be cleaned up 2025-06-09 20:48:50 -04:00
Dax Raad
fed659c582 properly support codex mini 2025-06-09 20:24:18 -04:00
Dax Raad
bffc612a4e notice 2025-06-09 19:58:08 -04:00
Jay V
b97b15e0fe share og image 2025-06-09 16:42:13 -05:00
Jay V
fcb972de19 edits 2025-06-09 16:09:15 -05:00
Dax Raad
4478195ea8 file permissions for anthropic credentials 2025-06-09 17:07:52 -04:00
Jay V
54c4a783b3 share page show lsp diag 2025-06-09 15:41:19 -05:00
Jay V
c091cbb624 share page fix ai text 2025-06-09 15:02:46 -05:00
Jay V
d4f8fd867a fix duplicates models 2025-06-09 15:02:46 -05:00
Dax Raad
a2884b08cc improve AGENTS.md 2025-06-09 15:28:06 -04:00
Dax Raad
60faa26a15 sync 2025-06-09 15:00:48 -04:00
Dax Raad
d8510ab452 Refactor logging system to centralize initialization and remove printLogs parameter
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-09 14:52:30 -04:00
Dax Raad
3c23b92bea optional 2025-06-09 14:02:58 -04:00
Dax Raad
021fd3fcb5 sync 2025-06-09 14:01:11 -04:00
Dax Raad
fa3253d1b6 Add TypeScript server initialization config to LSP server
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-08 13:22:07 -04:00
Dax Raad
a1cc8f6cdb fix ts lsp 2025-06-08 12:57:33 -04:00
Dax Raad
1bcc02442a sync 2025-06-08 12:46:32 -04:00
Frank
1d782dc19a Share: load server data on page load 2025-06-08 01:17:54 -04:00
Frank
879d02f86c Remove unused package 2025-06-07 23:47:45 -04:00
Frank
028d589ea0 Infra: use Astro component 2025-06-07 23:46:56 -04:00
Dax Raad
cdbdb96218 sync 2025-06-07 17:15:40 -04:00
Dax Raad
f22c93ba1b logs 2025-06-06 23:58:09 -04:00
Dax Raad
b34d5c959b add go version 2025-06-06 23:26:11 -04:00
Dax Raad
32e6a552c0 autodownload lsp 2025-06-06 23:21:57 -04:00
Dax Raad
d6afebf22a make lsp better 2025-06-06 17:20:08 -04:00
Jay V
b32cb2b932 share page styles 2025-06-06 12:18:02 -04:00
Dax Raad
265f427d2a lsp progress 2025-06-05 23:42:04 -04:00
Dax Raad
16520261f4 update auth and provider configuration
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-05 20:11:56 -04:00
Jay V
65b2cf73d7 share page markdown 2025-06-05 19:14:35 -04:00
Jay V
95069af03f share write tool 2025-06-05 16:41:44 -04:00
Jay V
3e4ebb6e5d share page 2025-06-05 16:35:23 -04:00
Dax Raad
9147108675 fix webfetch 2025-06-05 15:59:17 -04:00
Jay V
ea9dd4e9e2 share ssr 2025-06-05 15:37:23 -04:00
Dax Raad
4a6e36a404 fix cost 2025-06-05 15:06:42 -04:00
Dax Raad
db2bb32bcf integrate with models.dev 2025-06-05 14:59:16 -04:00
Jay V
1384a5e3e6 share page fetch 2025-06-05 14:17:43 -04:00
adamdottv
167aea6aaf wip: refactoring tui 2025-06-05 13:10:20 -05:00
Jay V
142056e9af share page todos 2025-06-05 13:52:44 -04:00
Dax Raad
241c366164 sync 2025-06-05 13:51:18 -04:00
Dax Raad
3cd7ae0807 gopls 2025-06-05 13:51:18 -04:00
Dax Raad
299a74061a sync 2025-06-05 13:51:18 -04:00
adamdottv
e3d5af2855 wip: refactoring tui 2025-06-05 12:38:25 -05:00
adamdottv
bbfa72552a feat: opus 4 2025-06-05 11:39:13 -05:00
Dax Raad
8dfdd3927e sync 2025-06-05 12:06:21 -04:00
Dax Raad
02e326f87f fixed 2025-06-05 11:58:04 -04:00
Dax Raad
35b03e4cb3 claude oauth support 2025-06-05 11:51:06 -04:00
adamdottv
b3555cda30 wip: refactoring tui 2025-06-05 10:46:07 -05:00
adamdottv
04bd98cf4d wip: refactoring tui 2025-06-05 05:43:33 -05:00
Dax Raad
f3e31130ba fix cost 2025-06-05 02:23:11 -04:00
Dax Raad
671e91f201 Add session share URL display to CLI output
🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-04 21:01:36 -04:00
Dax Raad
d334ead84a sync 2025-06-04 20:49:33 -04:00
Jay V
160428d2d4 share page glob 2025-06-04 20:14:14 -04:00
Jay V
0a1f9accd7 share page glob 2025-06-04 19:34:15 -04:00
Jay V
a74f27e59a read tool share page 2025-06-04 18:39:06 -04:00
Dax Raad
f76cdfff9b sync 2025-06-04 18:32:10 -04:00
Dax Raad
05974ea109 rework 2025-06-04 18:03:04 -04:00
Dax Raad
6cfce1e4da track errors 2025-06-04 17:55:14 -04:00
Jay V
e20093678f share page tool args 2025-06-04 17:48:42 -04:00
Dax Raad
7f8f46f9fe Refactor session module structure and improve error handling
- Rename session.ts to index.ts for cleaner module imports
- Update all imports to use new session module structure
- Add error metadata tracking to message schema
- Improve error handling in session stream processing

🤖 Generated with [OpenCode](https://opencode.ai)

Co-Authored-By: OpenCode <noreply@opencode.ai>
2025-06-04 17:38:54 -04:00
Jay V
2dbdecb0f7 styles share 2025-06-04 17:01:04 -04:00
Dax Raad
53b0a25085 implemented todo tool 2025-06-04 15:09:50 -04:00
adamdottv
093e64eb54 wip: refactoring tui 2025-06-04 13:52:23 -05:00
adamdottv
f34a3b6f67 wip: refactoring tui 2025-06-04 12:57:17 -05:00
Jay V
484c90ed00 share collapse system prompt 2025-06-04 13:37:07 -04:00
Dax Raad
f49694a543 sync 2025-06-04 13:33:53 -04:00
Dax Raad
fb88705bdc more tools 2025-06-04 13:33:25 -04:00
Dax Raad
90d85e6393 sync 2025-06-04 13:12:55 -04:00
Dax Raad
d13822d26e tool updates 2025-06-04 13:12:48 -04:00
adamdottv
a890288900 wip: refactoring tui 2025-06-04 11:48:01 -05:00
adamdottv
31d6e303a6 wip: refactoring tui 2025-06-04 11:48:01 -05:00
Jay V
199c42f726 styles share 2025-06-04 12:44:36 -04:00
Jay V
3211594821 styles 2025-06-04 12:32:25 -04:00
adamdottv
01050a430f wip: refactoring tui 2025-06-04 09:20:48 -05:00
Dax Raad
0b565b18c4 sync 2025-06-04 10:20:29 -04:00
Dax Raad
0791b077d7 fix tokens 2025-06-04 10:14:42 -04:00
Jay V
2fb59fee8e share paage durations 2025-06-03 18:08:46 -04:00
Jay V
8206da4d9e share page bugs 2025-06-03 17:20:30 -04:00
adamdottv
0c6bda8255 wip: refactoring tui 2025-06-03 15:49:41 -05:00
Dax Raad
1e063e7937 fix port issue 2025-06-03 16:35:37 -04:00
Dax Raad
37c34fd39c mcp support 2025-06-03 15:57:48 -04:00
Jay V
3a60ae98f3 styles 2025-06-03 15:57:00 -04:00
Jay V
feeb49a42b Styling share 2025-06-03 15:55:34 -04:00
Jay V
ad84355ebc lock 2025-06-03 15:55:34 -04:00
Dax Raad
e2397a343d Fix bash tool stream handling by ensuring consistent stdout/stderr pipe configuration
🤖 Generated with opencode
Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-03 14:48:05 -04:00
Dax Raad
8e769dcac0 Replace env-paths with xdg-basedir for better XDG compliance and cross-platform directory handling
🤖 Generated with opencode
Co-Authored-By: opencode <noreply@opencode.ai>
2025-06-03 14:46:28 -04:00
Dax Raad
9ad0477af6 change file name again 2025-06-03 14:28:50 -04:00
Dax Raad
c5eafd5722 sync 2025-06-03 14:25:25 -04:00
Dax Raad
caf9fdc893 initialized 2025-06-03 14:24:45 -04:00
Dax Raad
be4155a838 max output tokens 2025-06-03 13:46:39 -04:00
adamdottv
b00326a75a wip: refactoring tui 2025-06-03 12:45:28 -05:00
Dax Raad
4cf0aebb2e do not list files if not git 2025-06-03 13:19:44 -04:00
Dax Raad
a5a39dada7 include env 2025-06-03 13:18:42 -04:00
Dax Raad
866f22b077 sync 2025-06-03 13:08:47 -04:00
Dax Raad
ec7ab16ce4 sync 2025-06-03 13:00:27 -04:00
Dax Raad
e5b06a2d95 initialzie 2025-06-03 12:38:48 -04:00
226 changed files with 18566 additions and 16313 deletions

View File

@@ -1,37 +0,0 @@
name: build
on:
workflow_dispatch:
push:
branches:
- dev
concurrency: ${{ github.workflow }}-${{ github.ref }}
permissions:
contents: write
packages: write
jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
- run: git fetch --force --tags
- uses: actions/setup-go@v5
with:
go-version: ">=1.23.2"
cache: true
cache-dependency-path: go.sum
- run: go mod download
- uses: goreleaser/goreleaser-action@v6
with:
distribution: goreleaser
version: latest
args: build --snapshot --clean

View File

@@ -3,7 +3,7 @@ name: deploy
on:
push:
branches:
- dontlook
- dev
workflow_dispatch:
concurrency: ${{ github.workflow }}-${{ github.ref }}

63
.github/workflows/publish.yml vendored Normal file
View File

@@ -0,0 +1,63 @@
name: publish
on:
workflow_dispatch:
push:
branches:
- dev
tags:
- "*"
concurrency: ${{ github.workflow }}-${{ github.ref }}
permissions:
contents: write
packages: write
jobs:
publish:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
- run: git fetch --force --tags
- uses: actions/setup-go@v5
with:
go-version: ">=1.24.0"
cache: true
cache-dependency-path: go.sum
- uses: oven-sh/setup-bun@v2
with:
bun-version: 1.2.16
- name: Install makepkg
run: |
sudo apt-get update
sudo apt-get install -y pacman-package-manager
- name: Setup SSH for AUR
run: |
mkdir -p ~/.ssh
echo "${{ secrets.AUR_KEY }}" > ~/.ssh/id_rsa
chmod 600 ~/.ssh/id_rsa
ssh-keyscan -H aur.archlinux.org >> ~/.ssh/known_hosts
git config --global user.email "opencode@sst.dev"
git config --global user.name "opencode"
- name: Publish
run: |
bun install
if [ "${{ startsWith(github.ref, 'refs/tags/') }}" = "true" ]; then
./script/publish.ts
else
./script/publish.ts --snapshot
fi
working-directory: ./packages/opencode
env:
GITHUB_TOKEN: ${{ secrets.SST_GITHUB_TOKEN }}
AUR_KEY: ${{ secrets.AUR_KEY }}
NPM_CONFIG_TOKEN: ${{ secrets.NPM_TOKEN }}

View File

@@ -1,40 +0,0 @@
name: release
on:
workflow_dispatch:
push:
tags:
- "*"
concurrency: ${{ github.workflow }}-${{ github.ref }}
permissions:
contents: write
packages: write
jobs:
goreleaser:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
- run: git fetch --force --tags
- uses: actions/setup-go@v5
with:
go-version: ">=1.23.2"
cache: true
cache-dependency-path: go.sum
- run: go mod download
- uses: goreleaser/goreleaser-action@v6
with:
distribution: goreleaser
version: latest
args: release --clean
env:
GITHUB_TOKEN: ${{ secrets.SST_GITHUB_TOKEN }}
AUR_KEY: ${{ secrets.AUR_KEY }}

4
.gitignore vendored
View File

@@ -1,5 +1,7 @@
.DS_Store
node_modules
.opencode
.sst
app.log
.env
.idea
.vscode

818
README.md
View File

@@ -1,728 +1,218 @@
# ◍OpenCode
<p align="center">
<a href="https://opencode.ai">
<picture>
<source srcset="packages/web/src/assets/logo-dark.svg" media="(prefers-color-scheme: dark)">
<source srcset="packages/web/src/assets/logo-light.svg" media="(prefers-color-scheme: light)">
<img src="packages/web/src/assets/logo-light.svg" alt="opencode logo">
</picture>
</a>
</p>
<p align="center">
<a href="https://www.npmjs.com/package/opencode-ai"><img alt="npm" src="https://img.shields.io/npm/v/opencode-ai?style=flat-square" /></a>
<a href="https://github.com/sst/opencode/actions/workflows/publish.yml"><img alt="Build status" src="https://img.shields.io/github/actions/workflow/status/sst/opencode/publish.yml?style=flat-square&branch=dev" /></a>
</p>
![OpenCode Terminal UI](screenshot.png)
---
> **⚠️ Early Development Notice:** This project is in early development and is not yet ready for production use. Features may change, break, or be incomplete. Use at your own risk.
AI coding agent, built for the terminal.
A powerful terminal-based AI assistant for developers, providing intelligent coding assistance directly in your terminal.
**Note:** Version 0.1.x is a full rewrite, and we do not have proper documentation for it yet. Should have this out week of June 17th 2025.
## Overview
[![opencode Terminal UI](screenshot.png)](https://opencode.ai)
OpenCode is a Go-based CLI application that brings AI assistance to your terminal. It provides a TUI (Terminal User Interface) for interacting with various AI models to help with coding tasks, debugging, and more.
## Features
- **Interactive TUI**: Built with [Bubble Tea](https://github.com/charmbracelet/bubbletea) for a smooth terminal experience
- **Multiple AI Providers**: Support for OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, Groq, Azure OpenAI, and OpenRouter
- **Session Management**: Save and manage multiple conversation sessions
- **Tool Integration**: AI can execute commands, search files, and modify code
- **Vim-like Editor**: Integrated editor with text input capabilities
- **Persistent Storage**: SQLite database for storing conversations and sessions
- **LSP Integration**: Language Server Protocol support for code intelligence
- **File Change Tracking**: Track and visualize file changes during sessions
- **External Editor Support**: Open your preferred editor for composing messages
- **Named Arguments for Custom Commands**: Create powerful custom commands with multiple named placeholders
## Installation
### Using the Install Script
### Installation
```bash
# Install the latest version
# YOLO
curl -fsSL https://opencode.ai/install | bash
# Install a specific version
curl -fsSL https://opencode.ai/install | VERSION=0.1.0 bash
# Package managers
npm i -g opencode-ai@latest # or bun/pnpm/yarn
brew install sst/tap/opencode # macOS
paru -S opencode-bin # Arch Linux
```
### Using Homebrew (macOS and Linux)
> **Note:** Remove versions older than 0.1.x before installing
### Providers
The recommended approach is to sign up for Claude Pro or Max, run `opencode auth login`, and select Anthropic. It's the most cost-effective way to use opencode.
opencode is powered by the provider list at [Models.dev](https://models.dev), so you can use `opencode auth login` to configure API keys for any provider you'd like to use. This is stored in `~/.local/share/opencode/auth.json`.
```bash
brew install sst/tap/opencode
$ opencode auth login
┌ Add credential
◆ Select provider
│ ● Anthropic (recommended)
│ ○ OpenAI
│ ○ Google
│ ○ Amazon Bedrock
│ ○ Azure
│ ○ DeepSeek
│ ○ Groq
│ ...
```
### Using AUR (Arch Linux)
The Models.dev dataset is also used to detect common environment variables like `OPENAI_API_KEY` to autoload that provider.
```bash
# Using yay
yay -S opencode-bin
If there are additional providers you want to use you can submit a PR to the [Models.dev repo](https://github.com/sst/models.dev). If configuring just for yourself check out the Config section below.
# Using paru
paru -S opencode-bin
```
### Config
### Using Go
Config is optional and can be placed in the root of your repo or globally in `~/.config/opencode/config.json`. It can be checked in and shared with your team.
```bash
go install github.com/sst/opencode@latest
```
## Configuration
OpenCode looks for configuration in the following locations:
- `$HOME/.opencode.json`
- `$XDG_CONFIG_HOME/opencode/.opencode.json`
- `./.opencode.json` (local directory)
### Environment Variables
You can configure OpenCode using environment variables:
| Environment Variable | Purpose |
| -------------------------- | ------------------------------------------------------ |
| `ANTHROPIC_API_KEY` | For Claude models |
| `OPENAI_API_KEY` | For OpenAI models |
| `GEMINI_API_KEY` | For Google Gemini models |
| `VERTEXAI_PROJECT` | For Google Cloud VertexAI (Gemini) |
| `VERTEXAI_LOCATION` | For Google Cloud VertexAI (Gemini) |
| `GROQ_API_KEY` | For Groq models |
| `AWS_ACCESS_KEY_ID` | For AWS Bedrock (Claude) |
| `AWS_SECRET_ACCESS_KEY` | For AWS Bedrock (Claude) |
| `AWS_REGION` | For AWS Bedrock (Claude) |
| `AZURE_OPENAI_ENDPOINT` | For Azure OpenAI models |
| `AZURE_OPENAI_API_KEY` | For Azure OpenAI models (optional when using Entra ID) |
| `AZURE_OPENAI_API_VERSION` | For Azure OpenAI models |
### Configuration File Structure
```json
```json title="opencode.json"
{
"data": {
"directory": ".opencode"
},
"providers": {
"openai": {
"apiKey": "your-api-key",
"disabled": false
},
"anthropic": {
"apiKey": "your-api-key",
"disabled": false
},
"groq": {
"apiKey": "your-api-key",
"disabled": false
},
"openrouter": {
"apiKey": "your-api-key",
"disabled": false
}
},
"agents": {
"primary": {
"model": "claude-3.7-sonnet",
"maxTokens": 5000
},
"task": {
"model": "claude-3.7-sonnet",
"maxTokens": 5000
},
"title": {
"model": "claude-3.7-sonnet",
"maxTokens": 80
}
},
"mcpServers": {
"example": {
"type": "stdio",
"command": "path/to/mcp-server",
"env": [],
"args": []
}
},
"lsp": {
"go": {
"disabled": false,
"command": "gopls"
}
},
"shell": {
"path": "/bin/zsh",
"args": ["-l"]
},
"debug": false,
"debugLSP": false
"$schema": "http://opencode.ai/config.json"
"theme": "opencode",
"model": "anthropic/claude-sonnet-4-20250514" // format is provider/model
"autoshare": false,
"autoupdate": true,
}
```
## Supported AI Models
#### Keybinds
OpenCode supports a variety of AI models from different providers:
You can configure custom keybinds, the values listed below are the defaults.
### OpenAI
- GPT-4.1 family (gpt-4.1, gpt-4.1-mini, gpt-4.1-nano)
- GPT-4.5 Preview
- GPT-4o family (gpt-4o, gpt-4o-mini)
- O1 family (o1, o1-pro, o1-mini)
- O3 family (o3, o3-mini)
- O4 Mini
### Anthropic
- Claude 3.5 Sonnet
- Claude 3.5 Haiku
- Claude 3.7 Sonnet
- Claude 3 Haiku
- Claude 3 Opus
### Google
- Gemini 2.5
- Gemini 2.5 Flash
- Gemini 2.0 Flash
- Gemini 2.0 Flash Lite
### AWS Bedrock
- Claude 3.7 Sonnet
### Groq
- Llama 4 Maverick (17b-128e-instruct)
- Llama 4 Scout (17b-16e-instruct)
- QWEN QWQ-32b
- Deepseek R1 distill Llama 70b
- Llama 3.3 70b Versatile
### Azure OpenAI
- GPT-4.1 family (gpt-4.1, gpt-4.1-mini, gpt-4.1-nano)
- GPT-4.5 Preview
- GPT-4o family (gpt-4o, gpt-4o-mini)
- O1 family (o1, o1-mini)
- O3 family (o3, o3-mini)
- O4 Mini
### Google Cloud VertexAI
- Gemini 2.5
- Gemini 2.5 Flash
## Using Bedrock Models
To use bedrock models with OpenCode you need three things.
1. Valid AWS credentials (the env vars: `AWS_SECRET_KEY_ID`, `AWS_SECRET_ACCESS_KEY` and `AWS_REGION`)
2. Access to the corresponding model in AWS Bedrock in your region.
a. You can request access in the AWS console on the Bedrock -> "Model access" page.
3. A correct configuration file. You don't need the `providers` key. Instead you have to prefix your models per agent with `bedrock.` and then a valid model. For now only Claude 3.7 is supported.
```json
```json title="opencode.json"
{
"agents": {
"primary": {
"model": "bedrock.claude-3.7-sonnet",
"maxTokens": 5000,
"reasoningEffort": ""
"$schema": "http://opencode.ai/config.json",
"keybinds": {
"leader": "ctrl+x",
"help": "<leader>h",
"editor_open": "<leader>e",
"session_new": "<leader>n",
"session_list": "<leader>l",
"session_share": "<leader>s",
"session_interrupt": "esc",
"session_compact": "<leader>c",
"tool_details": "<leader>d",
"model_list": "<leader>m",
"theme_list": "<leader>t",
"project_init": "<leader>i",
"input_clear": "ctrl+c",
"input_paste": "ctrl+v",
"input_submit": "enter",
"input_newline": "shift+enter,ctrl+j",
"history_previous": "up",
"history_next": "down",
"messages_page_up": "pgup",
"messages_page_down": "pgdown",
"messages_half_page_up": "ctrl+alt+u",
"messages_half_page_down": "ctrl+alt+d",
"messages_previous": "ctrl+alt+k",
"messages_next": "ctrl+alt+j",
"messages_first": "ctrl+g",
"messages_last": "ctrl+alt+g",
"app_exit": "ctrl+c,<leader>q"
}
}
```
#### MCP
```json title="opencode.json"
{
"$schema": "http://opencode.ai/config.json",
"mcp": {
"localmcp": {
"type": "local",
"command": ["bun", "x", "my-mcp-command"],
"environment": {
"MY_ENV_VAR": "my_env_var_value"
}
},
"task": {
"model": "bedrock.claude-3.7-sonnet",
"maxTokens": 5000,
"reasoningEffort": ""
},
"title": {
"model": "bedrock.claude-3.7-sonnet",
"maxTokens": 80,
"reasoningEffort": ""
"remotemcp": {
"type": "remote",
"url": "https://my-mcp-server.com"
}
}
}
```
## Interactive Mode Usage
#### Providers
```bash
# Start OpenCode
opencode
You can use opencode with any provider listed at [here](https://ai-sdk.dev/providers/ai-sdk-providers). Be sure to specify the npm package to use to load the provider. Remember most popular providers are preloaded from [models.dev](https://models.dev)
# Start with debug logging
opencode -d
# Start with a specific working directory
opencode -c /path/to/project
```
## Non-interactive Prompt Mode
You can run OpenCode in non-interactive mode by passing a prompt directly as a command-line argument or by piping text into the command. This is useful for scripting, automation, or when you want a quick answer without launching the full TUI.
```bash
# Run a single prompt and print the AI's response to the terminal
opencode -p "Explain the use of context in Go"
# Pipe input to OpenCode (equivalent to using -p flag)
echo "Explain the use of context in Go" | opencode
# Get response in JSON format
opencode -p "Explain the use of context in Go" -f json
# Or with piped input
echo "Explain the use of context in Go" | opencode -f json
# Run without showing the spinner
opencode -p "Explain the use of context in Go" -q
# Or with piped input
echo "Explain the use of context in Go" | opencode -q
# Enable verbose logging to stderr
opencode -p "Explain the use of context in Go" --verbose
# Or with piped input
echo "Explain the use of context in Go" | opencode --verbose
# Restrict the agent to only use specific tools
opencode -p "Explain the use of context in Go" --allowedTools=view,ls,glob
# Or with piped input
echo "Explain the use of context in Go" | opencode --allowedTools=view,ls,glob
# Prevent the agent from using specific tools
opencode -p "Explain the use of context in Go" --excludedTools=bash,edit
# Or with piped input
echo "Explain the use of context in Go" | opencode --excludedTools=bash,edit
```
In this mode, OpenCode will process your prompt, print the result to standard output, and then exit. All permissions are auto-approved for the session.
### Tool Restrictions
You can control which tools the AI assistant has access to in non-interactive mode:
- `--allowedTools`: Comma-separated list of tools that the agent is allowed to use. Only these tools will be available.
- `--excludedTools`: Comma-separated list of tools that the agent is not allowed to use. All other tools will be available.
These flags are mutually exclusive - you can use either `--allowedTools` or `--excludedTools`, but not both at the same time.
### Output Formats
OpenCode supports the following output formats in non-interactive mode:
| Format | Description |
| ------ | ------------------------------- |
| `text` | Plain text output (default) |
| `json` | Output wrapped in a JSON object |
The output format is implemented as a strongly-typed `OutputFormat` in the codebase, ensuring type safety and validation when processing outputs.
## Command-line Flags
| Flag | Short | Description |
| ----------------- | ----- | --------------------------------------------------- |
| `--help` | `-h` | Display help information |
| `--debug` | `-d` | Enable debug mode |
| `--cwd` | `-c` | Set current working directory |
| `--prompt` | `-p` | Run a single prompt in non-interactive mode |
| `--output-format` | `-f` | Output format for non-interactive mode (text, json) |
| `--quiet` | `-q` | Hide spinner in non-interactive mode |
| `--verbose` | | Display logs to stderr in non-interactive mode |
| `--allowedTools` | | Restrict the agent to only use specified tools |
| `--excludedTools` | | Prevent the agent from using specified tools |
## Keyboard Shortcuts
### Global Shortcuts
| Shortcut | Action |
| -------- | ------------------------------------------------------- |
| `Ctrl+C` | Quit application |
| `Ctrl+?` | Toggle help dialog |
| `?` | Toggle help dialog (when not in editing mode) |
| `Ctrl+L` | View logs |
| `Ctrl+A` | Switch session |
| `Ctrl+K` | Command dialog |
| `Ctrl+O` | Toggle model selection dialog |
| `Esc` | Close current overlay/dialog or return to previous mode |
### Chat Page Shortcuts
| Shortcut | Action |
| -------- | --------------------------------------- |
| `Ctrl+N` | Create new session |
| `Ctrl+X` | Cancel current operation/generation |
| `i` | Focus editor (when not in writing mode) |
| `Esc` | Exit writing mode and focus messages |
### Editor Shortcuts
| Shortcut | Action |
| ------------------- | ----------------------------------------- |
| `Ctrl+S` | Send message (when editor is focused) |
| `Enter` or `Ctrl+S` | Send message (when editor is not focused) |
| `Ctrl+E` | Open external editor |
| `Esc` | Blur editor and focus messages |
### Session Dialog Shortcuts
| Shortcut | Action |
| ---------- | ---------------- |
| `↑` or `k` | Previous session |
| `↓` or `j` | Next session |
| `Enter` | Select session |
| `Esc` | Close dialog |
### Model Dialog Shortcuts
| Shortcut | Action |
| ---------- | ----------------- |
| `↑` or `k` | Move up |
| `↓` or `j` | Move down |
| `←` or `h` | Previous provider |
| `→` or `l` | Next provider |
| `Esc` | Close dialog |
### Permission Dialog Shortcuts
| Shortcut | Action |
| ----------------------- | ---------------------------- |
| `←` or `left` | Switch options left |
| `→` or `right` or `tab` | Switch options right |
| `Enter` or `space` | Confirm selection |
| `a` | Allow permission |
| `A` | Allow permission for session |
| `d` | Deny permission |
### Logs Page Shortcuts
| Shortcut | Action |
| ------------------ | ------------------- |
| `Backspace` or `q` | Return to chat page |
## AI Assistant Tools
OpenCode's AI assistant has access to various tools to help with coding tasks:
### File and Code Tools
| Tool | Description | Parameters |
| ------------- | --------------------------- | ---------------------------------------------------------------------------------------- |
| `glob` | Find files by pattern | `pattern` (required), `path` (optional) |
| `grep` | Search file contents | `pattern` (required), `path` (optional), `include` (optional), `literal_text` (optional) |
| `ls` | List directory contents | `path` (optional), `ignore` (optional array of patterns) |
| `view` | View file contents | `file_path` (required), `offset` (optional), `limit` (optional) |
| `write` | Write to files | `file_path` (required), `content` (required) |
| `edit` | Edit files | Various parameters for file editing |
| `patch` | Apply patches to files | `file_path` (required), `diff` (required) |
| `diagnostics` | Get diagnostics information | `file_path` (optional) |
### Other Tools
| Tool | Description | Parameters |
| ------- | ------------------------------- | ----------------------------------------------------------- |
| `bash` | Execute shell commands | `command` (required), `timeout` (optional) |
| `fetch` | Fetch data from URLs | `url` (required), `format` (required), `timeout` (optional) |
| `agent` | Run sub-tasks with the AI agent | `prompt` (required) |
## Theming
OpenCode supports multiple themes for customizing the appearance of the terminal interface.
### Available Themes
The following predefined themes are available:
- `opencode` (default)
- `catppuccin`
- `dracula`
- `flexoki`
- `gruvbox`
- `monokai`
- `onedark`
- `tokyonight`
- `tron`
- `custom` (user-defined)
### Setting a Theme
You can set a theme in your `.opencode.json` configuration file:
```json
```json title="opencode.json"
{
"tui": {
"theme": "monokai"
}
}
```
### Custom Themes
You can define your own custom theme by setting the `theme` to `"custom"` and providing color definitions in the `customTheme` map:
```json
{
"tui": {
"theme": "custom",
"customTheme": {
"primary": "#ffcc00",
"secondary": "#00ccff",
"accent": { "dark": "#aa00ff", "light": "#ddccff" },
"error": "#ff0000"
}
}
}
```
#### Color Definition Formats
Custom theme colors support two formats:
1. **Simple Hex String**: A single hex color string (e.g., `"#aabbcc"`) that will be used for both light and dark terminal backgrounds.
2. **Adaptive Object**: An object with `dark` and `light` keys, each holding a hex color string. This allows for adaptive colors based on the terminal's background.
#### Available Color Keys
You can define any of the following color keys in your `customTheme`:
- Base colors: `primary`, `secondary`, `accent`
- Status colors: `error`, `warning`, `success`, `info`
- Text colors: `text`, `textMuted`, `textEmphasized`
- Background colors: `background`, `backgroundSecondary`, `backgroundDarker`
- Border colors: `borderNormal`, `borderFocused`, `borderDim`
- Diff view colors: `diffAdded`, `diffRemoved`, `diffContext`, etc.
You don't need to define all colors. Any undefined colors will fall back to the default "opencode" theme colors.
### Shell Configuration
OpenCode allows you to configure the shell used by the `bash` tool. By default, it uses:
1. The shell specified in the config file (if provided)
2. The shell from the `$SHELL` environment variable (if available)
3. Falls back to `/bin/bash` if neither of the above is available
To configure a custom shell, add a `shell` section to your `.opencode.json` configuration file:
```json
{
"shell": {
"path": "/bin/zsh",
"args": ["-l"]
}
}
```
You can specify any shell executable and custom arguments:
```json
{
"shell": {
"path": "/usr/bin/fish",
"args": []
}
}
```
## Architecture
OpenCode is built with a modular architecture:
- **cmd**: Command-line interface using Cobra
- **internal/app**: Core application services
- **internal/config**: Configuration management
- **internal/db**: Database operations and migrations
- **internal/llm**: LLM providers and tools integration
- **internal/tui**: Terminal UI components and layouts
- **internal/logging**: Logging infrastructure
- **internal/message**: Message handling
- **internal/session**: Session management
- **internal/lsp**: Language Server Protocol integration
## Custom Commands
OpenCode supports custom commands that can be created by users to quickly send predefined prompts to the AI assistant.
### Creating Custom Commands
Custom commands are predefined prompts stored as Markdown files in one of three locations:
1. **User Commands** (prefixed with `user:`):
```
$XDG_CONFIG_HOME/opencode/commands/
```
(typically `~/.config/opencode/commands/` on Linux/macOS)
or
```
$HOME/.opencode/commands/
```
2. **Project Commands** (prefixed with `project:`):
```
<PROJECT DIR>/.opencode/commands/
```
Each `.md` file in these directories becomes a custom command. The file name (without extension) becomes the command ID.
For example, creating a file at `~/.config/opencode/commands/prime-context.md` with content:
```markdown
RUN git ls-files
READ README.md
```
This creates a command called `user:prime-context`.
### Command Arguments
OpenCode supports named arguments in custom commands using placeholders in the format `$NAME` (where NAME consists of uppercase letters, numbers, and underscores, and must start with a letter).
For example:
```markdown
# Fetch Context for Issue $ISSUE_NUMBER
RUN gh issue view $ISSUE_NUMBER --json title,body,comments
RUN git grep --author="$AUTHOR_NAME" -n .
RUN grep -R "$SEARCH_PATTERN" $DIRECTORY
```
When you run a command with arguments, OpenCode will prompt you to enter values for each unique placeholder. Named arguments provide several benefits:
- Clear identification of what each argument represents
- Ability to use the same argument multiple times
- Better organization for commands with multiple inputs
### Organizing Commands
You can organize commands in subdirectories:
```
~/.config/opencode/commands/git/commit.md
```
This creates a command with ID `user:git:commit`.
### Using Custom Commands
1. Press `Ctrl+K` to open the command dialog
2. Select your custom command (prefixed with either `user:` or `project:`)
3. Press Enter to execute the command
The content of the command file will be sent as a message to the AI assistant.
## MCP (Model Context Protocol)
OpenCode implements the Model Context Protocol (MCP) to extend its capabilities through external tools. MCP provides a standardized way for the AI assistant to interact with external services and tools.
### MCP Features
- **External Tool Integration**: Connect to external tools and services via a standardized protocol
- **Tool Discovery**: Automatically discover available tools from MCP servers
- **Multiple Connection Types**:
- **Stdio**: Communicate with tools via standard input/output
- **SSE**: Communicate with tools via Server-Sent Events
- **Security**: Permission system for controlling access to MCP tools
### Configuring MCP Servers
MCP servers are defined in the configuration file under the `mcpServers` section:
```json
{
"mcpServers": {
"example": {
"type": "stdio",
"command": "path/to/mcp-server",
"env": [],
"args": []
},
"web-example": {
"type": "sse",
"url": "https://example.com/mcp",
"headers": {
"Authorization": "Bearer token"
"$schema": "https://opencode.ai/config.json",
"provider": {
"ollama": {
"npm": "@ai-sdk/openai-compatible",
"options": {
"baseURL": "http://localhost:11434/v1"
},
"models": {
"llama2": {}
}
}
}
}
```
### MCP Tool Usage
### Contributing
Once configured, MCP tools are automatically available to the AI assistant alongside built-in tools. They follow the same permission model as other tools, requiring user approval before execution.
To run opencode locally you need.
## LSP (Language Server Protocol)
- Bun
- Golang 1.24.x
OpenCode integrates with Language Server Protocol to provide code intelligence features across multiple programming languages.
To run.
### LSP Features
```bash
$ bun install
$ bun run packages/opencode/src/index.ts
```
- **Multi-language Support**: Connect to language servers for different programming languages
- **Diagnostics**: Receive error checking and linting information
- **File Watching**: Automatically notify language servers of file changes
### FAQ
### Configuring LSP
#### How do I use this with OpenRouter?
Language servers are configured in the configuration file under the `lsp` section:
OpenRouter is not in the Models.dev database yet, but you can configure it manually.
```json
```json title="opencode.json"
{
"lsp": {
"go": {
"disabled": false,
"command": "gopls"
},
"typescript": {
"disabled": false,
"command": "typescript-language-server",
"args": ["--stdio"]
"$schema": "https://opencode.ai/config.json",
"provider": {
"openrouter": {
"npm": "@openrouter/ai-sdk-provider",
"name": "OpenRouter",
"options": {},
"models": {
"anthropic/claude-3.5-sonnet": {
"name": "Claude 3.5 Sonnet"
}
}
}
}
}
```
### LSP Integration with AI
And then to configure an api key you can do `opencode auth login` and select "Other -> 'openrouter'"
The AI assistant can access LSP features through the `diagnostics` tool, allowing it to:
#### How is this different than Claude Code?
- Check for errors in your code
- Suggest fixes based on diagnostics
It's very similar to Claude Code in terms of capability. Here are the key differences:
While the LSP client implementation supports the full LSP protocol (including completions, hover, definition, etc.), currently only diagnostics are exposed to the AI assistant.
- 100% open source
- Not coupled to any provider. Although Anthropic is recommended, opencode can be used with OpenAI, Google or even local models. As models evolve the gaps between them will close and pricing will drop so being provider agnostic is important.
- A focus on TUI. opencode is built by neovim users and the creators of [terminal.shop](https://terminal.shop); we are going to push the limits of what's possible in the terminal.
- A client/server architecture. This for example can allow opencode to run on your computer, while you can drive it remotely from a mobile app. Meaning that the TUI frontend is just one of the possible clients.
## Development
#### What about Windows support?
### Prerequisites
There are some minor problems blocking opencode from working on windows. We are working on on them now. You'll need to use WSL for now.
- Go 1.24.0 or higher
#### What's the other repo?
### Building from Source
The other confusingly named repo has no relation to this one. You can [read the story behind it here](https://x.com/thdxr/status/1933561254481666466).
```bash
# Clone the repository
git clone https://github.com/sst/opencode.git
cd opencode
---
# Build
go build -o opencode
# Run
./opencode
```
## Acknowledgments
OpenCode gratefully acknowledges the contributions and support from these key individuals:
- [@isaacphi](https://github.com/isaacphi) - For the [mcp-language-server](https://github.com/isaacphi/mcp-language-server) project which provided the foundation for our LSP client implementation
- [@adamdottv](https://github.com/adamdottv) - For the design direction and UI/UX architecture
Special thanks to the broader open source community whose tools and libraries have made this project possible.
## License
OpenCode is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
## Contributing
Contributions are welcome! Here's how you can contribute:
1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add some amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request
Please make sure to update tests as appropriate and follow the existing code style.
**Join our community** [YouTube](https://www.youtube.com/c/sst-dev) | [X.com](https://x.com/SST_dev)

268
bun.lock
View File

@@ -5,7 +5,7 @@
"name": "opencode",
"devDependencies": {
"prettier": "3.5.3",
"sst": "3.16.0",
"sst": "3.17.6",
},
},
"packages/function": {
@@ -21,36 +21,44 @@
"name": "opencode",
"version": "0.0.0",
"dependencies": {
"@clack/prompts": "0.11.0",
"@flystorage/file-storage": "1.1.0",
"@flystorage/local-fs": "1.1.0",
"@hono/zod-validator": "0.5.0",
"@openauthjs/openauth": "0.4.3",
"@standard-schema/spec": "1.0.0",
"ai": "catalog:",
"cac": "6.7.14",
"decimal.js": "10.5.0",
"diff": "8.0.2",
"env-paths": "3.0.0",
"hono": "4.7.10",
"hono-openapi": "0.4.8",
"open": "10.1.2",
"remeda": "2.22.3",
"ts-lsp-client": "1.0.3",
"turndown": "7.2.0",
"vscode-jsonrpc": "8.2.1",
"vscode-languageclient": "8",
"xdg-basedir": "5.1.0",
"yargs": "18.0.0",
"zod": "catalog:",
"zod-openapi": "4.2.4",
},
"devDependencies": {
"@ai-sdk/anthropic": "1.2.12",
"@tsconfig/bun": "1.0.7",
"@types/bun": "latest",
"@types/turndown": "5.0.5",
"@types/yargs": "17.0.33",
"typescript": "catalog:",
"zod-to-json-schema": "3.24.5",
},
},
"packages/web": {
"name": "@opencode/web",
"version": "0.0.1",
"dependencies": {
"@astrojs/cloudflare": "^12.5.4",
"@astrojs/markdown-remark": "6.3.1",
"@astrojs/solid-js": "5.1.0",
"@astrojs/starlight": "0.34.3",
@@ -60,15 +68,18 @@
"ai": "catalog:",
"astro": "5.7.13",
"diff": "8.0.2",
"js-base64": "3.7.7",
"luxon": "3.6.1",
"marked": "15.0.12",
"rehype-autolink-headings": "7.1.0",
"sharp": "0.32.5",
"shiki": "3.4.2",
"solid-js": "1.9.7",
"toolbeam-docs-theme": "0.2.4",
"toolbeam-docs-theme": "0.3.0",
},
"devDependencies": {
"@types/node": "catalog:",
"opencode": "workspace:*",
"typescript": "catalog:",
},
},
@@ -77,26 +88,35 @@
"sharp",
"esbuild",
],
"patchedDependencies": {
"ai@4.3.16": "patches/ai@4.3.16.patch",
},
"overrides": {
"zod": "3.24.2",
},
"catalog": {
"@types/node": "22.13.9",
"ai": "5.0.0-alpha.7",
"ai": "4.3.16",
"typescript": "5.8.2",
"zod": "3.24.2",
},
"packages": {
"@ai-sdk/gateway": ["@ai-sdk/gateway@1.0.0-alpha.7", "", { "dependencies": { "@ai-sdk/provider": "2.0.0-alpha.7", "@ai-sdk/provider-utils": "3.0.0-alpha.7" }, "peerDependencies": { "zod": "^3.24.0" } }, "sha512-gz1V165eiJnQIexfLyKm11vimrmQ3zdcJhPpjeLFmDU9wrvZwLuklfZ0WgfYSb+EjiP1cKypwt6JSGvWkfKIAQ=="],
"@ai-sdk/anthropic": ["@ai-sdk/anthropic@1.2.12", "", { "dependencies": { "@ai-sdk/provider": "1.1.3", "@ai-sdk/provider-utils": "2.2.8" }, "peerDependencies": { "zod": "^3.0.0" } }, "sha512-YSzjlko7JvuiyQFmI9RN1tNZdEiZxc+6xld/0tq/VkJaHpEzGAb1yiNxxvmYVcjvfu/PcvCxAAYXmTYQQ63IHQ=="],
"@ai-sdk/provider": ["@ai-sdk/provider@2.0.0-alpha.7", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-lhdrARU3SSmt5p/GNNK7VhazvZpKSCIOjpHUfX7f5jIhVGi/vvlxP1rD6Go57nn1MtuGKNqL04AebSRFDQsQbw=="],
"@ai-sdk/provider": ["@ai-sdk/provider@1.1.3", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-qZMxYJ0qqX/RfnuIaab+zp8UAeJn/ygXXAffR5I4N0n1IrvA6qBsjc8hXLmBiMV2zoXlifkacF7sEFnYnjBcqg=="],
"@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@3.0.0-alpha.7", "", { "dependencies": { "@ai-sdk/provider": "2.0.0-alpha.7", "@standard-schema/spec": "^1.0.0", "zod-to-json-schema": "^3.24.1" }, "peerDependencies": { "zod": "^3.23.8" } }, "sha512-AYkT3jskmo7Lwzijo/yHKD1jC+UZizsROO8ULTg9aJZUwR4ABZzAxh4NxDIEy4TWRfBGufp+/9ICHAn6pkU71w=="],
"@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@2.2.8", "", { "dependencies": { "@ai-sdk/provider": "1.1.3", "nanoid": "^3.3.8", "secure-json-parse": "^2.7.0" }, "peerDependencies": { "zod": "^3.23.8" } }, "sha512-fqhG+4sCVv8x7nFzYnFo19ryhAa3w096Kmc3hWxMQfW/TubPOmt3A6tYZhl4mUfQWWQMsuSkLrtjlWuXBVSGQA=="],
"@ai-sdk/react": ["@ai-sdk/react@1.2.12", "", { "dependencies": { "@ai-sdk/provider-utils": "2.2.8", "@ai-sdk/ui-utils": "1.2.11", "swr": "^2.2.5", "throttleit": "2.1.0" }, "peerDependencies": { "react": "^18 || ^19 || ^19.0.0-rc", "zod": "^3.23.8" }, "optionalPeers": ["zod"] }, "sha512-jK1IZZ22evPZoQW3vlkZ7wvjYGYF+tRBKXtrcolduIkQ/m/sOAVcVeVDUDvh1T91xCnWCdUGCPZg2avZ90mv3g=="],
"@ai-sdk/ui-utils": ["@ai-sdk/ui-utils@1.2.11", "", { "dependencies": { "@ai-sdk/provider": "1.1.3", "@ai-sdk/provider-utils": "2.2.8", "zod-to-json-schema": "^3.24.1" }, "peerDependencies": { "zod": "^3.23.8" } }, "sha512-3zcwCc8ezzFlwp3ZD15wAPjf2Au4s3vAbKsXQVyhxODHcmu0iyPO2Eua6D/vicq/AUm/BAo60r97O6HU+EI0+w=="],
"@ampproject/remapping": ["@ampproject/remapping@2.3.0", "", { "dependencies": { "@jridgewell/gen-mapping": "^0.3.5", "@jridgewell/trace-mapping": "^0.3.24" } }, "sha512-30iZtAPgz+LTIYoeivqYo853f02jBYSd5uGnGpkFV0M3xOt9aN73erkgYAmZU43x4VfqcnLxW9Kpg3R5LC4YYw=="],
"@apidevtools/json-schema-ref-parser": ["@apidevtools/json-schema-ref-parser@11.9.3", "", { "dependencies": { "@jsdevtools/ono": "^7.1.3", "@types/json-schema": "^7.0.15", "js-yaml": "^4.1.0" } }, "sha512-60vepv88RwcJtSHrD6MjIL6Ta3SOYbgfnkHb+ppAVK+o9mXprRtulx7VlRl3lN3bbvysAfCS7WMVfhUYemB0IQ=="],
"@astrojs/cloudflare": ["@astrojs/cloudflare@12.5.4", "", { "dependencies": { "@astrojs/internal-helpers": "0.6.1", "@astrojs/underscore-redirects": "0.6.1", "@cloudflare/workers-types": "^4.20250507.0", "tinyglobby": "^0.2.13", "vite": "^6.3.5", "wrangler": "^4.14.1" }, "peerDependencies": { "astro": "^5.0.0" } }, "sha512-WKUeMP2tIbddEu0tlVEPj8o9m/8CJB6who3a3jupuIyR56ltmW924ZOMYtp/C9uxH7KeDJXrMszRj3LHs9U97w=="],
"@astrojs/compiler": ["@astrojs/compiler@2.12.0", "", {}, "sha512-7bCjW6tVDpUurQLeKBUN9tZ5kSv5qYrGmcn0sG0IwacL7isR2ZbyyA3AdZ4uxsuUFOS2SlgReTH7wkxO6zpqWA=="],
"@astrojs/internal-helpers": ["@astrojs/internal-helpers@0.6.1", "", {}, "sha512-l5Pqf6uZu31aG+3Lv8nl/3s4DbUzdlxTWDof4pEpto6GUJNhhCbelVi9dEyurOVyqaelwmS9oSyOWOENSfgo9A=="],
@@ -115,6 +135,8 @@
"@astrojs/telemetry": ["@astrojs/telemetry@3.2.1", "", { "dependencies": { "ci-info": "^4.2.0", "debug": "^4.4.0", "dlv": "^1.1.3", "dset": "^3.1.4", "is-docker": "^3.0.0", "is-wsl": "^3.1.0", "which-pm-runs": "^1.1.0" } }, "sha512-SSVM820Jqc6wjsn7qYfV9qfeQvePtVc1nSofhyap7l0/iakUKywj3hfy3UJAOV4sGV4Q/u450RD4AaCaFvNPlg=="],
"@astrojs/underscore-redirects": ["@astrojs/underscore-redirects@0.6.1", "", {}, "sha512-4bMLrs2KW+8/vHEE5Ffv2HbxCbbgXO+2N6MpoCsMXUlUoi7pgEEx8kbkzMXJ2dZtWF3gvwm9lvgjnFeanC2LGg=="],
"@babel/code-frame": ["@babel/code-frame@7.27.1", "", { "dependencies": { "@babel/helper-validator-identifier": "^7.27.1", "js-tokens": "^4.0.0", "picocolors": "^1.1.1" } }, "sha512-cjQ7ZlQ0Mv3b47hABuTevyTuYN4i+loJKGeV9flcCgIK37cCXRh+L1bd3iBHlynerhQ7BhCkn2BPbQUL+rGqFg=="],
"@babel/compat-data": ["@babel/compat-data@7.27.3", "", {}, "sha512-V42wFfx1ymFte+ecf6iXghnnP8kWTO+ZLXIyZq+1LAXHHvTZdVxicn4yiVYdYMGaCO3tmqub11AorKkv+iodqw=="],
@@ -153,8 +175,28 @@
"@capsizecss/unpack": ["@capsizecss/unpack@2.4.0", "", { "dependencies": { "blob-to-buffer": "^1.2.8", "cross-fetch": "^3.0.4", "fontkit": "^2.0.2" } }, "sha512-GrSU71meACqcmIUxPYOJvGKF0yryjN/L1aCuE9DViCTJI7bfkjgYDPD1zbNDcINJwSSP6UaBZY9GAbYDO7re0Q=="],
"@clack/core": ["@clack/core@0.5.0", "", { "dependencies": { "picocolors": "^1.0.0", "sisteransi": "^1.0.5" } }, "sha512-p3y0FIOwaYRUPRcMO7+dlmLh8PSRcrjuTndsiA0WAFbWES0mLZlrjVoBRZ9DzkPFJZG6KGkJmoEAY0ZcVWTkow=="],
"@clack/prompts": ["@clack/prompts@0.11.0", "", { "dependencies": { "@clack/core": "0.5.0", "picocolors": "^1.0.0", "sisteransi": "^1.0.5" } }, "sha512-pMN5FcrEw9hUkZA4f+zLlzivQSeQf5dRGJjSUbvVYDLvpKCdQx5OaknvKzgbtXOizhP+SJJJjqEbOe55uKKfAw=="],
"@cloudflare/kv-asset-handler": ["@cloudflare/kv-asset-handler@0.4.0", "", { "dependencies": { "mime": "^3.0.0" } }, "sha512-+tv3z+SPp+gqTIcImN9o0hqE9xyfQjI1XD9pL6NuKjua9B1y7mNYv0S9cP+QEbA4ppVgGZEmKOvHX5G5Ei1CVA=="],
"@cloudflare/unenv-preset": ["@cloudflare/unenv-preset@2.3.2", "", { "peerDependencies": { "unenv": "2.0.0-rc.17", "workerd": "^1.20250508.0" }, "optionalPeers": ["workerd"] }, "sha512-MtUgNl+QkQyhQvv5bbWP+BpBC1N0me4CHHuP2H4ktmOMKdB/6kkz/lo+zqiA4mEazb4y+1cwyNjVrQ2DWeE4mg=="],
"@cloudflare/workerd-darwin-64": ["@cloudflare/workerd-darwin-64@1.20250525.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-L5l+7sSJJT2+riR5rS3Q3PKNNySPjWfRIeaNGMVRi1dPO6QPi4lwuxfRUFNoeUdilZJUVPfSZvTtj9RedsKznQ=="],
"@cloudflare/workerd-darwin-arm64": ["@cloudflare/workerd-darwin-arm64@1.20250525.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-Y3IbIdrF/vJWh/WBvshwcSyUh175VAiLRW7963S1dXChrZ1N5wuKGQm9xY69cIGVtitpMJWWW3jLq7J/Xxwm0Q=="],
"@cloudflare/workerd-linux-64": ["@cloudflare/workerd-linux-64@1.20250525.0", "", { "os": "linux", "cpu": "x64" }, "sha512-KSyQPAby+c6cpENoO0ayCQlY6QIh28l/+QID7VC1SLXfiNHy+hPNsH1vVBTST6CilHVAQSsy9tCZ9O9XECB8yg=="],
"@cloudflare/workerd-linux-arm64": ["@cloudflare/workerd-linux-arm64@1.20250525.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-Nt0FUxS2kQhJUea4hMCNPaetkrAFDhPnNX/ntwcqVlGgnGt75iaAhupWJbU0GB+gIWlKeuClUUnDZqKbicoKyg=="],
"@cloudflare/workerd-windows-64": ["@cloudflare/workerd-windows-64@1.20250525.0", "", { "os": "win32", "cpu": "x64" }, "sha512-mwTj+9f3uIa4NEXR1cOa82PjLa6dbrb3J+KCVJFYIaq7e63VxEzOchCXS4tublT2pmOhmFqkgBMXrxozxNkR2Q=="],
"@cloudflare/workers-types": ["@cloudflare/workers-types@4.20250522.0", "", {}, "sha512-9RIffHobc35JWeddzBguGgPa4wLDr5x5F94+0/qy7LiV6pTBQ/M5qGEN9VA16IDT3EUpYI0WKh6VpcmeVEtVtw=="],
"@cspotcode/source-map-support": ["@cspotcode/source-map-support@0.8.1", "", { "dependencies": { "@jridgewell/trace-mapping": "0.3.9" } }, "sha512-IchNf6dN4tHoMFIn/7OE8LWZ19Y6q/67Bmf6vnGREv8RSbBVb9LPJxEcnwrcwX6ixSvaiGoomAUvu4YSxXrVgw=="],
"@ctrl/tinycolor": ["@ctrl/tinycolor@4.1.0", "", {}, "sha512-WyOx8cJQ+FQus4Mm4uPIZA64gbk3Wxh0so5Lcii0aJifqwoVOlfFtorjLE0Hen4OYyHZMXDWqMmaQemBhgxFRQ=="],
"@emnapi/runtime": ["@emnapi/runtime@1.4.3", "", { "dependencies": { "tslib": "^2.4.0" } }, "sha512-pBPWdu6MLKROBX05wSNKcNb++m5Er+KQ9QkB+WVM+pW2Kx9hoSrVTnu3BdkI5eBLZoKu/J6mW/B6i6bJB2ytXQ=="],
@@ -217,6 +259,8 @@
"@expressive-code/plugin-text-markers": ["@expressive-code/plugin-text-markers@0.41.2", "", { "dependencies": { "@expressive-code/core": "^0.41.2" } }, "sha512-JFWBz2qYxxJOJkkWf96LpeolbnOqJY95TvwYc0hXIHf9oSWV0h0SY268w/5N3EtQaD9KktzDE+VIVwb9jdb3nw=="],
"@fastify/busboy": ["@fastify/busboy@2.1.1", "", {}, "sha512-vBZP4NlzfOlerQTnba4aqZoMhE/a9HY7HRqoOPaETQcSQuWEIyZMHGfVu6w9wGtGK5fED5qRs2DteVCjOH60sA=="],
"@flystorage/dynamic-import": ["@flystorage/dynamic-import@1.0.0", "", {}, "sha512-CIbIUrBdaPFyKnkVBaqzksvzNtsMSXITR/G/6zlil3MBnPFq2LX+X4Mv5p2XOmv/3OulFs/ff2SNb+5dc2Twtg=="],
"@flystorage/file-storage": ["@flystorage/file-storage@1.1.0", "", {}, "sha512-25Gd5EsXDmhHrK5orpRuVqebQms1Cm9m5ACMZ0sVDX+Sbl1V0G88CbcWt7mEoWRYLvQ1U072htqg6Sav76ZlVA=="],
@@ -275,7 +319,7 @@
"@jridgewell/sourcemap-codec": ["@jridgewell/sourcemap-codec@1.5.0", "", {}, "sha512-gv3ZRaISU3fjPAgNsriBRqGWQL6quFx04YMPW/zD8XMLsU32mhCCbfbO6KZFLjvYpCZ8zyDEgqsgf+PwPaM7GQ=="],
"@jridgewell/trace-mapping": ["@jridgewell/trace-mapping@0.3.25", "", { "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", "@jridgewell/sourcemap-codec": "^1.4.14" } }, "sha512-vNk6aEwybGtawWmy/PzwnGDOjCkLWSD2wqvjGGAgOAwCGWySYXfYoxt00IJkTF+8Lb57DwOb3Aa0o9CApepiYQ=="],
"@jridgewell/trace-mapping": ["@jridgewell/trace-mapping@0.3.9", "", { "dependencies": { "@jridgewell/resolve-uri": "^3.0.3", "@jridgewell/sourcemap-codec": "^1.4.10" } }, "sha512-3Belt6tdc8bPgAtbcmdtNJlirVoTmEb5e2gC94PnkwEW9jI6CAHUeoG85tjWP5WquqfavoMtMwiG4P926ZKKuQ=="],
"@jsdevtools/ono": ["@jsdevtools/ono@7.1.3", "", {}, "sha512-4JQNk+3mVzK3xh2rqd6RB4J46qUR19azEHBneZyTZM+c456qOrbbM/5xcR8huNCCcbVt7+UmizG6GuUvPvKUYg=="],
@@ -285,14 +329,24 @@
"@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.6.1", "", { "dependencies": { "content-type": "^1.0.5", "cors": "^2.8.5", "eventsource": "^3.0.2", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "pkce-challenge": "^4.1.0", "raw-body": "^3.0.0", "zod": "^3.23.8", "zod-to-json-schema": "^3.24.1" } }, "sha512-oxzMzYCkZHMntzuyerehK3fV6A2Kwh5BD6CGEJSVDU2QNEhfLOptf2X7esQgaHZXHZY0oHmMsOtIDLP71UJXgA=="],
"@openauthjs/openauth": ["@openauthjs/openauth@0.4.3", "", { "dependencies": { "@standard-schema/spec": "1.0.0-beta.3", "aws4fetch": "1.0.20", "jose": "5.9.6" }, "peerDependencies": { "arctic": "^2.2.2", "hono": "^4.0.0" } }, "sha512-RlnjqvHzqcbFVymEwhlUEuac4utA5h4nhSK/i2szZuQmxTIqbGUxZ+nM+avM+VV4Ing+/ZaNLKILoXS3yrkOOw=="],
"@opencode/function": ["@opencode/function@workspace:packages/function"],
"@opencode/web": ["@opencode/web@workspace:packages/web"],
"@opentelemetry/api": ["@opentelemetry/api@1.9.0", "", {}, "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg=="],
"@oslojs/asn1": ["@oslojs/asn1@1.0.0", "", { "dependencies": { "@oslojs/binary": "1.0.0" } }, "sha512-zw/wn0sj0j0QKbIXfIlnEcTviaCzYOY3V5rAyjR6YtOByFtJiT574+8p9Wlach0lZH9fddD4yb9laEAIl4vXQA=="],
"@oslojs/binary": ["@oslojs/binary@1.0.0", "", {}, "sha512-9RCU6OwXU6p67H4NODbuxv2S3eenuQ4/WFLrsq+K/k682xrznH5EVWA7N4VFk9VYVcbFtKqur5YQQZc0ySGhsQ=="],
"@oslojs/crypto": ["@oslojs/crypto@1.0.1", "", { "dependencies": { "@oslojs/asn1": "1.0.0", "@oslojs/binary": "1.0.0" } }, "sha512-7n08G8nWjAr/Yu3vu9zzrd0L9XnrJfpMioQcvCMxBIiF5orECHe5/3J0jmXRVvgfqMm/+4oxlQ+Sq39COYLcNQ=="],
"@oslojs/encoding": ["@oslojs/encoding@1.1.0", "", {}, "sha512-70wQhgYmndg4GCPxPPxPGevRKqTIJ2Nh4OkiMWmDAVYsTQ+Ta7Sq+rPevXyXGdzr30/qZBnyOalCszoMxlyldQ=="],
"@oslojs/jwt": ["@oslojs/jwt@0.2.0", "", { "dependencies": { "@oslojs/encoding": "0.4.1" } }, "sha512-bLE7BtHrURedCn4Mco3ma9L4Y1GR2SMBuIvjWr7rmQ4/W/4Jy70TIAgZ+0nIlk0xHz1vNP8x8DCns45Sb2XRbg=="],
"@pagefind/darwin-arm64": ["@pagefind/darwin-arm64@1.3.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-365BEGl6ChOsauRjyVpBjXybflXAOvoMROw3TucAROHIcdBvXk9/2AmEvGFU0r75+vdQI4LJdJdpH4Y6Yqaj4A=="],
"@pagefind/darwin-x64": ["@pagefind/darwin-x64@1.3.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-zlGHA23uuXmS8z3XxEGmbHpWDxXfPZ47QS06tGUq0HDcZjXjXHeLG+cboOy828QIV5FXsm9MjfkP5e4ZNbOkow=="],
@@ -381,10 +435,12 @@
"@types/babel__traverse": ["@types/babel__traverse@7.20.7", "", { "dependencies": { "@babel/types": "^7.20.7" } }, "sha512-dkO5fhS7+/oos4ciWxyEyjWe48zmG6wbCheo/G2ZnHx4fs3EU6YC6UM8rk56gAjNJ9P3MTH2jo5jb92/K6wbng=="],
"@types/bun": ["@types/bun@1.2.15", "", { "dependencies": { "bun-types": "1.2.15" } }, "sha512-U1ljPdBEphF0nw1MIk0hI7kPg7dFdPyM7EenHsp6W5loNHl7zqy6JQf/RKCgnUn2KDzUpkBwHPnEJEjII594bA=="],
"@types/bun": ["@types/bun@1.2.16", "", { "dependencies": { "bun-types": "1.2.16" } }, "sha512-1aCZJ/6nSiViw339RsaNhkNoEloLaPzZhxMOYEa7OzRzO41IGg5n/7I43/ZIAW/c+Q6cT12Vf7fOZOoVIzb5BQ=="],
"@types/debug": ["@types/debug@4.1.12", "", { "dependencies": { "@types/ms": "*" } }, "sha512-vIChWdVG3LG1SMxEvI/AK+FWJthlrqlTu7fbrlywTkkaONwk/UAGaULXRlf8vkzFBLVm0zkMdCquhL5aOjhXPQ=="],
"@types/diff-match-patch": ["@types/diff-match-patch@1.0.36", "", {}, "sha512-xFdR6tkm0MWvBfO8xXCSsinYxHcqkQUlcHeSpMC2ukzOb6lwQAfDmW+Qt0AvlGd8HpsS28qKsB+oPeJn9I39jg=="],
"@types/estree": ["@types/estree@1.0.7", "", {}, "sha512-w28IoSUCJpidD/TGviZwwMJckNESJZXFu7NBZ5YJ4mEUnNraUn9Pm8HSZm/jDF1pDWYKspWE7oVphigUPRakIQ=="],
"@types/estree-jsx": ["@types/estree-jsx@1.0.5", "", { "dependencies": { "@types/estree": "*" } }, "sha512-52CcUVNFyfb1A2ALocQw/Dd1BQFNmSdkuC3BkZ6iqhdMfQz7JWOFRuJFloOzjk+6WijU56m9oKXFAXc7o3Towg=="],
@@ -415,6 +471,10 @@
"@types/unist": ["@types/unist@3.0.3", "", {}, "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q=="],
"@types/yargs": ["@types/yargs@17.0.33", "", { "dependencies": { "@types/yargs-parser": "*" } }, "sha512-WpxBCKWPLr4xSsHgz511rFJAM+wS28w2zEO1QDNY5zM/S8ok70NNfztH0xwhqKyaK0OHCbN98LDAZuy1ctxDkA=="],
"@types/yargs-parser": ["@types/yargs-parser@21.0.3", "", {}, "sha512-I4q9QU9MQv4oEOz4tAHJtNz1cwuLxn2F3xcc2iV5WdqLPpUnj30aUuxt1mAxYTG+oe8CZMV/+6rU4S4gRDzqtQ=="],
"@ungap/structured-clone": ["@ungap/structured-clone@1.3.0", "", {}, "sha512-WmoN8qaIAo7WTYWbAZuG8PYEhn5fkz7dZrqTBZ7dtt//lL2Gwms1IcnQ5yHqjDfX8Ft5j4YzDM23f87zBfDe9g=="],
"accepts": ["accepts@2.0.0", "", { "dependencies": { "mime-types": "^3.0.0", "negotiator": "^1.0.0" } }, "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng=="],
@@ -423,7 +483,9 @@
"acorn-jsx": ["acorn-jsx@5.3.2", "", { "peerDependencies": { "acorn": "^6.0.0 || ^7.0.0 || ^8.0.0" } }, "sha512-rq9s+JNhf0IChjtDXxllJ7g41oZk5SlXtp0LHwyA5cejwn7vKmKp4pPri6YEePv2PU65sAsegbXtIinmDFDXgQ=="],
"ai": ["ai@5.0.0-alpha.7", "", { "dependencies": { "@ai-sdk/gateway": "1.0.0-alpha.7", "@ai-sdk/provider": "2.0.0-alpha.7", "@ai-sdk/provider-utils": "3.0.0-alpha.7", "@opentelemetry/api": "1.9.0" }, "peerDependencies": { "zod": "^3.23.8" } }, "sha512-ShCk3frIMdVtK9knvWKiFS7N6Vwnf8mLMv670+T//W9oqfoetSVPBhTF6Dy+oDM/bjVSsBf1BuYImLDvHICOIQ=="],
"acorn-walk": ["acorn-walk@8.3.2", "", {}, "sha512-cjkyv4OtNCIeqhHrfS81QWXoCBPExR/J62oyEqepVw8WaQeSqpW2uhuLPh1m9eWhDuOo/jUXVTlifvesOWp/4A=="],
"ai": ["ai@4.3.16", "", { "dependencies": { "@ai-sdk/provider": "1.1.3", "@ai-sdk/provider-utils": "2.2.8", "@ai-sdk/react": "1.2.12", "@ai-sdk/ui-utils": "1.2.11", "@opentelemetry/api": "1.9.0", "jsondiffpatch": "0.6.0" }, "peerDependencies": { "react": "^18 || ^19 || ^19.0.0-rc", "zod": "^3.23.8" }, "optionalPeers": ["react"] }, "sha512-KUDwlThJ5tr2Vw0A1ZkbDKNME3wzWhuVfAOwIvFUzl1TPVDFAXDFTXio3p+jaKneB+dKNCvFFlolYmmgHttG1g=="],
"ansi-align": ["ansi-align@3.0.1", "", { "dependencies": { "string-width": "^4.1.0" } }, "sha512-IOfwwBF5iczOjp/WeY4YxyjqAFMQoZufdQWDd19SEExbVLNXqvpzSJ/M7Za4/sCPmQ0+GRquoA7bGcINcxew6w=="],
@@ -433,6 +495,8 @@
"anymatch": ["anymatch@3.1.3", "", { "dependencies": { "normalize-path": "^3.0.0", "picomatch": "^2.0.4" } }, "sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw=="],
"arctic": ["arctic@2.3.4", "", { "dependencies": { "@oslojs/crypto": "1.0.1", "@oslojs/encoding": "1.1.0", "@oslojs/jwt": "0.2.0" } }, "sha512-+p30BOWsctZp+CVYCt7oAean/hWGW42sH5LAcRQX56ttEkFJWbzXBhmSpibbzwSJkRrotmsA+oAoJoVsU0f5xA=="],
"arg": ["arg@5.0.2", "", {}, "sha512-PYjyFOLKQ9y57JvQ6QLo8dAgNqswh8M1RMJYdQduT6xbWSgK36P/Z/v+p888pM69jMMfS8Xd8F6I1kQ/I9HUGg=="],
"argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],
@@ -443,6 +507,8 @@
"array-iterate": ["array-iterate@2.0.1", "", {}, "sha512-I1jXZMjAgCMmxT4qxXfPXa6SthSoE8h6gkSI9BGGNv8mP8G/v0blc+qFnZu6K42vTOiuME596QaLO0TP3Lk0xg=="],
"as-table": ["as-table@1.0.55", "", { "dependencies": { "printable-characters": "^1.0.42" } }, "sha512-xvsWESUJn0JN421Xb9MQw6AsMHRCUknCe0Wjlxvjud80mU4E6hQf1A6NzQKcYNmYw62MfzEtXc+badstZP3JpQ=="],
"astring": ["astring@1.9.0", "", { "bin": { "astring": "bin/astring" } }, "sha512-LElXdjswlqjWrPpJFg1Fx4wpkOCxj1TDHlSV4PlaRxHGWko024xICaa97ZkMfs6DRKlCguiAI+rbXv5GWwXIkg=="],
"astro": ["astro@5.7.13", "", { "dependencies": { "@astrojs/compiler": "^2.11.0", "@astrojs/internal-helpers": "0.6.1", "@astrojs/markdown-remark": "6.3.1", "@astrojs/telemetry": "3.2.1", "@capsizecss/unpack": "^2.4.0", "@oslojs/encoding": "^1.1.0", "@rollup/pluginutils": "^5.1.4", "acorn": "^8.14.1", "aria-query": "^5.3.2", "axobject-query": "^4.1.0", "boxen": "8.0.1", "ci-info": "^4.2.0", "clsx": "^2.1.1", "common-ancestor-path": "^1.0.1", "cookie": "^1.0.2", "cssesc": "^3.0.0", "debug": "^4.4.0", "deterministic-object-hash": "^2.0.2", "devalue": "^5.1.1", "diff": "^5.2.0", "dlv": "^1.1.3", "dset": "^3.1.4", "es-module-lexer": "^1.6.0", "esbuild": "^0.25.0", "estree-walker": "^3.0.3", "flattie": "^1.1.1", "fontace": "~0.3.0", "github-slugger": "^2.0.0", "html-escaper": "3.0.3", "http-cache-semantics": "^4.1.1", "js-yaml": "^4.1.0", "kleur": "^4.1.5", "magic-string": "^0.30.17", "magicast": "^0.3.5", "mrmime": "^2.0.1", "neotraverse": "^0.6.18", "p-limit": "^6.2.0", "p-queue": "^8.1.0", "package-manager-detector": "^1.1.0", "picomatch": "^4.0.2", "prompts": "^2.4.2", "rehype": "^13.0.2", "semver": "^7.7.1", "shiki": "^3.2.1", "tinyexec": "^0.3.2", "tinyglobby": "^0.2.12", "tsconfck": "^3.1.5", "ultrahtml": "^1.6.0", "unifont": "~0.5.0", "unist-util-visit": "^5.0.0", "unstorage": "^1.15.0", "vfile": "^6.0.3", "vite": "^6.3.4", "vitefu": "^1.0.6", "xxhash-wasm": "^1.1.0", "yargs-parser": "^21.1.1", "yocto-spinner": "^0.2.1", "zod": "^3.24.2", "zod-to-json-schema": "^3.24.5", "zod-to-ts": "^1.2.0" }, "optionalDependencies": { "sharp": "^0.33.3" }, "bin": { "astro": "astro.js" } }, "sha512-cRGq2llKOhV3XMcYwQpfBIUcssN6HEK5CRbcMxAfd9OcFhvWE7KUy50zLioAZVVl3AqgUTJoNTlmZfD2eG0G1w=="],
@@ -489,6 +555,8 @@
"bl": ["bl@4.1.0", "", { "dependencies": { "buffer": "^5.5.0", "inherits": "^2.0.4", "readable-stream": "^3.4.0" } }, "sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w=="],
"blake3-wasm": ["blake3-wasm@2.1.5", "", {}, "sha512-F1+K8EbfOZE49dtoPtmxUQrpXaBIl3ICvasLh+nJta0xkz+9kF/7uet9fLnwKqhDrmj6g+6K3Tw9yQPUg2ka5g=="],
"blob-to-buffer": ["blob-to-buffer@1.2.9", "", {}, "sha512-BF033y5fN6OCofD3vgHmNtwZWRcq9NLyyxyILx9hfMy1sXYy4ojFl765hJ2lP0YaN2fuxPaLO2Vzzoxy0FLFFA=="],
"body-parser": ["body-parser@2.2.0", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.0", "http-errors": "^2.0.0", "iconv-lite": "^0.6.3", "on-finished": "^2.4.1", "qs": "^6.14.0", "raw-body": "^3.0.0", "type-is": "^2.0.0" } }, "sha512-02qvAaxv8tp7fBa/mw1ga98OGm+eCbqzJOKoRt70sLmfEEi+jyBYVTDGfCL/k06/4EMk/z01gCe7HoCH/f2LTg=="],
@@ -505,12 +573,12 @@
"buffer": ["buffer@4.9.2", "", { "dependencies": { "base64-js": "^1.0.2", "ieee754": "^1.1.4", "isarray": "^1.0.0" } }, "sha512-xq+q3SRMOxGivLhBNaUdC64hDTQwejJ+H0T/NB1XMtTVEwNTrfFF3gAxiyW0Bu/xWEGhjVKgUcMhCrUy2+uCWg=="],
"bun-types": ["bun-types@1.2.15", "", { "dependencies": { "@types/node": "*" } }, "sha512-NarRIaS+iOaQU1JPfyKhZm4AsUOrwUOqRNHY0XxI8GI8jYxiLXLcdjYMG9UKS+fwWasc1uw1htV9AX24dD+p4w=="],
"bun-types": ["bun-types@1.2.16", "", { "dependencies": { "@types/node": "*" } }, "sha512-ciXLrHV4PXax9vHvUrkvun9VPVGOVwbbbBF/Ev1cXz12lyEZMoJpIJABOfPcN9gDJRaiKF9MVbSygLg4NXu3/A=="],
"bundle-name": ["bundle-name@4.1.0", "", { "dependencies": { "run-applescript": "^7.0.0" } }, "sha512-tjwM5exMg6BGRI+kNmTntNsvdZS1X8BFYS6tnJ2hdH0kVxM6/eVZ2xy+FqStSWvYmtfFMDLIxurorHwDKfDz5Q=="],
"bytes": ["bytes@3.1.2", "", {}, "sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg=="],
"cac": ["cac@6.7.14", "", {}, "sha512-b6Ilus+c3RrdDk+JhLKUAQfzzgLEPy6wcXqS7f/xe1EETvsDP6GORG7SFuOs6cID5YkqchW/LXZbX5bc8j7ZcQ=="],
"call-bind": ["call-bind@1.0.8", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.0", "es-define-property": "^1.0.0", "get-intrinsic": "^1.2.4", "set-function-length": "^1.2.2" } }, "sha512-oKlSFMcMwpUg2ednkhQ454wfWiU/ul3CkJe/PEHcTKuiX6RpbehUiFMXu13HalGZxfUwCQzZG747YXBn1im9ww=="],
"call-bind-apply-helpers": ["call-bind-apply-helpers@1.0.2", "", { "dependencies": { "es-errors": "^1.3.0", "function-bind": "^1.1.2" } }, "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ=="],
@@ -541,6 +609,8 @@
"cli-boxes": ["cli-boxes@3.0.0", "", {}, "sha512-/lzGpEWL/8PfI0BmBOPRwp0c/wFNX1RdUML3jK/RcSBA9T8mZDdQpqYBKtCFTOfQbwPqWEOpjqW+Fnayc0969g=="],
"cliui": ["cliui@9.0.1", "", { "dependencies": { "string-width": "^7.2.0", "strip-ansi": "^7.1.0", "wrap-ansi": "^9.0.0" } }, "sha512-k7ndgKhwoQveBL+/1tqGJYNz097I7WOvwbmmU2AR5+magtbjPWQTS1C5vzGkBC8Ym8UWRzfKUzUUqFLypY4Q+w=="],
"clone": ["clone@2.1.2", "", {}, "sha512-3Pe/CF1Nn94hyhIYpjtiLhdCoEoz0DqQ+988E9gmeEdQZlojxnOb74wctFyuwWQHzqyf9X7C7MG8juUpqBJT8w=="],
"clsx": ["clsx@2.1.1", "", {}, "sha512-eYm0QWBtUrBWZWG0d386OGAw16Z995PiOVo2B7bjWSbHedGl5e0ZWaq65kOGgUSNesEIDkB9ISbTg/JK9dhCZA=="],
@@ -585,6 +655,8 @@
"csstype": ["csstype@3.1.3", "", {}, "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw=="],
"data-uri-to-buffer": ["data-uri-to-buffer@2.0.2", "", {}, "sha512-ND9qDTLc6diwj+Xe5cdAgVTbLVdXbtxTJRXRhli8Mowuaan+0EJOtdqJ0QCHNSSPyoXGx9HX2/VMnKeC34AChA=="],
"dateformat": ["dateformat@4.6.3", "", {}, "sha512-2P0p0pFGzHS5EMnhdxQi7aJN+iMheud0UhG4dlE1DLAlvL8JHjJJTX/CSm4JXwV0Ka5nGk3zC5mcb5bUQUxxMA=="],
"debug": ["debug@4.4.1", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-KcKCqiftBJcZr++7ykoDIEwSa3XWowTfNPo92BYxjXiyYEVrUQh2aLyhxBCwww+heortUFxEJYcRzosstTEBYQ=="],
@@ -597,8 +669,14 @@
"deep-extend": ["deep-extend@0.6.0", "", {}, "sha512-LOHxIOaPYdHlJRtCQfDIVZtfw/ufM8+rVj649RIHzcm/vGwQRXFt6OPqIFWsm2XEMrNIEtWR64sY1LEKD2vAOA=="],
"default-browser": ["default-browser@5.2.1", "", { "dependencies": { "bundle-name": "^4.1.0", "default-browser-id": "^5.0.0" } }, "sha512-WY/3TUME0x3KPYdRRxEJJvXRHV4PyPoUsxtZa78lwItwRQRHhd2U9xOscaT/YTf8uCXIAjeJOFBVEh/7FtD8Xg=="],
"default-browser-id": ["default-browser-id@5.0.0", "", {}, "sha512-A6p/pu/6fyBcA1TRz/GqWYPViplrftcW2gZC9q79ngNCKAeR/X3gcEdXQHl4KNXV+3wgIJ1CPkJQ3IHM6lcsyA=="],
"define-data-property": ["define-data-property@1.1.4", "", { "dependencies": { "es-define-property": "^1.0.0", "es-errors": "^1.3.0", "gopd": "^1.0.1" } }, "sha512-rBMvIzlpA8v6E+SJZoo++HAYqsLrkg7MSfIinMPFhmkorw7X+dOXVJQs+QT69zGkzMyfDnIMN2Wid1+NbL3T+A=="],
"define-lazy-prop": ["define-lazy-prop@3.0.0", "", {}, "sha512-N+MeXYoqr3pOgn8xfyRPREN7gHakLYjhsHhWGT3fWAiL4IkAt0iDw14QiiEm2bE30c5XX5q0FtAA3CK5f9/BUg=="],
"defu": ["defu@6.1.4", "", {}, "sha512-mEQCMmwJu317oSz8CwdIOdwf3xMif1ttiM8LTufzc3g6kR+9Pe236twL8j3IYT1F7GfRgGcW6MWxzZjLIkuHIg=="],
"depd": ["depd@2.0.0", "", {}, "sha512-g7nH6P6dyDioJogAAGprGpCtVImJhpPk/roCzdb3fIh61/s/nPsfR6onyMwkCAR/OlC3yBC0lESvUoQEAssIrw=="],
@@ -619,6 +697,8 @@
"diff": ["diff@8.0.2", "", {}, "sha512-sSuxWU5j5SR9QQji/o2qMvqRNYRDOcBTgsJ/DeCf4iSN4gW+gNMXM7wFIP+fdXZxoNiAnHUTGjCr+TSWXdRDKg=="],
"diff-match-patch": ["diff-match-patch@1.0.5", "", {}, "sha512-IayShXAgj/QMXgB0IWmKx+rOPuGMhqm5w6jvFxmVenXKIzRqTAAsbBPT3kWQeGANj3jGgvcvv4yK6SxqYmikgw=="],
"direction": ["direction@2.0.1", "", { "bin": { "direction": "cli.js" } }, "sha512-9S6m9Sukh1cZNknO1CWAr2QAWsbKLafQiyM5gZ7VgXHeuaoUwffKN4q6NC4A/Mf9iiPlOXQEKW/Mv/mh9/3YFA=="],
"dlv": ["dlv@1.1.3", "", {}, "sha512-+HlytyjlPKnIG8XuRG8WvmBP8xs8P71y+SKKS6ZXWoEgLuePxtDoUEiH7WkdePWrQ5JBpE6aoVqfZfJUQkjXwA=="],
@@ -687,6 +767,8 @@
"eventsource-parser": ["eventsource-parser@3.0.2", "", {}, "sha512-6RxOBZ/cYgd8usLwsEl+EC09Au/9BcmCKYF2/xbml6DNczf7nv0MQb+7BA2F+li6//I+28VNlQR37XfQtcAJuA=="],
"exit-hook": ["exit-hook@2.2.1", "", {}, "sha512-eNTPlAD67BmP31LDINZ3U7HSF8l57TxOY2PmBJ1shpCvpnxBF93mWCE8YHBnXs8qiUZJc9WDcWIeC3a2HIAMfw=="],
"expand-template": ["expand-template@2.0.3", "", {}, "sha512-XYfuKMvj4O35f/pOXLObndIRvyQ+/+6AhODh+OKWj9S9498pHHn/IMszH+gt0fBCRWMNfk1ZSp5x3AifmnI2vg=="],
"express": ["express@5.1.0", "", { "dependencies": { "accepts": "^2.0.0", "body-parser": "^2.2.0", "content-disposition": "^1.0.0", "content-type": "^1.0.5", "cookie": "^0.7.1", "cookie-signature": "^1.2.1", "debug": "^4.4.0", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "etag": "^1.8.1", "finalhandler": "^2.1.0", "fresh": "^2.0.0", "http-errors": "^2.0.0", "merge-descriptors": "^2.0.0", "mime-types": "^3.0.0", "on-finished": "^2.4.1", "once": "^1.4.0", "parseurl": "^1.3.3", "proxy-addr": "^2.0.7", "qs": "^6.14.0", "range-parser": "^1.2.1", "router": "^2.2.0", "send": "^1.1.0", "serve-static": "^2.2.0", "statuses": "^2.0.1", "type-is": "^2.0.1", "vary": "^1.1.2" } }, "sha512-DT9ck5YIRU+8GYzzU5kT3eHGA5iL+1Zd0EutOmTE9Dtk+Tvuzd23VBU+ec7HPNSTxXYO55gPV/hq4pSBJDjFpA=="],
@@ -695,6 +777,8 @@
"expressive-code": ["expressive-code@0.41.2", "", { "dependencies": { "@expressive-code/core": "^0.41.2", "@expressive-code/plugin-frames": "^0.41.2", "@expressive-code/plugin-shiki": "^0.41.2", "@expressive-code/plugin-text-markers": "^0.41.2" } }, "sha512-aLZiZaqorRtNExtGpUjK9zFH9aTpWeoTXMyLo4b4IcuXfPqtLPPxhRm/QlPb8QqIcMMXnSiGRHSFpQfX0m7HJw=="],
"exsolve": ["exsolve@1.0.5", "", {}, "sha512-pz5dvkYYKQ1AHVrgOzBKWeP4u4FRb3a6DNK2ucr0OoNwYIU4QWsJ+NM36LLzORT+z845MzKHHhpXiUF5nvQoJg=="],
"extend": ["extend@3.0.2", "", {}, "sha512-fjquC59cD7CyW6urNXK0FBufkZcoiGG80wTuPujX590cB5Ttln20E2UB4S/WARVqhXffZl2LNgS+gQdPIIim/g=="],
"fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],
@@ -733,16 +817,22 @@
"gensync": ["gensync@1.0.0-beta.2", "", {}, "sha512-3hN7NaskYvMDLQY55gnW3NQ+mesEAepTqlg+VEbj7zzqEMBVNhzcGYYeqFo/TlYz6eQiFcp1HcsCZO+nGgS8zg=="],
"get-caller-file": ["get-caller-file@2.0.5", "", {}, "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg=="],
"get-east-asian-width": ["get-east-asian-width@1.3.0", "", {}, "sha512-vpeMIQKxczTD/0s2CdEWHcb0eeJe6TFjxb+J5xgX7hScxqrGuyjmv4c1D4A/gelKfyox0gJJwIHF+fLjeaM8kQ=="],
"get-intrinsic": ["get-intrinsic@1.3.0", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "es-define-property": "^1.0.1", "es-errors": "^1.3.0", "es-object-atoms": "^1.1.1", "function-bind": "^1.1.2", "get-proto": "^1.0.1", "gopd": "^1.2.0", "has-symbols": "^1.1.0", "hasown": "^2.0.2", "math-intrinsics": "^1.1.0" } }, "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ=="],
"get-proto": ["get-proto@1.0.1", "", { "dependencies": { "dunder-proto": "^1.0.1", "es-object-atoms": "^1.0.0" } }, "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g=="],
"get-source": ["get-source@2.0.12", "", { "dependencies": { "data-uri-to-buffer": "^2.0.0", "source-map": "^0.6.1" } }, "sha512-X5+4+iD+HoSeEED+uwrQ07BOQr0kEDFMVqqpBuI+RaZBpBpHCuXxo70bjar6f0b0u/DQJsJ7ssurpP0V60Az+w=="],
"github-from-package": ["github-from-package@0.0.0", "", {}, "sha512-SyHy3T1v2NUXn29OsWdxmK6RwHD+vkj3v8en8AOBZ1wBQ/hCAQ5bAQTD02kW4W9tUp/3Qh6J8r9EvntiyCmOOw=="],
"github-slugger": ["github-slugger@2.0.0", "", {}, "sha512-IaOQ9puYtjrkq7Y0Ygl9KDZnrf/aiUJYUpVf89y8kyaxbRG7Y1SrX/jaumrv81vc61+kiMempujsM3Yw7w5qcw=="],
"glob-to-regexp": ["glob-to-regexp@0.4.1", "", {}, "sha512-lkX1HJXwyMcprw/5YUZc2s7DrpAiHB21/V+E1rHUrVNokkvB6bqMzT0VfV6/86ZNabt1k14YOIaT7nDvOX3Iiw=="],
"globals": ["globals@11.12.0", "", {}, "sha512-WOBp/EEGUiIsJSp7wcv/y6MO+lV9UoncWqxuFfm8eBwzWNgyfBd6Gz+IeKQ9jCmyhoH99g15M3T+QaVHFjizVA=="],
"gopd": ["gopd@1.2.0", "", {}, "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg=="],
@@ -877,6 +967,8 @@
"joycon": ["joycon@3.1.1", "", {}, "sha512-34wB/Y7MW7bzjKRjUKTa46I2Z7eV62Rkhva+KkopW7Qvv/OSWBqvkSY7vusOPrNuZcUG3tApvdVgNB8POj3SPw=="],
"js-base64": ["js-base64@3.7.7", "", {}, "sha512-7rCnleh0z2CkXhH67J8K1Ytz0b2Y+yxTPL+/KOJoa20hfnVQ/3/T6W/KflYI4bRHRagNeXeU2bkNGI3v1oS/lw=="],
"js-tokens": ["js-tokens@4.0.0", "", {}, "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ=="],
"js-yaml": ["js-yaml@4.1.0", "", { "dependencies": { "argparse": "^2.0.1" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA=="],
@@ -891,6 +983,8 @@
"json5": ["json5@2.2.3", "", { "bin": { "json5": "lib/cli.js" } }, "sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg=="],
"jsondiffpatch": ["jsondiffpatch@0.6.0", "", { "dependencies": { "@types/diff-match-patch": "^1.0.36", "chalk": "^5.3.0", "diff-match-patch": "^1.0.5" }, "bin": { "jsondiffpatch": "bin/jsondiffpatch.js" } }, "sha512-3QItJOXp2AP1uv7waBkao5nCvhEv+QmJAd38Ybq7wNI74Q+BBmnLn4EDKz6yI9xGAIQoUF87qHt+kc1IVxB4zQ=="],
"kleur": ["kleur@4.1.5", "", {}, "sha512-o+NO+8WrRiQEE4/7nwRJhN1HWpVmJm511pBHUxPLtp0BUISzlBplORYSmTclCnJvQq2tKu/sgl3xVpkc7ZWuQQ=="],
"klona": ["klona@2.0.6", "", {}, "sha512-dhG34DXATL5hSxJbIexCft8FChFXtmskoZYnoPWjXQuebWYCNkVeV3KkGegCK9CP1oswI/vQibS2GY7Em/sJJA=="],
@@ -911,6 +1005,8 @@
"markdown-table": ["markdown-table@3.0.4", "", {}, "sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw=="],
"marked": ["marked@15.0.12", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-8dD6FusOQSrpv9Z1rdNMdlSgQOIP880DHqnohobOmYLElGEqAL/JvxvuxZO16r4HtjTlfPRDC1hbvxC9dPN2nA=="],
"math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="],
"mdast-util-definitions": ["mdast-util-definitions@6.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "@types/unist": "^3.0.0", "unist-util-visit": "^5.0.0" } }, "sha512-scTllyX6pnYNZH/AIp/0ePz6s4cZtARxImwoPJ7kS42n+MnVsI4XbnG6d4ibehRIldYMWM2LD7ImQblVhUejVQ=="],
@@ -1029,12 +1125,16 @@
"micromark-util-types": ["micromark-util-types@2.0.2", "", {}, "sha512-Yw0ECSpJoViF1qTU4DC6NwtC4aWGt1EkzaQB8KPPyCRR8z9TWeV0HbEFGTO+ZY1wB22zmxnJqhPyTpOVCpeHTA=="],
"mime": ["mime@3.0.0", "", { "bin": { "mime": "cli.js" } }, "sha512-jSCU7/VB1loIWBZe14aEYHU/+1UMEHoaO7qxCOVJOw9GgH72VAWppxNcjU+x9a2k3GSIBXNKxXQFqRvvZ7vr3A=="],
"mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],
"mime-types": ["mime-types@3.0.1", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-xRc4oEhT6eaBpU1XF7AjpOFD+xQmXNB5OVKwp4tqCuBpHLS/ZbBDrc07mYTDqVMg6PfxUjjNp85O6Cd2Z/5HWA=="],
"mimic-response": ["mimic-response@3.1.0", "", {}, "sha512-z0yWI+4FDrrweS8Zmt4Ej5HdJmky15+L2e6Wgn3+iK5fWzb6T3fhNFq2+MeTRb064c6Wr4N/wv0DzQTjNzHNGQ=="],
"miniflare": ["miniflare@4.20250525.1", "", { "dependencies": { "@cspotcode/source-map-support": "0.8.1", "acorn": "8.14.0", "acorn-walk": "8.3.2", "exit-hook": "2.2.1", "glob-to-regexp": "0.4.1", "sharp": "^0.33.5", "stoppable": "1.1.0", "undici": "^5.28.5", "workerd": "1.20250525.0", "ws": "8.18.0", "youch": "3.3.4", "zod": "3.22.3" }, "bin": { "miniflare": "bootstrap.js" } }, "sha512-4PJlT5WA+hfclFU5Q7xnpG1G1VGYTXaf/3iu6iKQ8IsbSi9QvPTA2bSZ5goCFxmJXDjV4cxttVxB0Wl1CLuQ0w=="],
"minimatch": ["minimatch@5.1.6", "", { "dependencies": { "brace-expansion": "^2.0.1" } }, "sha512-lKwV/1brpG6mBUFHtb7NUmtABCb2WZZmm2wNiOA5hAb8VdCS4B3dtMWyvcoViccwAW/COERjXLt0zP1zXUN26g=="],
"minimist": ["minimist@1.2.8", "", {}, "sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA=="],
@@ -1047,6 +1147,8 @@
"ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
"mustache": ["mustache@4.2.0", "", { "bin": { "mustache": "bin/mustache" } }, "sha512-71ippSywq5Yb7/tVYyGbkBggbU8H3u5Rz56fH60jGFgr8uHwxs+aSKeqmluIVzM0m0kB7xQjKS6qPfd0b2ZoqQ=="],
"nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="],
"napi-build-utils": ["napi-build-utils@2.0.0", "", {}, "sha512-GEbrYkbfF7MoNaoh2iGG84Mnf/WZfB0GdGEsM8wz7Expx/LlWf5U8t9nvJKXSp3qr5IsEbK04cBGhol/KwOsWA=="],
@@ -1095,6 +1197,8 @@
"oniguruma-to-es": ["oniguruma-to-es@4.3.3", "", { "dependencies": { "oniguruma-parser": "^0.12.1", "regex": "^6.0.1", "regex-recursion": "^6.0.2" } }, "sha512-rPiZhzC3wXwE59YQMRDodUwwT9FZ9nNBwQQfsd1wfdtlKEyCdRV0avrTcSZ5xlIvGRVPd/cx6ZN45ECmS39xvg=="],
"open": ["open@10.1.2", "", { "dependencies": { "default-browser": "^5.2.1", "define-lazy-prop": "^3.0.0", "is-inside-container": "^1.0.0", "is-wsl": "^3.1.0" } }, "sha512-cxN6aIDPz6rm8hbebcP7vrQNhvRcveZoJU72Y7vskh4oIm+BZwBECnx5nTmrlres1Qapvx27Qo1Auukpf8PKXw=="],
"openapi-types": ["openapi-types@12.1.3", "", {}, "sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw=="],
"opencode": ["opencode@workspace:packages/opencode"],
@@ -1123,7 +1227,9 @@
"parseurl": ["parseurl@1.3.3", "", {}, "sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ=="],
"path-to-regexp": ["path-to-regexp@8.2.0", "", {}, "sha512-TdrF7fW9Rphjq4RjrW0Kp2AW0Ahwu9sRGTkS6bvDi0SCwZlEZYmcfDbEsTz8RVk0EHIS/Vd1bv3JhG+1xZuAyQ=="],
"path-to-regexp": ["path-to-regexp@6.3.0", "", {}, "sha512-Yhpw4T9C6hPpgPeA28us07OJeqZ5EzQTkbfwuhsUg0c237RomFoETJgmp2sa3F/41gfLE6G5cqcYwznmeEeOlQ=="],
"pathe": ["pathe@2.0.3", "", {}, "sha512-WUjGcAqP1gQacoQe+OBJsFA7Ld4DyXuUIjZ5cc75cLHvJ7dtNsTugphxIADwspS+AraAUePCKrSVtPLFj/F88w=="],
"peek-readable": ["peek-readable@7.0.0", "", {}, "sha512-nri2TO5JE3/mRryik9LlHFT53cgHfRK0Lt0BAZQXku/AW3E6XLt2GaY8siWi7dvW/m1z0ecn+J+bpDa9ZN3IsQ=="],
@@ -1153,6 +1259,8 @@
"prettier": ["prettier@3.5.3", "", { "bin": { "prettier": "bin/prettier.cjs" } }, "sha512-QQtaxnoDJeAkDvDKWCLiwIXkTgRhwYDEQCghU9Z6q03iyek/rxRh/2lC3HB7P8sWT2xC/y5JDctPLBIGzHKbhw=="],
"printable-characters": ["printable-characters@1.0.42", "", {}, "sha512-dKp+C4iXWK4vVYZmYSd0KBH5F/h1HoZRsbJ82AVKRO3PEo8L4lBS/vLwhVtpwwuYcoIsVY+1JYKR268yn480uQ=="],
"prismjs": ["prismjs@1.30.0", "", {}, "sha512-DEvV2ZF2r2/63V+tK8hQvrR2ZGn10srHbXviTlcv7Kpzw8jWiNTqbVgjO3IY8RxrrOUF8VPMQQFysYYYv0YZxw=="],
"process-warning": ["process-warning@1.0.0", "", {}, "sha512-du4wfLyj4yCZq1VupnVSZmRsPJsNuxoDQFdCFHLaYiEbFBD7QE0a+I4D7hOxrVnh78QE/YipFAj9lXHiXocV+Q=="],
@@ -1181,6 +1289,8 @@
"rc": ["rc@1.2.8", "", { "dependencies": { "deep-extend": "^0.6.0", "ini": "~1.3.0", "minimist": "^1.2.0", "strip-json-comments": "~2.0.1" }, "bin": { "rc": "./cli.js" } }, "sha512-y3bGgqKj3QBdxLbLkomlohkvsA8gdAiUQlSBJnBhfn+BPxg4bc62d8TcBW15wavDfgexCgccckhcZvywyQYPOw=="],
"react": ["react@19.1.0", "", {}, "sha512-FS+XFBNvn3GTAWq26joslQgWNoFu08F4kl0J4CgdNKADkdSGXQyTCnKteIAJy96Br6YbpEU1LSzV5dYtjMkMDg=="],
"readable-stream": ["readable-stream@3.6.2", "", { "dependencies": { "inherits": "^2.0.3", "string_decoder": "^1.1.1", "util-deprecate": "^1.0.1" } }, "sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA=="],
"readdirp": ["readdirp@4.1.2", "", {}, "sha512-GDhwkLfywWL2s6vEjyhri+eXmfH6j1L7JE27WhqLeYzoh/A3DBaYGEj2H/HFZCn/kMfim73FXxEJTw06WtxQwg=="],
@@ -1249,6 +1359,8 @@
"router": ["router@2.2.0", "", { "dependencies": { "debug": "^4.4.0", "depd": "^2.0.0", "is-promise": "^4.0.0", "parseurl": "^1.3.3", "path-to-regexp": "^8.0.0" } }, "sha512-nLTrUKm2UyiL7rlhapu/Zl45FwNgkZGaCpZbIHajDYgwlJCOzLSk+cIPAnsEqV955GjILJnKbdQC1nVPz+gAYQ=="],
"run-applescript": ["run-applescript@7.0.0", "", {}, "sha512-9by4Ij99JUr/MCFBUkDKLWK3G9HVXmabKz9U5MlIAIuvuzkiOicRYs8XJLxX+xahD+mLiiCYDqF9dKAgtzKP1A=="],
"safe-buffer": ["safe-buffer@5.2.1", "", {}, "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ=="],
"safe-regex-test": ["safe-regex-test@1.1.0", "", { "dependencies": { "call-bound": "^1.0.2", "es-errors": "^1.3.0", "is-regex": "^1.2.1" } }, "sha512-x/+Cz4YrimQxQccJf5mKEbIa1NzeCRNI5Ecl/ekmlYaampdNLPalVyIcCZNNH3MvmqBugV5TMYZXv0ljslUlaw=="],
@@ -1259,6 +1371,8 @@
"sax": ["sax@1.2.1", "", {}, "sha512-8I2a3LovHTOpm7NV5yOyO8IHqgVsfK4+UuySrXU8YXkSRX7k6hCV9b3HrkKCr3nMpgj+0bmocaJJWpvp1oc7ZA=="],
"secure-json-parse": ["secure-json-parse@2.7.0", "", {}, "sha512-6aU+Rwsezw7VR8/nyvKTx8QpWH9FrcYiXXlqC4z5d5XQBDRqtbfsRjnwGyqbi3gddNtWHuEk9OANUotL26qKUw=="],
"semver": ["semver@7.7.2", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-RF0Fw+rO5AMf9MAyaRXI4AV0Ulj5lMHqVxxdSgiVbixSCXoEmmX/jk0CuJw4+3SqroYO9VoUh+HcuJivvtJemA=="],
"send": ["send@1.2.0", "", { "dependencies": { "debug": "^4.3.5", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "etag": "^1.8.1", "fresh": "^2.0.0", "http-errors": "^2.0.0", "mime-types": "^3.0.1", "ms": "^2.1.3", "on-finished": "^2.4.1", "range-parser": "^1.2.1", "statuses": "^2.0.1" } }, "sha512-uaW0WwXKpL9blXE2o0bRhoL2EGXIrZxQ2ZQ4mgcfoBxdFmQold+qWsD2jLrfZ0trjKL6vOw0j//eAwcALFjKSw=="],
@@ -1311,26 +1425,30 @@
"split2": ["split2@3.2.2", "", { "dependencies": { "readable-stream": "^3.0.0" } }, "sha512-9NThjpgZnifTkJpzTZ7Eue85S49QwpNhZTq6GRJwObb6jnLFNGB7Qm73V5HewTROPyxD0C29xqmaI68bQtV+hg=="],
"sst": ["sst@3.16.0", "", { "dependencies": { "aws-sdk": "2.1692.0", "aws4fetch": "1.0.18", "jose": "5.2.3", "opencontrol": "0.0.6", "openid-client": "5.6.4" }, "optionalDependencies": { "sst-darwin-arm64": "3.16.0", "sst-darwin-x64": "3.16.0", "sst-linux-arm64": "3.16.0", "sst-linux-x64": "3.16.0", "sst-linux-x86": "3.16.0", "sst-win32-arm64": "3.16.0", "sst-win32-x64": "3.16.0", "sst-win32-x86": "3.16.0" }, "bin": { "sst": "bin/sst.mjs" } }, "sha512-XX4ktkpyvB2lQCG8/jgH/RWAtdNahE/MjlK6OctM4Nagk1rOrMxxzARit2ZFCisX+ZBvcN0ymgJimnfZqWjM7Q=="],
"sst": ["sst@3.17.6", "", { "dependencies": { "aws-sdk": "2.1692.0", "aws4fetch": "1.0.18", "jose": "5.2.3", "opencontrol": "0.0.6", "openid-client": "5.6.4" }, "optionalDependencies": { "sst-darwin-arm64": "3.17.6", "sst-darwin-x64": "3.17.6", "sst-linux-arm64": "3.17.6", "sst-linux-x64": "3.17.6", "sst-linux-x86": "3.17.6", "sst-win32-arm64": "3.17.6", "sst-win32-x64": "3.17.6", "sst-win32-x86": "3.17.6" }, "bin": { "sst": "bin/sst.mjs" } }, "sha512-p+AcqwfYQUdkxeRjCikQoTMviPCBiGoU7M0vcV6GDVmVis8hzhVw4EFfHTafZC+aWfy1Ke2UQi66vZlEVWuEqA=="],
"sst-darwin-arm64": ["sst-darwin-arm64@3.16.0", "", { "os": "darwin", "cpu": "arm64" }, "sha512-NJDGjZ0bl+hWJoT1P2KLyA65OXHkItVg3BNkRsas6qaa+c1U6GU8wLFnfdqkDRnJIYhOIsnZtIquNp7lMIr3ww=="],
"sst-darwin-arm64": ["sst-darwin-arm64@3.17.6", "", { "os": "darwin", "cpu": "arm64" }, "sha512-6tb7KlcPR7PTi3ofQv8dX/n6Jf7pNP9VfrnYL4HBWnWrcYaZeJ5MWobILfIJ/y2jHgoqmg9e5C3266Eds0JQyw=="],
"sst-darwin-x64": ["sst-darwin-x64@3.16.0", "", { "os": "darwin", "cpu": "x64" }, "sha512-IZiIUZgTGKjW+aR6/qgqNMzdFS2789PBQjsMquXaTZc7ebRutbCozQ4CC78SuwPXDUZ0/Bz+hyGeXHNOB52lVQ=="],
"sst-darwin-x64": ["sst-darwin-x64@3.17.6", "", { "os": "darwin", "cpu": "x64" }, "sha512-lFakq6/EgTuBSjbl8Kry4pfgAPEIyn6o7ZkyRz3hz5331wUaX88yfjs3tL9JQ8Ey6jBUYxwhP/Q1n7fzIG046g=="],
"sst-linux-arm64": ["sst-linux-arm64@3.16.0", "", { "os": "linux", "cpu": "arm64" }, "sha512-pvbxU+hrbvtIt347ilbXzVQEl2kXXBIYArLMzblPNg4KblCRvJvH595P86hrr8ZojlOkEb1rC8NSAwiZyBad4g=="],
"sst-linux-arm64": ["sst-linux-arm64@3.17.6", "", { "os": "linux", "cpu": "arm64" }, "sha512-SdTxXMbTEdiwOqp37w31kXv97vHqSx3oK9h/76lKg7V9k5JxPJ6JMefPLhoKWwK0Zh6AndY2zo2oRoEv4SIaDw=="],
"sst-linux-x64": ["sst-linux-x64@3.16.0", "", { "os": "linux", "cpu": "x64" }, "sha512-p7qtmdiG1imWSZ7gUbVecee6TIuILTvIe6dgpvkgznYvuTFiMCZaY2SNMFuNRiBoN5zZI0y5osDDXY2uzzo7rA=="],
"sst-linux-x64": ["sst-linux-x64@3.17.6", "", { "os": "linux", "cpu": "x64" }, "sha512-qneh7uWDiTUYx8X1Y3h2YVw3SJ0ybBBlRrVybIvCM09JqQ8+qq/XjKXGzA/3/EF0Jr7Ug8cARSn9CwxhdQGN7Q=="],
"sst-linux-x86": ["sst-linux-x86@3.16.0", "", { "os": "linux", "cpu": "none" }, "sha512-bw+enzOnZ+MjGd7/h4swGfHpIoyLbIdguelGV7vZLIeuV4t4rZ/hAqfR25GEMjjonVv3Py5hsasMzR2s9GsBLA=="],
"sst-linux-x86": ["sst-linux-x86@3.17.6", "", { "os": "linux", "cpu": "none" }, "sha512-pU3D5OeqnmfxGqN31DxuwWnc1OayxhkErnITHhZ39D0MTiwbIgCapH26FuLW8B08/uxJWG8djUlOboCRhSBvWA=="],
"sst-win32-arm64": ["sst-win32-arm64@3.16.0", "", { "os": "win32", "cpu": "arm64" }, "sha512-bjjYn1gq1p1tBFKvuB3K5ZMuofK/WWmrtKpD+OJOf8PE5fxzRJ8yvOFVIm1QhD4hxDQAPdNonE/P/cXDtKXQig=="],
"sst-win32-arm64": ["sst-win32-arm64@3.17.6", "", { "os": "win32", "cpu": "arm64" }, "sha512-Rr3RTYWAsH9sM9CbM/sAZCk7dB1OsSAljjJuuHMvdSAYW3RDpXEza0PBJGxnBID2eOrpswEchzMPL2d8LtL7oA=="],
"sst-win32-x64": ["sst-win32-x64@3.16.0", "", { "os": "win32", "cpu": "x64" }, "sha512-WFHaUyaLHepKPOMFr7Kf8iECIg1prn3L7c5r+IKgIiv+KznOeslwG6f9mYwxcOYZrZNiXVeDJmDp9xZtB5auSQ=="],
"sst-win32-x64": ["sst-win32-x64@3.17.6", "", { "os": "win32", "cpu": "x64" }, "sha512-yZ3roxwI0Wve9PFzdrrF1kfzCmIMFCCoa8qKeXY7LxCJ4QQIqHbCOccLK1Wv/MIU/mcZHWXTQVCLHw77uaa0GQ=="],
"sst-win32-x86": ["sst-win32-x86@3.16.0", "", { "os": "win32", "cpu": "none" }, "sha512-Twbdy9sS6zSKsdwpWVEYpFEjVcRAn0Ufdbz+pVdMK3JXniSB7MLC6/KQuxUwvUk2a88+jnPuPVXAYC51SgzDyg=="],
"sst-win32-x86": ["sst-win32-x86@3.17.6", "", { "os": "win32", "cpu": "none" }, "sha512-zV7TJWPJN9PmIXr15iXFSs0tbGsa52oBR3+xiKrUj2qj9XsZe7HBFwskRnHyiFq0durZY9kk9ZtoVlpuUuzr1g=="],
"stacktracey": ["stacktracey@2.1.8", "", { "dependencies": { "as-table": "^1.0.36", "get-source": "^2.0.12" } }, "sha512-Kpij9riA+UNg7TnphqjH7/CzctQ/owJGNbFkfEeve4Z4uxT5+JapVLFXcsurIfN34gnTWZNJ/f7NMG0E8JDzTw=="],
"statuses": ["statuses@2.0.1", "", {}, "sha512-RwNA9Z/7PrK06rYLIzFMlaF+l73iwpzsqRIFgbMLbTcLD6cOao82TaWefPXQvB2fOC4AjuYSEndS7N/mTCbkdQ=="],
"stoppable": ["stoppable@1.1.0", "", {}, "sha512-KXDYZ9dszj6bzvnEMRYvxgeTHU74QBFL54XKtP3nyMuJ81CFYtABZ3bAzL2EdFUaEwJOBOgENyFj3R7oTzDyyw=="],
"stream-replace-string": ["stream-replace-string@2.0.0", "", {}, "sha512-TlnjJ1C0QrmxRNrON00JvaFFlNh5TTG00APw23j74ET7gkQpTASi6/L2fuiav8pzK715HXtUeClpBTw2NPSn6w=="],
"stream-shift": ["stream-shift@1.0.3", "", {}, "sha512-76ORR0DO1o1hlKwTbi/DM3EXWGf3ZJYO8cXX5RJwnul2DEg2oyoZyjLNoQM8WsvZiFKCRfC1O0J7iCvie3RZmQ=="],
@@ -1355,6 +1473,8 @@
"supports-color": ["supports-color@7.2.0", "", { "dependencies": { "has-flag": "^4.0.0" } }, "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw=="],
"swr": ["swr@2.3.3", "", { "dependencies": { "dequal": "^2.0.3", "use-sync-external-store": "^1.4.0" }, "peerDependencies": { "react": "^16.11.0 || ^17.0.0 || ^18.0.0 || ^19.0.0" } }, "sha512-dshNvs3ExOqtZ6kJBaAsabhPdHyeY4P2cKwRCniDVifBMoG/SVI7tfLWqPXriVspf2Rg4tPzXJTnwaihIeFw2A=="],
"tar-fs": ["tar-fs@3.0.9", "", { "dependencies": { "pump": "^3.0.0", "tar-stream": "^3.1.5" }, "optionalDependencies": { "bare-fs": "^4.0.1", "bare-path": "^3.0.0" } }, "sha512-XF4w9Xp+ZQgifKakjZYmFdkLoSWd34VGKcsTCwlNWM7QG3ZbaxnTsaBwnjFZqHRf/rROxaR8rXnbtwdvaDI+lA=="],
"tar-stream": ["tar-stream@3.1.7", "", { "dependencies": { "b4a": "^1.6.4", "fast-fifo": "^1.2.0", "streamx": "^2.15.0" } }, "sha512-qJj60CXt7IU1Ffyc3NJMjh6EkuCFej46zUqJ4J7pqYlThyd9bO0XBTmcOIhSzZJVWfsLks0+nle/j538YAW9RQ=="],
@@ -1363,6 +1483,8 @@
"thread-stream": ["thread-stream@0.15.2", "", { "dependencies": { "real-require": "^0.1.0" } }, "sha512-UkEhKIg2pD+fjkHQKyJO3yoIvAP3N6RlNFt2dUhcS1FGvCD1cQa1M/PGknCLFIyZdtJOWQjejp7bdNqmN7zwdA=="],
"throttleit": ["throttleit@2.1.0", "", {}, "sha512-nt6AMGKW1p/70DF/hGBdJB57B8Tspmbp5gfJ8ilhLnt7kkr2ye7hzD6NVG8GGErk2HWF34igrL2CXmNIkzKqKw=="],
"tiny-inflate": ["tiny-inflate@1.0.3", "", {}, "sha512-pkY1fj1cKHb2seWDy0B16HeWyczlJA9/WW3u3c4z/NiWDsO3DOU5D7nhTLE9CF0yXv/QZFY7sEJmj24dK+Rrqw=="],
"tinyexec": ["tinyexec@0.3.2", "", {}, "sha512-KQQR9yN7R5+OSwaK0XQoj22pwHoTlgYqmUscPYoknOoWCWfj/5/ABTMRi69FrKU5ffPVh5QcFikpWJI/P1ocHA=="],
@@ -1373,7 +1495,7 @@
"token-types": ["token-types@6.0.0", "", { "dependencies": { "@tokenizer/token": "^0.3.0", "ieee754": "^1.2.1" } }, "sha512-lbDrTLVsHhOMljPscd0yitpozq7Ga2M5Cvez5AjGg8GASBjtt6iERCAJ93yommPmz62fb45oFIXHEZ3u9bfJEA=="],
"toolbeam-docs-theme": ["toolbeam-docs-theme@0.2.4", "", { "peerDependencies": { "@astrojs/starlight": "^0.34.3", "astro": "^5.7.13" } }, "sha512-W5mdbcgRpTBDFyEdcU81USs3MFZoXMInpSznc/AFZCwqz8atk4iBNDIlhvihpGHY54Nf5crKmZwJjxVojkHFvA=="],
"toolbeam-docs-theme": ["toolbeam-docs-theme@0.3.0", "", { "peerDependencies": { "@astrojs/starlight": "^0.34.3", "astro": "^5.7.13" } }, "sha512-qlBkKRp8HVYV7p7jaG9lT2lvQY7c8b9czZ0tnsJUrN2TBTtEyFJymCdkhhpZNC9U4oGZ7lLk0glRJHrndWvVsg=="],
"tr46": ["tr46@0.0.3", "", {}, "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="],
@@ -1405,8 +1527,12 @@
"uncrypto": ["uncrypto@0.1.3", "", {}, "sha512-Ql87qFHB3s/De2ClA9e0gsnS6zXG27SkTiSJwjCc9MebbfapQfuPzumMIUMi38ezPZVNFcHI9sUIepeQfw8J8Q=="],
"undici": ["undici@5.29.0", "", { "dependencies": { "@fastify/busboy": "^2.0.0" } }, "sha512-raqeBD6NQK4SkWhQzeYKd1KmIG6dllBOTt55Rmkt4HtI9mwdWtJljnrXjAFUBLTSN67HWrOIZ3EPF4kjUw80Bg=="],
"undici-types": ["undici-types@6.20.0", "", {}, "sha512-Ny6QZ2Nju20vw1SRHe3d9jVu6gJ+4e3+MMpqu7pqE5HT6WsTSlce++GQmK5UXS8mzV8DSYHrQH+Xrf2jVcuKNg=="],
"unenv": ["unenv@2.0.0-rc.17", "", { "dependencies": { "defu": "^6.1.4", "exsolve": "^1.0.4", "ohash": "^2.0.11", "pathe": "^2.0.3", "ufo": "^1.6.1" } }, "sha512-B06u0wXkEd+o5gOCMl/ZHl5cfpYbDZKAT+HWTL+Hws6jWu7dCiqBBXXXzMFcFVJb8D4ytAnYmxJA83uwOQRSsg=="],
"unicode-properties": ["unicode-properties@1.4.1", "", { "dependencies": { "base64-js": "^1.3.0", "unicode-trie": "^2.0.0" } }, "sha512-CLjCCLQ6UuMxWnbIylkisbRj31qxHPAurvena/0iwSVbQ2G1VY5/HjV0IRabOEbDHlzZlRdCrD4NhB0JtU40Pg=="],
"unicode-trie": ["unicode-trie@2.0.0", "", { "dependencies": { "pako": "^0.2.5", "tiny-inflate": "^1.0.0" } }, "sha512-x7bc76x0bm4prf1VLg79uhAzKw8DVboClSN5VxJuQ+LKDOVEW9CdH+VY7SP+vX7xCYQqzzgQpFqz15zeLvAtZQ=="],
@@ -1443,6 +1569,8 @@
"url": ["url@0.10.3", "", { "dependencies": { "punycode": "1.3.2", "querystring": "0.2.0" } }, "sha512-hzSUW2q06EqL1gKM/a+obYHLIO6ct2hwPuviqTTOcfFVc61UbfJ2Q32+uGL/HCPxKqrdGB5QUwIe7UqlDgwsOQ=="],
"use-sync-external-store": ["use-sync-external-store@1.5.0", "", { "peerDependencies": { "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0" } }, "sha512-Rb46I4cGGVBmjamjphe8L/UnvJD+uPPtTkNvX5mZgqdbavhI4EbgIWJiIHXJ8bc/i9EQGPRh4DwEURJ552Do0A=="],
"util": ["util@0.12.5", "", { "dependencies": { "inherits": "^2.0.3", "is-arguments": "^1.0.4", "is-generator-function": "^1.0.7", "is-typed-array": "^1.1.3", "which-typed-array": "^1.1.2" } }, "sha512-kZf/K6hEIrWHI6XqOFUiiMa+79wE/D8Q+NCNAWclkyg3b4d2k7s0QGepNjiABc+aR3N1PAyHL7p6UcLY6LmrnA=="],
"util-deprecate": ["util-deprecate@1.0.2", "", {}, "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw=="],
@@ -1485,18 +1613,30 @@
"widest-line": ["widest-line@5.0.0", "", { "dependencies": { "string-width": "^7.0.0" } }, "sha512-c9bZp7b5YtRj2wOe6dlj32MK+Bx/M/d+9VB2SHM1OtsUHR0aV0tdP6DWh/iMt0kWi1t5g1Iudu6hQRNd1A4PVA=="],
"workerd": ["workerd@1.20250525.0", "", { "optionalDependencies": { "@cloudflare/workerd-darwin-64": "1.20250525.0", "@cloudflare/workerd-darwin-arm64": "1.20250525.0", "@cloudflare/workerd-linux-64": "1.20250525.0", "@cloudflare/workerd-linux-arm64": "1.20250525.0", "@cloudflare/workerd-windows-64": "1.20250525.0" }, "bin": { "workerd": "bin/workerd" } }, "sha512-SXJgLREy/Aqw2J71Oah0Pbu+SShbqbTExjVQyRBTM1r7MG7fS5NUlknhnt6sikjA/t4cO09Bi8OJqHdTkrcnYQ=="],
"wrangler": ["wrangler@4.19.1", "", { "dependencies": { "@cloudflare/kv-asset-handler": "0.4.0", "@cloudflare/unenv-preset": "2.3.2", "blake3-wasm": "2.1.5", "esbuild": "0.25.4", "miniflare": "4.20250525.1", "path-to-regexp": "6.3.0", "unenv": "2.0.0-rc.17", "workerd": "1.20250525.0" }, "optionalDependencies": { "fsevents": "~2.3.2" }, "peerDependencies": { "@cloudflare/workers-types": "^4.20250525.0" }, "optionalPeers": ["@cloudflare/workers-types"], "bin": { "wrangler": "bin/wrangler.js", "wrangler2": "bin/wrangler.js" } }, "sha512-b+ed2SJKauHgndl4Im1wHE+FeSSlrdlEZNuvpc8q/94k4EmRxRkXnwBAsVWuicBxG3HStFLQPGGlvL8wGKTtHw=="],
"wrap-ansi": ["wrap-ansi@9.0.0", "", { "dependencies": { "ansi-styles": "^6.2.1", "string-width": "^7.0.0", "strip-ansi": "^7.1.0" } }, "sha512-G8ura3S+3Z2G+mkgNRq8dqaFZAuxfsxpBB8OCTGRTCtp+l/v9nbFNmCUP1BZMts3G1142MsZfn6eeUKrr4PD1Q=="],
"wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
"ws": ["ws@8.18.0", "", { "peerDependencies": { "bufferutil": "^4.0.1", "utf-8-validate": ">=5.0.2" }, "optionalPeers": ["bufferutil", "utf-8-validate"] }, "sha512-8VbfWfHLbbwu3+N6OKsOMpBdT4kXPDDB9cJk2bJ6mh9ucxdlnNvH1e+roYkKmN9Nxw2yjz7VzeO9oOz2zJ04Pw=="],
"xdg-basedir": ["xdg-basedir@5.1.0", "", {}, "sha512-GCPAHLvrIH13+c0SuacwvRYj2SxJXQ4kaVTT5xgL3kPrz56XxkF21IGhjSE1+W0aw7gpBWRGXLCPnPby6lSpmQ=="],
"xml2js": ["xml2js@0.6.2", "", { "dependencies": { "sax": ">=0.6.0", "xmlbuilder": "~11.0.0" } }, "sha512-T4rieHaC1EXcES0Kxxj4JWgaUQHDk+qwHcYOCFHfiwKz7tOVPLq7Hjq9dM1WCMhylqMEfP7hMcOIChvotiZegA=="],
"xmlbuilder": ["xmlbuilder@11.0.1", "", {}, "sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA=="],
"xxhash-wasm": ["xxhash-wasm@1.1.0", "", {}, "sha512-147y/6YNh+tlp6nd/2pWq38i9h6mz/EuQ6njIrmW8D1BS5nCqs0P6DG+m6zTGnNz5I+uhZ0SHxBs9BsPrwcKDA=="],
"y18n": ["y18n@5.0.8", "", {}, "sha512-0pfFzegeDWJHJIAmTLRP2DwHjdF5s7jo9tuztdQxAhINCdvS+3nGINqPd00AphqJR/0LhANUS6/+7SCb98YOfA=="],
"yallist": ["yallist@4.0.0", "", {}, "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A=="],
"yargs": ["yargs@18.0.0", "", { "dependencies": { "cliui": "^9.0.1", "escalade": "^3.1.1", "get-caller-file": "^2.0.5", "string-width": "^7.2.0", "y18n": "^5.0.5", "yargs-parser": "^22.0.0" } }, "sha512-4UEqdc2RYGHZc7Doyqkrqiln3p9X2DZVxaGbwhn2pi7MrRagKaOcIKe8L3OxYcbhXLgLFUS3zAYuQjKBQgmuNg=="],
"yargs-parser": ["yargs-parser@21.1.1", "", {}, "sha512-tVpsJW7DdjecAiFpbIB1e3qxIQsE6NoPc5/eTdrbbIC4h0LVsWhnoa3g+m2HclBIujHzsxZ4VJVA+GUuc2/LBw=="],
"yocto-queue": ["yocto-queue@1.2.1", "", {}, "sha512-AyeEbWOu/TAXdxlV9wmGcR0+yh2j3vYPGOECcIj2S7MkrLyC7ne+oye2BKTItt0ii2PHk4cDy+95+LshzbXnGg=="],
@@ -1505,6 +1645,8 @@
"yoctocolors": ["yoctocolors@2.1.1", "", {}, "sha512-GQHQqAopRhwU8Kt1DDM8NjibDXHC8eoh1erhGAJPEyveY9qqVeXvVikNKrDz69sHowPMorbPUrH/mx8c50eiBQ=="],
"youch": ["youch@3.3.4", "", { "dependencies": { "cookie": "^0.7.1", "mustache": "^4.2.0", "stacktracey": "^2.1.8" } }, "sha512-UeVBXie8cA35DS6+nBkls68xaBBXCye0CNznrhszZjTbRVnJKQuNsyLKBTTL4ln1o1rh2PKtv35twV7irj5SEg=="],
"zod": ["zod@3.24.2", "", {}, "sha512-lY7CDW43ECgW9u1TcT3IoXHflywfVqDYze4waEz812jR/bZ8FHDsl7pFQoSZTz5N+2NqRXs8GBwnAwo3ZNxqhQ=="],
"zod-openapi": ["zod-openapi@4.2.4", "", { "peerDependencies": { "zod": "^3.21.4" } }, "sha512-tsrQpbpqFCXqVXUzi3TPwFhuMtLN3oNZobOtYnK6/5VkXsNdnIgyNr4r8no4wmYluaxzN3F7iS+8xCW8BmMQ8g=="],
@@ -1515,15 +1657,27 @@
"zwitch": ["zwitch@2.0.4", "", {}, "sha512-bXE4cR/kVZhKZX/RjPEflHaKVhUVl85noU3v6b8apfQEc1x4A+zBxjZ4lN8LqGd6WZ3dl98pY4o717VFmoPp+A=="],
"@ampproject/remapping/@jridgewell/trace-mapping": ["@jridgewell/trace-mapping@0.3.25", "", { "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", "@jridgewell/sourcemap-codec": "^1.4.14" } }, "sha512-vNk6aEwybGtawWmy/PzwnGDOjCkLWSD2wqvjGGAgOAwCGWySYXfYoxt00IJkTF+8Lb57DwOb3Aa0o9CApepiYQ=="],
"@astrojs/mdx/@astrojs/markdown-remark": ["@astrojs/markdown-remark@6.3.2", "", { "dependencies": { "@astrojs/internal-helpers": "0.6.1", "@astrojs/prism": "3.3.0", "github-slugger": "^2.0.0", "hast-util-from-html": "^2.0.3", "hast-util-to-text": "^4.0.2", "import-meta-resolve": "^4.1.0", "js-yaml": "^4.1.0", "mdast-util-definitions": "^6.0.0", "rehype-raw": "^7.0.0", "rehype-stringify": "^10.0.1", "remark-gfm": "^4.0.1", "remark-parse": "^11.0.0", "remark-rehype": "^11.1.2", "remark-smartypants": "^3.0.2", "shiki": "^3.2.1", "smol-toml": "^1.3.1", "unified": "^11.0.5", "unist-util-remove-position": "^5.0.0", "unist-util-visit": "^5.0.0", "unist-util-visit-parents": "^6.0.1", "vfile": "^6.0.3" } }, "sha512-bO35JbWpVvyKRl7cmSJD822e8YA8ThR/YbUsciWNA7yTcqpIAL2hJDToWP5KcZBWxGT6IOdOkHSXARSNZc4l/Q=="],
"@babel/core/semver": ["semver@6.3.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA=="],
"@babel/generator/@jridgewell/trace-mapping": ["@jridgewell/trace-mapping@0.3.25", "", { "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", "@jridgewell/sourcemap-codec": "^1.4.14" } }, "sha512-vNk6aEwybGtawWmy/PzwnGDOjCkLWSD2wqvjGGAgOAwCGWySYXfYoxt00IJkTF+8Lb57DwOb3Aa0o9CApepiYQ=="],
"@babel/helper-compilation-targets/lru-cache": ["lru-cache@5.1.1", "", { "dependencies": { "yallist": "^3.0.2" } }, "sha512-KpNARQA3Iwv+jTA0utUVVbrh+Jlrr1Fv0e56GGzAFOXN7dk/FviaDW8LHmK52DlcH4WP2n6gI8vN1aesBFgo9w=="],
"@babel/helper-compilation-targets/semver": ["semver@6.3.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA=="],
"@emnapi/runtime/tslib": ["tslib@2.8.1", "", {}, "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w=="],
"@jridgewell/gen-mapping/@jridgewell/trace-mapping": ["@jridgewell/trace-mapping@0.3.25", "", { "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", "@jridgewell/sourcemap-codec": "^1.4.14" } }, "sha512-vNk6aEwybGtawWmy/PzwnGDOjCkLWSD2wqvjGGAgOAwCGWySYXfYoxt00IJkTF+8Lb57DwOb3Aa0o9CApepiYQ=="],
"@openauthjs/openauth/@standard-schema/spec": ["@standard-schema/spec@1.0.0-beta.3", "", {}, "sha512-0ifF3BjA1E8SY9C+nUew8RefNOIq0cDlYALPty4rhUm8Rrl6tCM8hBT4bhGhx7I7iXD0uAgt50lgo8dD73ACMw=="],
"@openauthjs/openauth/aws4fetch": ["aws4fetch@1.0.20", "", {}, "sha512-/djoAN709iY65ETD6LKCtyyEI04XIBP5xVvfmNxsEP0uJB5tyaGBztSryRr4HqMStr9R06PisQE7m9zDTXKu6g=="],
"@openauthjs/openauth/jose": ["jose@5.9.6", "", {}, "sha512-AMlnetc9+CV9asI19zHmrgS/WYsWUwCn2R7RzlbJWD7F9eWYUTGyBmU9o6PxngtLGOiDGPRu+Uc4fhKzbpteZQ=="],
"@oslojs/jwt/@oslojs/encoding": ["@oslojs/encoding@0.4.1", "", {}, "sha512-hkjo6MuIK/kQR5CrGNdAPZhS01ZCXuWDRJ187zh6qqF2+yMHZpD9fAYpX8q2bOO6Ryhl3XpCT6kUX76N8hhm4Q=="],
"@rollup/pluginutils/estree-walker": ["estree-walker@2.0.2", "", {}, "sha512-Rfkk/Mp/DL7JVje3u18FxFujQlTNR2q6QfMSMB7AvCBx91NGj/ba3kCfza0f6dVDbw7YlRf/nDrn7pQrCCyQ/w=="],
@@ -1547,10 +1701,16 @@
"express/cookie": ["cookie@0.7.2", "", {}, "sha512-yki5XnKuf750l50uGTllt6kKILY4nQ1eNIQatoXEByZ5dWgnKqbnqmTrBE5B4N7lrMJKQ2ytWMiTO2o0v6Ew/w=="],
"get-source/source-map": ["source-map@0.6.1", "", {}, "sha512-UjgapumWlbMhkBgzT7Ykc5YXUT46F0iKu8SGXq0bcwP5dz/h0Plj6enJqjz1Zbq2l5WaqYnrVbwWOWMyF3F47g=="],
"hast-util-to-parse5/property-information": ["property-information@6.5.0", "", {}, "sha512-PgTgs/BlvHxOu8QuEN7wi5A0OmXaBcHpmCSTehcs6Uuu9IkDIEo13Hy7n898RHfrQ49vKCoGeWZSaAK01nwVig=="],
"mdast-util-find-and-replace/escape-string-regexp": ["escape-string-regexp@5.0.0", "", {}, "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw=="],
"miniflare/acorn": ["acorn@8.14.0", "", { "bin": { "acorn": "bin/acorn" } }, "sha512-cl669nCJTZBsL97OF4kUQm5g5hC2uihk0NxY3WENAC0TYdILVkAyHymAntgxGkl7K+t0cXIrH5siy5S4XkFycA=="],
"miniflare/sharp": ["sharp@0.33.5", "", { "dependencies": { "color": "^4.2.3", "detect-libc": "^2.0.3", "semver": "^7.6.3" }, "optionalDependencies": { "@img/sharp-darwin-arm64": "0.33.5", "@img/sharp-darwin-x64": "0.33.5", "@img/sharp-libvips-darwin-arm64": "1.0.4", "@img/sharp-libvips-darwin-x64": "1.0.4", "@img/sharp-libvips-linux-arm": "1.0.5", "@img/sharp-libvips-linux-arm64": "1.0.4", "@img/sharp-libvips-linux-s390x": "1.0.4", "@img/sharp-libvips-linux-x64": "1.0.4", "@img/sharp-libvips-linuxmusl-arm64": "1.0.4", "@img/sharp-libvips-linuxmusl-x64": "1.0.4", "@img/sharp-linux-arm": "0.33.5", "@img/sharp-linux-arm64": "0.33.5", "@img/sharp-linux-s390x": "0.33.5", "@img/sharp-linux-x64": "0.33.5", "@img/sharp-linuxmusl-arm64": "0.33.5", "@img/sharp-linuxmusl-x64": "0.33.5", "@img/sharp-wasm32": "0.33.5", "@img/sharp-win32-ia32": "0.33.5", "@img/sharp-win32-x64": "0.33.5" } }, "sha512-haPVm1EkS9pgvHrQ/F3Xy+hgcuMV0Wm9vfIBSiwZ05k+xgb0PkBQpGsAA/oWdDobNaZTH5ppvHtzCFbnSEwHVw=="],
"opencontrol/hono": ["hono@4.7.4", "", {}, "sha512-Pst8FuGqz3L7tFF+u9Pu70eI0xa5S3LPUmrNd5Jm8nTHze9FxLTK9Kaj5g/k4UcwuJSXTP65SyHOPLrffpcAJg=="],
"opencontrol/zod-to-json-schema": ["zod-to-json-schema@3.24.3", "", { "peerDependencies": { "zod": "^3.24.1" } }, "sha512-HIAfWdYIt1sssHfYZFCXp4rU1w2r8hVVXYIlmoa0r0gABLs5di3RCqPU5DDROogVz1pAdYBaz7HK5n9pSUNs3A=="],
@@ -1571,6 +1731,8 @@
"rc/strip-json-comments": ["strip-json-comments@2.0.1", "", {}, "sha512-4gB8na07fecVVkOI6Rs4e7T6NOTki5EmL7TUduTs6bu3EdnSycntVJ4re8kgZA+wx9IueI2Y11bfbgwtzuE0KQ=="],
"router/path-to-regexp": ["path-to-regexp@8.2.0", "", {}, "sha512-TdrF7fW9Rphjq4RjrW0Kp2AW0Ahwu9sRGTkS6bvDi0SCwZlEZYmcfDbEsTz8RVk0EHIS/Vd1bv3JhG+1xZuAyQ=="],
"sitemap/@types/node": ["@types/node@17.0.45", "", {}, "sha512-w+tIMs3rq2afQdsPJlODhoUEKzFP1ayaoyl1CcnwtIlsVe7K7bA1NGm4s3PraqTLlXnbIN84zuBlxBWo1u9BLw=="],
"sitemap/sax": ["sax@1.4.1", "", {}, "sha512-+aWOz7yVScEGoKNd4PA10LZ8sk0A/z5+nXQG5giUO5rprX9jgYsTdov9qCchZiPIZezbZH+jRut8nPodFAX4Jg=="],
@@ -1581,6 +1743,12 @@
"vscode-languageserver-protocol/vscode-jsonrpc": ["vscode-jsonrpc@8.1.0", "", {}, "sha512-6TDy/abTQk+zDGYazgbIPc+4JoXdwC8NHU9Pbn4UJP1fehUyZmM4RHp5IthX7A6L5KS30PRui+j+tbbMMMafdw=="],
"wrangler/esbuild": ["esbuild@0.25.4", "", { "optionalDependencies": { "@esbuild/aix-ppc64": "0.25.4", "@esbuild/android-arm": "0.25.4", "@esbuild/android-arm64": "0.25.4", "@esbuild/android-x64": "0.25.4", "@esbuild/darwin-arm64": "0.25.4", "@esbuild/darwin-x64": "0.25.4", "@esbuild/freebsd-arm64": "0.25.4", "@esbuild/freebsd-x64": "0.25.4", "@esbuild/linux-arm": "0.25.4", "@esbuild/linux-arm64": "0.25.4", "@esbuild/linux-ia32": "0.25.4", "@esbuild/linux-loong64": "0.25.4", "@esbuild/linux-mips64el": "0.25.4", "@esbuild/linux-ppc64": "0.25.4", "@esbuild/linux-riscv64": "0.25.4", "@esbuild/linux-s390x": "0.25.4", "@esbuild/linux-x64": "0.25.4", "@esbuild/netbsd-arm64": "0.25.4", "@esbuild/netbsd-x64": "0.25.4", "@esbuild/openbsd-arm64": "0.25.4", "@esbuild/openbsd-x64": "0.25.4", "@esbuild/sunos-x64": "0.25.4", "@esbuild/win32-arm64": "0.25.4", "@esbuild/win32-ia32": "0.25.4", "@esbuild/win32-x64": "0.25.4" }, "bin": { "esbuild": "bin/esbuild" } }, "sha512-8pgjLUcUjcgDg+2Q4NYXnPbo/vncAY4UmyaCm0jZevERqCHZIaWwdJHkf8XQtu4AxSKCdvrUbT0XUr1IdZzI8Q=="],
"yargs/yargs-parser": ["yargs-parser@22.0.0", "", {}, "sha512-rwu/ClNdSMpkSrUb+d6BRsSkLUq1fmfsY6TOpYzTwvwkg1/NRG85KBy3kq++A8LKQwX6lsu+aWad+2khvuXrqw=="],
"youch/cookie": ["cookie@0.7.2", "", {}, "sha512-yki5XnKuf750l50uGTllt6kKILY4nQ1eNIQatoXEByZ5dWgnKqbnqmTrBE5B4N7lrMJKQ2ytWMiTO2o0v6Ew/w=="],
"@astrojs/mdx/@astrojs/markdown-remark/@astrojs/prism": ["@astrojs/prism@3.3.0", "", { "dependencies": { "prismjs": "^1.30.0" } }, "sha512-q8VwfU/fDZNoDOf+r7jUnMC2//H2l0TuQ6FkGJL8vD8nw/q5KiL3DS1KKBI3QhI9UQhpJ5dc7AtqfbXWuOgLCQ=="],
"@babel/helper-compilation-targets/lru-cache/yallist": ["yallist@3.1.1", "", {}, "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g=="],
@@ -1599,6 +1767,56 @@
"prebuild-install/tar-fs/tar-stream": ["tar-stream@2.2.0", "", { "dependencies": { "bl": "^4.0.3", "end-of-stream": "^1.4.1", "fs-constants": "^1.0.0", "inherits": "^2.0.3", "readable-stream": "^3.1.1" } }, "sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ=="],
"wrangler/esbuild/@esbuild/aix-ppc64": ["@esbuild/aix-ppc64@0.25.4", "", { "os": "aix", "cpu": "ppc64" }, "sha512-1VCICWypeQKhVbE9oW/sJaAmjLxhVqacdkvPLEjwlttjfwENRSClS8EjBz0KzRyFSCPDIkuXW34Je/vk7zdB7Q=="],
"wrangler/esbuild/@esbuild/android-arm": ["@esbuild/android-arm@0.25.4", "", { "os": "android", "cpu": "arm" }, "sha512-QNdQEps7DfFwE3hXiU4BZeOV68HHzYwGd0Nthhd3uCkkEKK7/R6MTgM0P7H7FAs5pU/DIWsviMmEGxEoxIZ+ZQ=="],
"wrangler/esbuild/@esbuild/android-arm64": ["@esbuild/android-arm64@0.25.4", "", { "os": "android", "cpu": "arm64" }, "sha512-bBy69pgfhMGtCnwpC/x5QhfxAz/cBgQ9enbtwjf6V9lnPI/hMyT9iWpR1arm0l3kttTr4L0KSLpKmLp/ilKS9A=="],
"wrangler/esbuild/@esbuild/android-x64": ["@esbuild/android-x64@0.25.4", "", { "os": "android", "cpu": "x64" }, "sha512-TVhdVtQIFuVpIIR282btcGC2oGQoSfZfmBdTip2anCaVYcqWlZXGcdcKIUklfX2wj0JklNYgz39OBqh2cqXvcQ=="],
"wrangler/esbuild/@esbuild/darwin-arm64": ["@esbuild/darwin-arm64@0.25.4", "", { "os": "darwin", "cpu": "arm64" }, "sha512-Y1giCfM4nlHDWEfSckMzeWNdQS31BQGs9/rouw6Ub91tkK79aIMTH3q9xHvzH8d0wDru5Ci0kWB8b3up/nl16g=="],
"wrangler/esbuild/@esbuild/darwin-x64": ["@esbuild/darwin-x64@0.25.4", "", { "os": "darwin", "cpu": "x64" }, "sha512-CJsry8ZGM5VFVeyUYB3cdKpd/H69PYez4eJh1W/t38vzutdjEjtP7hB6eLKBoOdxcAlCtEYHzQ/PJ/oU9I4u0A=="],
"wrangler/esbuild/@esbuild/freebsd-arm64": ["@esbuild/freebsd-arm64@0.25.4", "", { "os": "freebsd", "cpu": "arm64" }, "sha512-yYq+39NlTRzU2XmoPW4l5Ifpl9fqSk0nAJYM/V/WUGPEFfek1epLHJIkTQM6bBs1swApjO5nWgvr843g6TjxuQ=="],
"wrangler/esbuild/@esbuild/freebsd-x64": ["@esbuild/freebsd-x64@0.25.4", "", { "os": "freebsd", "cpu": "x64" }, "sha512-0FgvOJ6UUMflsHSPLzdfDnnBBVoCDtBTVyn/MrWloUNvq/5SFmh13l3dvgRPkDihRxb77Y17MbqbCAa2strMQQ=="],
"wrangler/esbuild/@esbuild/linux-arm": ["@esbuild/linux-arm@0.25.4", "", { "os": "linux", "cpu": "arm" }, "sha512-kro4c0P85GMfFYqW4TWOpvmF8rFShbWGnrLqlzp4X1TNWjRY3JMYUfDCtOxPKOIY8B0WC8HN51hGP4I4hz4AaQ=="],
"wrangler/esbuild/@esbuild/linux-arm64": ["@esbuild/linux-arm64@0.25.4", "", { "os": "linux", "cpu": "arm64" }, "sha512-+89UsQTfXdmjIvZS6nUnOOLoXnkUTB9hR5QAeLrQdzOSWZvNSAXAtcRDHWtqAUtAmv7ZM1WPOOeSxDzzzMogiQ=="],
"wrangler/esbuild/@esbuild/linux-ia32": ["@esbuild/linux-ia32@0.25.4", "", { "os": "linux", "cpu": "ia32" }, "sha512-yTEjoapy8UP3rv8dB0ip3AfMpRbyhSN3+hY8mo/i4QXFeDxmiYbEKp3ZRjBKcOP862Ua4b1PDfwlvbuwY7hIGQ=="],
"wrangler/esbuild/@esbuild/linux-loong64": ["@esbuild/linux-loong64@0.25.4", "", { "os": "linux", "cpu": "none" }, "sha512-NeqqYkrcGzFwi6CGRGNMOjWGGSYOpqwCjS9fvaUlX5s3zwOtn1qwg1s2iE2svBe4Q/YOG1q6875lcAoQK/F4VA=="],
"wrangler/esbuild/@esbuild/linux-mips64el": ["@esbuild/linux-mips64el@0.25.4", "", { "os": "linux", "cpu": "none" }, "sha512-IcvTlF9dtLrfL/M8WgNI/qJYBENP3ekgsHbYUIzEzq5XJzzVEV/fXY9WFPfEEXmu3ck2qJP8LG/p3Q8f7Zc2Xg=="],
"wrangler/esbuild/@esbuild/linux-ppc64": ["@esbuild/linux-ppc64@0.25.4", "", { "os": "linux", "cpu": "ppc64" }, "sha512-HOy0aLTJTVtoTeGZh4HSXaO6M95qu4k5lJcH4gxv56iaycfz1S8GO/5Jh6X4Y1YiI0h7cRyLi+HixMR+88swag=="],
"wrangler/esbuild/@esbuild/linux-riscv64": ["@esbuild/linux-riscv64@0.25.4", "", { "os": "linux", "cpu": "none" }, "sha512-i8JUDAufpz9jOzo4yIShCTcXzS07vEgWzyX3NH2G7LEFVgrLEhjwL3ajFE4fZI3I4ZgiM7JH3GQ7ReObROvSUA=="],
"wrangler/esbuild/@esbuild/linux-s390x": ["@esbuild/linux-s390x@0.25.4", "", { "os": "linux", "cpu": "s390x" }, "sha512-jFnu+6UbLlzIjPQpWCNh5QtrcNfMLjgIavnwPQAfoGx4q17ocOU9MsQ2QVvFxwQoWpZT8DvTLooTvmOQXkO51g=="],
"wrangler/esbuild/@esbuild/linux-x64": ["@esbuild/linux-x64@0.25.4", "", { "os": "linux", "cpu": "x64" }, "sha512-6e0cvXwzOnVWJHq+mskP8DNSrKBr1bULBvnFLpc1KY+d+irZSgZ02TGse5FsafKS5jg2e4pbvK6TPXaF/A6+CA=="],
"wrangler/esbuild/@esbuild/netbsd-arm64": ["@esbuild/netbsd-arm64@0.25.4", "", { "os": "none", "cpu": "arm64" }, "sha512-vUnkBYxZW4hL/ie91hSqaSNjulOnYXE1VSLusnvHg2u3jewJBz3YzB9+oCw8DABeVqZGg94t9tyZFoHma8gWZQ=="],
"wrangler/esbuild/@esbuild/netbsd-x64": ["@esbuild/netbsd-x64@0.25.4", "", { "os": "none", "cpu": "x64" }, "sha512-XAg8pIQn5CzhOB8odIcAm42QsOfa98SBeKUdo4xa8OvX8LbMZqEtgeWE9P/Wxt7MlG2QqvjGths+nq48TrUiKw=="],
"wrangler/esbuild/@esbuild/openbsd-arm64": ["@esbuild/openbsd-arm64@0.25.4", "", { "os": "openbsd", "cpu": "arm64" }, "sha512-Ct2WcFEANlFDtp1nVAXSNBPDxyU+j7+tId//iHXU2f/lN5AmO4zLyhDcpR5Cz1r08mVxzt3Jpyt4PmXQ1O6+7A=="],
"wrangler/esbuild/@esbuild/openbsd-x64": ["@esbuild/openbsd-x64@0.25.4", "", { "os": "openbsd", "cpu": "x64" }, "sha512-xAGGhyOQ9Otm1Xu8NT1ifGLnA6M3sJxZ6ixylb+vIUVzvvd6GOALpwQrYrtlPouMqd/vSbgehz6HaVk4+7Afhw=="],
"wrangler/esbuild/@esbuild/sunos-x64": ["@esbuild/sunos-x64@0.25.4", "", { "os": "sunos", "cpu": "x64" }, "sha512-Mw+tzy4pp6wZEK0+Lwr76pWLjrtjmJyUB23tHKqEDP74R3q95luY/bXqXZeYl4NYlvwOqoRKlInQialgCKy67Q=="],
"wrangler/esbuild/@esbuild/win32-arm64": ["@esbuild/win32-arm64@0.25.4", "", { "os": "win32", "cpu": "arm64" }, "sha512-AVUP428VQTSddguz9dO9ngb+E5aScyg7nOeJDrF1HPYu555gmza3bDGMPhmVXL8svDSoqPCsCPjb265yG/kLKQ=="],
"wrangler/esbuild/@esbuild/win32-ia32": ["@esbuild/win32-ia32@0.25.4", "", { "os": "win32", "cpu": "ia32" }, "sha512-i1sW+1i+oWvQzSgfRcxxG2k4I9n3O9NRqy8U+uugaT2Dy7kLO9Y7wI72haOahxceMX8hZAzgGou1FhndRldxRg=="],
"wrangler/esbuild/@esbuild/win32-x64": ["@esbuild/win32-x64@0.25.4", "", { "os": "win32", "cpu": "x64" }, "sha512-nOT2vZNw6hJ+z43oP1SPea/G/6AbN6X+bGNhNuq8NtRHy4wsMhw765IKLNmnjek7GvjWBYQ8Q5VBoYTFg9y1UQ=="],
"ansi-align/string-width/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
"args/chalk/ansi-styles/color-convert": ["color-convert@1.9.3", "", { "dependencies": { "color-name": "1.1.3" } }, "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg=="],

View File

@@ -31,14 +31,10 @@ export const api = new sst.cloudflare.Worker("Api", {
},
})
new sst.cloudflare.StaticSite("Web", {
path: "packages/web",
new sst.cloudflare.x.Astro("Web", {
domain,
path: "packages/web",
environment: {
VITE_API_URL: api.url,
},
build: {
command: "bun run build",
output: "dist",
},
})

25
install
View File

@@ -12,23 +12,28 @@ requested_version=${VERSION:-}
os=$(uname -s | tr '[:upper:]' '[:lower:]')
if [[ "$os" == "darwin" ]]; then
os="mac"
os="darwin"
fi
arch=$(uname -m)
if [[ "$arch" == "aarch64" ]]; then
arch="arm64"
elif [[ "$arch" == "x86_64" ]]; then
arch="x64"
fi
filename="$APP-$os-$arch.tar.gz"
filename="$APP-$os-$arch.zip"
case "$filename" in
*"-linux-"*)
[[ "$arch" == "x86_64" || "$arch" == "arm64" || "$arch" == "i386" ]] || exit 1
[[ "$arch" == "x64" || "$arch" == "arm64" ]] || exit 1
;;
*"-mac-"*)
[[ "$arch" == "x86_64" || "$arch" == "arm64" ]] || exit 1
*"-darwin-"*)
[[ "$arch" == "x64" || "$arch" == "arm64" ]] || exit 1
;;
*"-windows-"*)
[[ "$arch" == "x64" ]] || exit 1
;;
*)
echo "${RED}Unsupported OS/Arch: $os/$arch${NC}"
@@ -88,8 +93,9 @@ check_version() {
download_and_install() {
print_message info "Downloading ${ORANGE}opencode ${GREEN}version: ${YELLOW}$specific_version ${GREEN}..."
mkdir -p opencodetmp && cd opencodetmp
curl -# -L $url | tar xz
mv opencode $INSTALL_DIR
curl -# -L -o "$filename" "$url"
unzip -q "$filename"
mv opencode "$INSTALL_DIR"
cd .. && rm -rf opencodetmp
}
@@ -101,7 +107,9 @@ add_to_path() {
local config_file=$1
local command=$2
if [[ -w $config_file ]]; then
if grep -Fxq "$command" "$config_file"; then
print_message info "Command already exists in $config_file, skipping write."
elif [[ -w $config_file ]]; then
echo -e "\n# opencode" >> "$config_file"
echo "$command" >> "$config_file"
print_message info "Successfully added ${ORANGE}opencode ${GREEN}to \$PATH in $config_file"
@@ -167,6 +175,7 @@ if [[ ":$PATH:" != *":$INSTALL_DIR:"* ]]; then
add_to_path "$config_file" "export PATH=$INSTALL_DIR:\$PATH"
;;
*)
export PATH=$INSTALL_DIR:$PATH
print_message warning "Manually add the directory to $config_file (or similar):"
print_message info " export PATH=$INSTALL_DIR:\$PATH"
;;

4
opencode.json Normal file
View File

@@ -0,0 +1,4 @@
{
"$schema": "https://opencode.ai/config.json",
"mcp": {}
}

View File

@@ -6,7 +6,7 @@
"packageManager": "bun@1.2.14",
"scripts": {
"typecheck": "bun run --filter='*' typecheck",
"dev": "sst dev"
"postinstall": "./scripts/hooks"
},
"workspaces": {
"packages": [
@@ -16,12 +16,12 @@
"typescript": "5.8.2",
"@types/node": "22.13.9",
"zod": "3.24.2",
"ai": "5.0.0-alpha.7"
"ai": "4.3.16"
}
},
"devDependencies": {
"prettier": "3.5.3",
"sst": "3.16.0"
"sst": "3.17.6"
},
"repository": {
"type": "git",
@@ -38,5 +38,8 @@
"esbuild",
"protobufjs",
"sharp"
]
],
"patchedDependencies": {
"ai@4.3.16": "patches/ai@4.3.16.patch"
}
}

View File

@@ -19,9 +19,9 @@ export class SyncServer extends DurableObject<Env> {
this.ctx.acceptWebSocket(server)
const data = await this.ctx.storage.list()
for (const [key, content] of data.entries()) {
server.send(JSON.stringify({ key, content }))
}
Array.from(data.entries())
.filter(([key, _]) => key.startsWith("session/"))
.map(([key, content]) => server.send(JSON.stringify({ key, content })))
return new Response(null, {
status: 101,
@@ -69,6 +69,13 @@ export class SyncServer extends DurableObject<Env> {
return secret
}
public async getData() {
const data = await this.ctx.storage.list()
return Array.from(data.entries())
.filter(([key, _]) => key.startsWith("session/"))
.map(([key, content]) => ({ key, content }))
}
private async getSecret() {
return this.ctx.storage.get<string>("secret")
}
@@ -113,7 +120,7 @@ export default {
return new Response(
JSON.stringify({
secret,
url: "https://dev.opencode.ai/s?id=" + short,
url: "https://dev.opencode.ai/s/" + short,
}),
{
headers: { "Content-Type": "application/json" },
@@ -163,5 +170,39 @@ export default {
const stub = env.SYNC_SERVER.get(env.SYNC_SERVER.idFromName(id))
return stub.fetch(request)
}
if (request.method === "GET" && method === "share_data") {
const id = url.searchParams.get("id")
console.log("share_data", id)
if (!id)
return new Response("Error: Share ID is required", { status: 400 })
const stub = env.SYNC_SERVER.get(env.SYNC_SERVER.idFromName(id))
const data = await stub.getData()
let info
const messages: Record<string, any> = {}
data.forEach((d) => {
const [root, type, ...splits] = d.key.split("/")
if (root !== "session") return
if (type === "info") {
info = d.content
return
}
if (type === "message") {
const [, messageID] = splits
messages[messageID] = d.content
}
})
return new Response(
JSON.stringify({
info,
messages,
}),
{
headers: { "Content-Type": "application/json" },
},
)
}
},
}

View File

@@ -7,7 +7,7 @@ import "sst"
declare module "sst" {
export interface Resource {
"Web": {
"type": "sst.cloudflare.StaticSite"
"type": "sst.cloudflare.Astro"
"url": string
}
}

View File

@@ -1,4 +1,5 @@
node_modules
research
dist
gen
app.log

View File

@@ -0,0 +1,39 @@
# opencode agent guidelines
## Build/Test Commands
- **Install**: `bun install`
- **Run**: `bun run index.ts`
- **Typecheck**: `bun run typecheck` (npm run typecheck)
- **Test**: `bun test` (runs all tests)
- **Single test**: `bun test test/tool/tool.test.ts` (specific test file)
## Code Style
- **Runtime**: Bun with TypeScript ESM modules
- **Imports**: Use relative imports for local modules, named imports preferred
- **Types**: Zod schemas for validation, TypeScript interfaces for structure
- **Naming**: camelCase for variables/functions, PascalCase for classes/namespaces
- **Error handling**: Use Result patterns, avoid throwing exceptions in tools
- **File structure**: Namespace-based organization (e.g., `Tool.define()`, `Session.create()`)
## IMPORTANT
- Try to keep things in one function unless composable or reusable
- DO NOT do unnecessary destructuring of variables
- DO NOT use `else` statements unless necessary
- DO NOT use `try`/`catch` if it can be avoided
- AVOID `try`/`catch` where possible
- AVOID `else` statements
- AVOID using `any` type
- AVOID `let` statements
- PREFER single word variable names where possible
- Use as many bun apis as possible like Bun.file()
## Architecture
- **Tools**: Implement `Tool.Info` interface with `execute()` method
- **Context**: Pass `sessionID` in tool context, use `App.provide()` for DI
- **Validation**: All inputs validated with Zod schemas
- **Logging**: Use `Log.create({ service: "name" })` pattern
- **Storage**: Use `Storage` namespace for persistence

View File

@@ -49,7 +49,7 @@ else
done
if [ -z "$resolved" ]; then
printf "It seems that your package manager failed to install the right version of the SST CLI for your platform. You can try manually installing the \"%s\" package\n" "$name" >&2
printf "It seems that your package manager failed to install the right version of the OpenCode CLI for your platform. You can try manually installing the \"%s\" package\n" "$name" >&2
exit 1
fi
fi

View File

@@ -0,0 +1,265 @@
{
"type": "object",
"properties": {
"$schema": {
"type": "string"
},
"theme": {
"type": "string"
},
"keybinds": {
"type": "object",
"properties": {
"leader": {
"type": "string"
},
"help": {
"type": "string"
},
"editor_open": {
"type": "string"
},
"session_new": {
"type": "string"
},
"session_list": {
"type": "string"
},
"session_share": {
"type": "string"
},
"session_interrupt": {
"type": "string"
},
"session_compact": {
"type": "string"
},
"tool_details": {
"type": "string"
},
"model_list": {
"type": "string"
},
"theme_list": {
"type": "string"
},
"project_init": {
"type": "string"
},
"input_clear": {
"type": "string"
},
"input_paste": {
"type": "string"
},
"input_submit": {
"type": "string"
},
"input_newline": {
"type": "string"
},
"history_previous": {
"type": "string"
},
"history_next": {
"type": "string"
},
"messages_page_up": {
"type": "string"
},
"messages_page_down": {
"type": "string"
},
"messages_half_page_up": {
"type": "string"
},
"messages_half_page_down": {
"type": "string"
},
"messages_previous": {
"type": "string"
},
"messages_next": {
"type": "string"
},
"messages_first": {
"type": "string"
},
"messages_last": {
"type": "string"
},
"app_exit": {
"type": "string"
}
},
"additionalProperties": false
},
"autoshare": {
"type": "boolean",
"description": "Share newly created sessions automatically"
},
"autoupdate": {
"type": "boolean",
"description": "Automatically update to the latest version"
},
"disabled_providers": {
"type": "array",
"items": {
"type": "string"
},
"description": "Disable providers that are loaded automatically"
},
"model": {
"type": "string",
"description": "Model to use in the format of provider/model, eg anthropic/claude-2"
},
"provider": {
"type": "object",
"additionalProperties": {
"type": "object",
"properties": {
"api": {
"type": "string"
},
"name": {
"type": "string"
},
"env": {
"type": "array",
"items": {
"type": "string"
}
},
"id": {
"type": "string"
},
"npm": {
"type": "string"
},
"models": {
"type": "object",
"additionalProperties": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"attachment": {
"type": "boolean"
},
"reasoning": {
"type": "boolean"
},
"temperature": {
"type": "boolean"
},
"cost": {
"type": "object",
"properties": {
"input": {
"type": "number"
},
"output": {
"type": "number"
},
"cache_read": {
"type": "number"
},
"cache_write": {
"type": "number"
}
},
"required": [
"input",
"output"
],
"additionalProperties": false
},
"limit": {
"type": "object",
"properties": {
"context": {
"type": "number"
},
"output": {
"type": "number"
}
},
"required": [
"context",
"output"
],
"additionalProperties": false
},
"id": {
"type": "string"
}
},
"additionalProperties": false
}
},
"options": {
"type": "object",
"additionalProperties": {}
}
},
"required": [
"models"
],
"additionalProperties": false
}
},
"mcp": {
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "local"
},
"command": {
"type": "array",
"items": {
"type": "string"
}
},
"environment": {
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"type",
"command"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "remote"
},
"url": {
"type": "string"
}
},
"required": [
"type",
"url"
],
"additionalProperties": false
}
]
}
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}

View File

@@ -5,37 +5,42 @@
"type": "module",
"private": true,
"scripts": {
"typecheck": "tsc --noEmit"
"typecheck": "tsc --noEmit",
"dev": "bun run ./src/index.ts"
},
"exports": {
"./*": [
"./src/*.ts",
"./src/*/index.ts"
]
"./*": "./src/*.ts"
},
"devDependencies": {
"@tsconfig/bun": "1.0.7",
"@types/bun": "latest",
"@types/turndown": "5.0.5",
"typescript": "catalog:"
"@types/yargs": "17.0.33",
"typescript": "catalog:",
"zod-to-json-schema": "3.24.5",
"@ai-sdk/anthropic": "1.2.12"
},
"dependencies": {
"@clack/prompts": "0.11.0",
"@flystorage/file-storage": "1.1.0",
"@flystorage/local-fs": "1.1.0",
"@hono/zod-validator": "0.5.0",
"@openauthjs/openauth": "0.4.3",
"@standard-schema/spec": "1.0.0",
"ai": "catalog:",
"cac": "6.7.14",
"decimal.js": "10.5.0",
"diff": "8.0.2",
"env-paths": "3.0.0",
"hono": "4.7.10",
"hono-openapi": "0.4.8",
"open": "10.1.2",
"remeda": "2.22.3",
"ts-lsp-client": "1.0.3",
"turndown": "7.2.0",
"vscode-jsonrpc": "8.2.1",
"vscode-languageclient": "8",
"xdg-basedir": "5.1.0",
"yargs": "18.0.0",
"zod": "catalog:",
"zod-openapi": "4.2.4"
}

View File

@@ -0,0 +1,90 @@
#!/usr/bin/env node
import fs from "fs"
import path from "path"
import os from "os"
import { fileURLToPath } from "url"
import { createRequire } from "module"
const __dirname = path.dirname(fileURLToPath(import.meta.url))
const require = createRequire(import.meta.url)
function detectPlatformAndArch() {
// Map platform names
let platform
switch (os.platform()) {
case "darwin":
platform = "darwin"
break
case "linux":
platform = "linux"
break
case "win32":
platform = "win32"
break
default:
platform = os.platform()
break
}
// Map architecture names
let arch
switch (os.arch()) {
case "x64":
arch = "x64"
break
case "arm64":
arch = "arm64"
break
case "arm":
arch = "arm"
break
default:
arch = os.arch()
break
}
return { platform, arch }
}
function findBinary() {
const { platform, arch } = detectPlatformAndArch()
const packageName = `opencode-${platform}-${arch}`
const binary = platform === "win32" ? "opencode.exe" : "opencode"
try {
// Use require.resolve to find the package
const packageJsonPath = require.resolve(`${packageName}/package.json`)
const packageDir = path.dirname(packageJsonPath)
const binaryPath = path.join(packageDir, "bin", binary)
if (!fs.existsSync(binaryPath)) {
throw new Error(`Binary not found at ${binaryPath}`)
}
return binaryPath
} catch (error) {
throw new Error(`Could not find package ${packageName}: ${error.message}`)
}
}
function main() {
try {
const binaryPath = findBinary()
const binScript = path.join(__dirname, "bin", "opencode")
// Remove existing bin script if it exists
if (fs.existsSync(binScript)) {
fs.unlinkSync(binScript)
}
// Create symlink to the actual binary
fs.symlinkSync(binaryPath, binScript)
console.log(`OpenCode binary symlinked: ${binScript} -> ${binaryPath}`)
} catch (error) {
console.error("Failed to create OpenCode binary symlink:", error.message)
process.exit(1)
}
}
main()

View File

@@ -0,0 +1,235 @@
#!/usr/bin/env bun
import { $ } from "bun"
import pkg from "../package.json"
const dry = process.argv.includes("--dry")
const snapshot = process.argv.includes("--snapshot")
const version = snapshot
? `0.0.0-${new Date().toISOString().slice(0, 16).replace(/[-:T]/g, "")}`
: await $`git describe --tags --exact-match HEAD`
.text()
.then((x) => x.substring(1).trim())
.catch(() => {
console.error("tag not found")
process.exit(1)
})
console.log(`publishing ${version}`)
const GOARCH: Record<string, string> = {
arm64: "arm64",
x64: "amd64",
}
const targets = [
["linux", "arm64"],
["linux", "x64"],
["darwin", "x64"],
["darwin", "arm64"],
// ["windows", "x64"],
]
await $`rm -rf dist`
const optionalDependencies: Record<string, string> = {}
const npmTag = snapshot ? "snapshot" : "latest"
for (const [os, arch] of targets) {
console.log(`building ${os}-${arch}`)
const name = `${pkg.name}-${os}-${arch}`
await $`mkdir -p dist/${name}/bin`
await $`GOOS=${os} GOARCH=${GOARCH[arch]} go build -ldflags="-s -w -X main.Version=${version}" -o ../opencode/dist/${name}/bin/tui ../tui/cmd/opencode/main.go`.cwd(
"../tui",
)
await $`bun build --define OPENCODE_VERSION="'${version}'" --compile --minify --target=bun-${os}-${arch} --outfile=dist/${name}/bin/opencode ./src/index.ts ./dist/${name}/bin/tui`
await $`rm -rf ./dist/${name}/bin/tui`
await Bun.file(`dist/${name}/package.json`).write(
JSON.stringify(
{
name,
version,
os: [os === "windows" ? "win32" : os],
cpu: [arch],
},
null,
2,
),
)
if (!dry)
await $`cd dist/${name} && bun publish --access public --tag ${npmTag}`
optionalDependencies[name] = version
}
await $`mkdir -p ./dist/${pkg.name}`
await $`cp -r ./bin ./dist/${pkg.name}/bin`
await $`cp ./script/postinstall.mjs ./dist/${pkg.name}/postinstall.mjs`
await Bun.file(`./dist/${pkg.name}/package.json`).write(
JSON.stringify(
{
name: pkg.name + "-ai",
bin: {
[pkg.name]: `./bin/${pkg.name}`,
},
scripts: {
postinstall: "node ./postinstall.mjs",
},
version,
optionalDependencies,
},
null,
2,
),
)
if (!dry)
await $`cd ./dist/${pkg.name} && bun publish --access public --tag ${npmTag}`
if (!snapshot) {
// Github Release
for (const key of Object.keys(optionalDependencies)) {
await $`cd dist/${key}/bin && zip -r ../../${key}.zip *`
}
const previous = await fetch(
"https://api.github.com/repos/sst/opencode/releases/latest",
)
.then((res) => res.json())
.then((data) => data.tag_name)
const commits = await fetch(
`https://api.github.com/repos/sst/opencode/compare/${previous}...HEAD`,
)
.then((res) => res.json())
.then((data) => data.commits || [])
const notes = commits
.map((commit: any) => `- ${commit.commit.message.split("\n")[0]}`)
.filter((x: string) => {
const lower = x.toLowerCase()
return (
!lower.includes("ignore:") &&
!lower.includes("ci:") &&
!lower.includes("docs:") &&
!lower.includes("doc:")
)
})
.join("\n")
if (!dry)
await $`gh release create v${version} --title "v${version}" --notes ${notes} ./dist/*.zip`
// Calculate SHA values
const arm64Sha =
await $`sha256sum ./dist/opencode-linux-arm64.zip | cut -d' ' -f1`
.text()
.then((x) => x.trim())
const x64Sha =
await $`sha256sum ./dist/opencode-linux-x64.zip | cut -d' ' -f1`
.text()
.then((x) => x.trim())
const macX64Sha =
await $`sha256sum ./dist/opencode-darwin-x64.zip | cut -d' ' -f1`
.text()
.then((x) => x.trim())
const macArm64Sha =
await $`sha256sum ./dist/opencode-darwin-arm64.zip | cut -d' ' -f1`
.text()
.then((x) => x.trim())
// AUR package
const pkgbuild = [
"# Maintainer: dax",
"# Maintainer: adam",
"",
"pkgname='opencode-bin'",
`pkgver=${version.split("-")[0]}`,
"options=('!debug' '!strip')",
"pkgrel=1",
"pkgdesc='The AI coding agent built for the terminal.'",
"url='https://github.com/sst/opencode'",
"arch=('aarch64' 'x86_64')",
"license=('MIT')",
"provides=('opencode')",
"conflicts=('opencode')",
"depends=('fzf' 'ripgrep')",
"",
`source_aarch64=("\${pkgname}_\${pkgver}_aarch64.zip::https://github.com/sst/opencode/releases/download/v${version}/opencode-linux-arm64.zip")`,
`sha256sums_aarch64=('${arm64Sha}')`,
"",
`source_x86_64=("\${pkgname}_\${pkgver}_x86_64.zip::https://github.com/sst/opencode/releases/download/v${version}/opencode-linux-x64.zip")`,
`sha256sums_x86_64=('${x64Sha}')`,
"",
"package() {",
' install -Dm755 ./opencode "${pkgdir}/usr/bin/opencode"',
"}",
"",
].join("\n")
await $`rm -rf ./dist/aur-opencode-bin`
await $`git clone ssh://aur@aur.archlinux.org/opencode-bin.git ./dist/aur-opencode-bin`
await Bun.file("./dist/aur-opencode-bin/PKGBUILD").write(pkgbuild)
await $`cd ./dist/aur-opencode-bin && makepkg --printsrcinfo > .SRCINFO`
await $`cd ./dist/aur-opencode-bin && git add PKGBUILD .SRCINFO`
await $`cd ./dist/aur-opencode-bin && git commit -m "Update to v${version}"`
if (!dry) await $`cd ./dist/aur-opencode-bin && git push`
// Homebrew formula
const homebrewFormula = [
"# typed: false",
"# frozen_string_literal: true",
"",
"# This file was generated by GoReleaser. DO NOT EDIT.",
"class Opencode < Formula",
` desc "The AI coding agent built for the terminal."`,
` homepage "https://github.com/sst/opencode"`,
` version "${version.split("-")[0]}"`,
"",
" on_macos do",
" if Hardware::CPU.intel?",
` url "https://github.com/sst/opencode/releases/download/v${version}/opencode-darwin-x64.zip"`,
` sha256 "${macX64Sha}"`,
"",
" def install",
' bin.install "opencode"',
" end",
" end",
" if Hardware::CPU.arm?",
` url "https://github.com/sst/opencode/releases/download/v${version}/opencode-darwin-arm64.zip"`,
` sha256 "${macArm64Sha}"`,
"",
" def install",
' bin.install "opencode"',
" end",
" end",
" end",
"",
" on_linux do",
" if Hardware::CPU.intel? and Hardware::CPU.is_64_bit?",
` url "https://github.com/sst/opencode/releases/download/v${version}/opencode-linux-x64.zip"`,
` sha256 "${x64Sha}"`,
" def install",
' bin.install "opencode"',
" end",
" end",
" if Hardware::CPU.arm? and Hardware::CPU.is_64_bit?",
` url "https://github.com/sst/opencode/releases/download/v${version}/opencode-linux-arm64.zip"`,
` sha256 "${arm64Sha}"`,
" def install",
' bin.install "opencode"',
" end",
" end",
" end",
"end",
"",
"",
].join("\n")
await $`rm -rf ./dist/homebrew-tap`
await $`git clone https://${process.env["GITHUB_TOKEN"]}@github.com/sst/homebrew-tap.git ./dist/homebrew-tap`
await Bun.file("./dist/homebrew-tap/opencode.rb").write(homebrewFormula)
await $`cd ./dist/homebrew-tap && git add opencode.rb`
await $`cd ./dist/homebrew-tap && git commit -m "Update to v${version}"`
if (!dry) await $`cd ./dist/homebrew-tap && git push`
}

View File

@@ -1,69 +0,0 @@
#!/usr/bin/env bun
import { $ } from "bun"
import pkg from "../package.json"
const dry = process.argv.includes("--dry")
const version = `0.0.0-${Date.now()}`
const GOARCH: Record<string, string> = {
arm64: "arm64",
x64: "amd64",
}
const targets = [
["linux", "arm64"],
["linux", "x64"],
["darwin", "x64"],
["darwin", "arm64"],
["windows", "x64"],
]
await $`rm -rf dist`
const optionalDependencies: Record<string, string> = {}
for (const [os, arch] of targets) {
console.log(`building ${os}-${arch}`)
const name = `${pkg.name}-${os}-${arch}`
await $`mkdir -p dist/${name}/bin`
await $`GOOS=${os} GOARCH=${GOARCH[arch]} go build -ldflags="-s -w -X github.com/sst/opencode/internal/version.Version=${version}" -o ../opencode/dist/${name}/bin/tui ../tui/main.go`.cwd(
"../tui",
)
await $`bun build --define OPENCODE_VERSION="'${version}'" --compile --minify --target=bun-${os}-${arch} --outfile=dist/${name}/bin/opencode ./src/index.ts ./dist/${name}/bin/tui`
await $`rm -rf ./dist/${name}/bin/tui`
await Bun.file(`dist/${name}/package.json`).write(
JSON.stringify(
{
name,
version,
os: [os === "windows" ? "win32" : os],
cpu: [arch],
},
null,
2,
),
)
if (!dry) await $`cd dist/${name} && npm publish --access public --tag latest`
optionalDependencies[name] = version
}
await $`mkdir -p ./dist/${pkg.name}`
await $`cp -r ./bin ./dist/${pkg.name}/bin`
await Bun.file(`./dist/${pkg.name}/package.json`).write(
JSON.stringify(
{
name: pkg.name + "-ai",
bin: {
[pkg.name]: `./bin/${pkg.name}`,
},
version,
optionalDependencies,
},
null,
2,
),
)
if (!dry)
await $`cd ./dist/${pkg.name} && npm publish --access public --tag latest`

View File

@@ -0,0 +1,8 @@
#!/usr/bin/env bun
import "zod-openapi/extend"
import { Config } from "../src/config/config"
import { zodToJsonSchema } from "zod-to-json-schema"
const result = zodToJsonSchema(Config.Info)
await Bun.write("config.schema.json", JSON.stringify(result, null, 2))

View File

@@ -3,6 +3,7 @@ import { Context } from "../util/context"
import { Filesystem } from "../util/filesystem"
import { Global } from "../global"
import path from "path"
import os from "os"
import { z } from "zod"
export namespace App {
@@ -10,13 +11,17 @@ export namespace App {
export const Info = z
.object({
time: z.object({
initialized: z.number().optional(),
}),
user: z.string(),
git: z.boolean(),
path: z.object({
config: z.string(),
data: z.string(),
root: z.string(),
cwd: z.string(),
state: z.string(),
}),
time: z.object({
initialized: z.number().optional(),
}),
})
.openapi({
@@ -26,20 +31,26 @@ export namespace App {
const ctx = Context.create<Awaited<ReturnType<typeof create>>>("app")
async function create(input: { cwd: string; version: string }) {
const git = await Filesystem.findUp(".git", input.cwd).then((x) =>
const APP_JSON = "app.json"
async function create(input: { cwd: string }) {
log.info("creating", {
cwd: input.cwd,
})
const git = await Filesystem.findUp(".git", input.cwd).then(([x]) =>
x ? path.dirname(x) : undefined,
)
log.info("git", { git })
const data = path.join(Global.data(), git ?? "global")
await Bun.write(path.join(data, "version"), input.version)
const stateFile = Bun.file(path.join(data, "state"))
const state = ((await stateFile.exists()) ? stateFile.json() : {}) as {
const data = path.join(
Global.Path.data,
"project",
git ? git.split(path.sep).join("-") : "global",
)
const stateFile = Bun.file(path.join(data, APP_JSON))
const state = (await stateFile.json().catch(() => ({}))) as {
initialized: number
version: string
}
state.version = input.version
if (!git) state.initialized = Date.now()
await stateFile.write(JSON.stringify(state))
const services = new Map<
@@ -50,13 +61,15 @@ export namespace App {
}
>()
await Log.file(path.join(data, "log"))
const info: Info = {
user: os.userInfo().username,
time: {
initialized: state.initialized,
},
git: git !== undefined,
path: {
config: Global.Path.config,
state: Global.Path.state,
data,
root: git ?? input.cwd,
cwd: input.cwd,
@@ -82,7 +95,7 @@ export namespace App {
log.info("registering service", { name: key })
services.set(key, {
state: init(app.info),
shutdown: shutdown,
shutdown,
})
}
return services.get(key)?.state as State
@@ -93,19 +106,30 @@ export namespace App {
return ctx.use().info
}
export async function provide<T extends (app: Info) => any>(
input: { cwd: string; version: string },
cb: T,
export async function provide<T>(
input: { cwd: string },
cb: (app: Info) => Promise<T>,
) {
const app = await create(input)
return ctx.provide(app, async () => {
const result = await cb(app.info)
for (const [key, entry] of app.services.entries()) {
if (!entry.shutdown) continue
log.info("shutdown", { name: key })
await entry.shutdown?.(await entry.state)
}
return result
})
}
export async function initialize() {
const { info } = ctx.use()
info.time.initialized = Date.now()
await Bun.write(
path.join(info.path.data, APP_JSON),
JSON.stringify({
initialized: Date.now(),
}),
)
}
}

View File

@@ -0,0 +1,90 @@
import { generatePKCE } from "@openauthjs/openauth/pkce"
import { Auth } from "./index"
export namespace AuthAnthropic {
const CLIENT_ID = "9d1c250a-e61b-44d9-88ed-5944d1962f5e"
export async function authorize() {
const pkce = await generatePKCE()
const url = new URL("https://claude.ai/oauth/authorize", import.meta.url)
url.searchParams.set("code", "true")
url.searchParams.set("client_id", "9d1c250a-e61b-44d9-88ed-5944d1962f5e")
url.searchParams.set("response_type", "code")
url.searchParams.set(
"redirect_uri",
"https://console.anthropic.com/oauth/code/callback",
)
url.searchParams.set(
"scope",
"org:create_api_key user:profile user:inference",
)
url.searchParams.set("code_challenge", pkce.challenge)
url.searchParams.set("code_challenge_method", "S256")
url.searchParams.set("state", pkce.verifier)
return {
url: url.toString(),
verifier: pkce.verifier,
}
}
export async function exchange(code: string, verifier: string) {
const splits = code.split("#")
const result = await fetch("https://console.anthropic.com/v1/oauth/token", {
method: "POST",
headers: {
"Content-Type": "application/json",
},
body: JSON.stringify({
code: splits[0],
state: splits[1],
grant_type: "authorization_code",
client_id: "9d1c250a-e61b-44d9-88ed-5944d1962f5e",
redirect_uri: "https://console.anthropic.com/oauth/code/callback",
code_verifier: verifier,
}),
})
if (!result.ok) throw new ExchangeFailed()
const json = await result.json()
await Auth.set("anthropic", {
type: "oauth",
refresh: json.refresh_token as string,
access: json.access_token as string,
expires: Date.now() + json.expires_in * 1000,
})
}
export async function access() {
const info = await Auth.get("anthropic")
if (!info || info.type !== "oauth") return
if (info.access && info.expires > Date.now()) return info.access
const response = await fetch(
"https://console.anthropic.com/v1/oauth/token",
{
method: "POST",
headers: {
"Content-Type": "application/json",
},
body: JSON.stringify({
grant_type: "refresh_token",
refresh_token: info.refresh,
client_id: CLIENT_ID,
}),
},
)
if (!response.ok) return
const json = await response.json()
await Auth.set("anthropic", {
type: "oauth",
refresh: json.refresh_token as string,
access: json.access_token as string,
expires: Date.now() + json.expires_in * 1000,
})
return json.access_token as string
}
export class ExchangeFailed extends Error {
constructor() {
super("Exchange failed")
}
}
}

View File

@@ -0,0 +1,51 @@
import path from "path"
import { Global } from "../global"
import fs from "fs/promises"
import { z } from "zod"
export namespace Auth {
export const Oauth = z.object({
type: z.literal("oauth"),
refresh: z.string(),
access: z.string(),
expires: z.number(),
})
export const Api = z.object({
type: z.literal("api"),
key: z.string(),
})
export const Info = z.discriminatedUnion("type", [Oauth, Api])
export type Info = z.infer<typeof Info>
const filepath = path.join(Global.Path.data, "auth.json")
export async function get(providerID: string) {
const file = Bun.file(filepath)
return file
.json()
.catch(() => ({}))
.then((x) => x[providerID] as Info | undefined)
}
export async function all(): Promise<Record<string, Info>> {
const file = Bun.file(filepath)
return file.json().catch(() => ({}))
}
export async function set(key: string, info: Info) {
const file = Bun.file(filepath)
const data = await all()
await Bun.write(file, JSON.stringify({ ...data, [key]: info }, null, 2))
await fs.chmod(file.name!, 0o600)
}
export async function remove(key: string) {
const file = Bun.file(filepath)
const data = await all()
delete data[key]
await Bun.write(file, JSON.stringify(data, null, 2))
await fs.chmod(file.name!, 0o600)
}
}

View File

@@ -1,32 +1,68 @@
import path from "path"
import { z } from "zod"
import { Global } from "../global"
import { Log } from "../util/log"
import path from "path"
import { NamedError } from "../util/error"
export namespace BunProc {
const log = Log.create({ service: "bun" })
export function run(
export async function run(
cmd: string[],
options?: Bun.SpawnOptions.OptionsObject<any, any, any>,
) {
const root =
process.argv0 !== "bun"
? path.resolve(process.cwd(), process.argv0)
: process.argv0
log.info("running", {
cmd: [root, ...cmd],
cmd: [which(), ...cmd],
options,
})
const result = Bun.spawnSync([root, ...cmd], {
const result = Bun.spawn([which(), ...cmd], {
...options,
argv0: "bun",
stdout: "pipe",
stderr: "pipe",
env: {
...process.env,
...options?.env,
BUN_BE_BUN: "1",
},
})
if (result.exitCode !== 0) {
console.error(result.stderr?.toString("utf8") ?? "")
const code = await result.exited
if (code !== 0) {
throw new Error(`Command failed with exit code ${result.exitCode}`)
}
return result
}
export function which() {
return process.execPath
}
export const InstallFailedError = NamedError.create(
"BunInstallFailedError",
z.object({
pkg: z.string(),
version: z.string(),
}),
)
export async function install(pkg: string, version = "latest") {
const mod = path.join(Global.Path.cache, "node_modules", pkg)
const pkgjson = Bun.file(path.join(Global.Path.cache, "package.json"))
const parsed = await pkgjson.json().catch(() => ({
dependencies: {},
}))
if (parsed.dependencies[pkg] === version) return mod
parsed.dependencies[pkg] = version
await Bun.write(pkgjson, JSON.stringify(parsed, null, 2))
await BunProc.run(["install"], {
cwd: Global.Path.cache,
}).catch((e) => {
new InstallFailedError(
{ pkg, version },
{
cause: e,
},
)
})
return mod
}
}

View File

@@ -78,6 +78,18 @@ export namespace Bus {
return raw(def.type, callback)
}
export function once<Definition extends EventDefinition>(
def: Definition,
callback: (event: {
type: Definition["type"]
properties: z.infer<Definition["properties"]>
}) => "done" | undefined,
) {
const unsub = subscribe(def, (event) => {
if (callback(event)) unsub()
})
}
export function subscribeAll(callback: (event: any) => void) {
return raw("*", callback)
}

View File

@@ -0,0 +1,191 @@
import { AuthAnthropic } from "../../auth/anthropic"
import { Auth } from "../../auth"
import { cmd } from "./cmd"
import * as prompts from "@clack/prompts"
import open from "open"
import { UI } from "../ui"
import { ModelsDev } from "../../provider/models"
import { map, pipe, sortBy, values } from "remeda"
export const AuthCommand = cmd({
command: "auth",
describe: "manage credentials",
builder: (yargs) =>
yargs
.command(AuthLoginCommand)
.command(AuthLogoutCommand)
.command(AuthListCommand)
.demandCommand(),
async handler() {},
})
export const AuthListCommand = cmd({
command: "list",
aliases: ["ls"],
describe: "list providers",
async handler() {
UI.empty()
prompts.intro("Credentials")
const results = await Auth.all().then((x) => Object.entries(x))
const database = await ModelsDev.get()
for (const [providerID, result] of results) {
const name = database[providerID]?.name || providerID
prompts.log.info(`${name} ${UI.Style.TEXT_DIM}(${result.type})`)
}
prompts.outro(`${results.length} credentials`)
},
})
export const AuthLoginCommand = cmd({
command: "login",
describe: "login to a provider",
async handler() {
UI.empty()
prompts.intro("Add credential")
const providers = await ModelsDev.get()
const priority: Record<string, number> = {
anthropic: 0,
openai: 1,
google: 2,
}
let provider = await prompts.select({
message: "Select provider",
maxItems: 8,
options: [
...pipe(
providers,
values(),
sortBy(
(x) => priority[x.id] ?? 99,
(x) => x.name ?? x.id,
),
map((x) => ({
label: x.name,
value: x.id,
hint: priority[x.id] === 0 ? "recommended" : undefined,
})),
),
{
value: "other",
label: "Other",
},
],
})
if (prompts.isCancel(provider)) throw new UI.CancelledError()
if (provider === "other") {
provider = await prompts.text({
message: "Enter provider id",
validate: (x) =>
x.match(/^[a-z-]+$/) ? undefined : "a-z and hyphens only",
})
if (prompts.isCancel(provider)) throw new UI.CancelledError()
provider = provider.replace(/^@ai-sdk\//, "")
if (prompts.isCancel(provider)) throw new UI.CancelledError()
prompts.log.warn(
`This only stores a credential for ${provider} - you will need configure it in opencode.json, check the docs for examples.`,
)
}
if (provider === "amazon-bedrock") {
prompts.log.info(
"Amazon bedrock can be configured with standard AWS environment variables like AWS_PROFILE or AWS_ACCESS_KEY_ID",
)
prompts.outro("Done")
return
}
if (provider === "anthropic") {
const method = await prompts.select({
message: "Login method",
options: [
{
label: "Claude Pro/Max",
value: "oauth",
},
{
label: "API Key",
value: "api",
},
],
})
if (prompts.isCancel(method)) throw new UI.CancelledError()
if (method === "oauth") {
// some weird bug where program exits without this
await new Promise((resolve) => setTimeout(resolve, 10))
const { url, verifier } = await AuthAnthropic.authorize()
prompts.note("Trying to open browser...")
try {
await open(url)
} catch (e) {
prompts.log.error(
"Failed to open browser perhaps you are running without a display or X server, please open the following URL in your browser:",
)
}
prompts.log.info(url)
const code = await prompts.text({
message: "Paste the authorization code here: ",
validate: (x) => (x.length > 0 ? undefined : "Required"),
})
if (prompts.isCancel(code)) throw new UI.CancelledError()
await AuthAnthropic.exchange(code, verifier)
.then(() => {
prompts.log.success("Login successful")
})
.catch(() => {
prompts.log.error("Invalid code")
})
prompts.outro("Done")
return
}
}
const key = await prompts.password({
message: "Enter your API key",
validate: (x) => (x.length > 0 ? undefined : "Required"),
})
if (prompts.isCancel(key)) throw new UI.CancelledError()
await Auth.set(provider, {
type: "api",
key,
})
prompts.outro("Done")
},
})
export const AuthLogoutCommand = cmd({
command: "logout",
describe: "logout from a configured provider",
async handler() {
UI.empty()
const credentials = await Auth.all().then((x) => Object.entries(x))
prompts.intro("Remove credential")
if (credentials.length === 0) {
prompts.log.error("No credentials found")
return
}
const database = await ModelsDev.get()
const providerID = await prompts.select({
message: "Select provider",
options: credentials.map(([key, value]) => ({
label:
(database[key]?.name || key) +
UI.Style.TEXT_DIM +
" (" +
value.type +
")",
value: key,
})),
})
if (prompts.isCancel(providerID)) throw new UI.CancelledError()
await Auth.remove(providerID)
prompts.outro("Logout successful")
},
})

View File

@@ -0,0 +1,5 @@
import type { CommandModule } from "yargs"
export function cmd<T, U>(input: CommandModule<T, U>) {
return input
}

View File

@@ -0,0 +1,18 @@
import { Server } from "../../server/server"
import fs from "fs/promises"
import path from "path"
import type { CommandModule } from "yargs"
export const GenerateCommand = {
command: "generate",
handler: async () => {
const specs = await Server.openapi()
const dir = "gen"
await fs.rmdir(dir, { recursive: true }).catch(() => {})
await fs.mkdir(dir, { recursive: true })
await Bun.write(
path.join(dir, "openapi.json"),
JSON.stringify(specs, null, 2),
)
},
} satisfies CommandModule

View File

@@ -0,0 +1,20 @@
import { AuthAnthropic } from "../../auth/anthropic"
import { UI } from "../ui"
// Example: https://claude.ai/oauth/authorize?code=true&client_id=9d1c250a-e61b-44d9-88ed-5944d1962f5e&response_type=code&redirect_uri=https%3A%2F%2Fconsole.anthropic.com%2Foauth%2Fcode%2Fcallback&scope=org%3Acreate_api_key+user%3Aprofile+user%3Ainference&code_challenge=MdFtFgFap23AWDSN0oa3-eaKjQRFE4CaEhXx8M9fHZg&code_challenge_method=S256&state=rKLtaDzm88GSwekyEqdi0wXX-YqIr13tSzYymSzpvfs
export const LoginAnthropicCommand = {
command: "anthropic",
describe: "Login to Anthropic",
handler: async () => {
const { url, verifier } = await AuthAnthropic.authorize()
UI.println("Login to Anthropic")
UI.println("Open the following URL in your browser:")
UI.println(url)
UI.println("")
const code = await UI.input("Paste the authorization code here: ")
await AuthAnthropic.exchange(code, verifier)
},
}

View File

@@ -0,0 +1,138 @@
import type { Argv } from "yargs"
import { App } from "../../app/app"
import { Bus } from "../../bus"
import { Provider } from "../../provider/provider"
import { Session } from "../../session"
import { Share } from "../../share/share"
import { Message } from "../../session/message"
import { UI } from "../ui"
import { cmd } from "./cmd"
import { Flag } from "../../flag/flag"
import { Config } from "../../config/config"
const TOOL: Record<string, [string, string]> = {
todowrite: ["Todo", UI.Style.TEXT_WARNING_BOLD],
todoread: ["Todo", UI.Style.TEXT_WARNING_BOLD],
bash: ["Bash", UI.Style.TEXT_DANGER_BOLD],
edit: ["Edit", UI.Style.TEXT_SUCCESS_BOLD],
glob: ["Glob", UI.Style.TEXT_INFO_BOLD],
grep: ["Grep", UI.Style.TEXT_INFO_BOLD],
list: ["List", UI.Style.TEXT_INFO_BOLD],
read: ["Read", UI.Style.TEXT_HIGHLIGHT_BOLD],
write: ["Write", UI.Style.TEXT_SUCCESS_BOLD],
}
export const RunCommand = cmd({
command: "run [message..]",
describe: "Run OpenCode with a message",
builder: (yargs: Argv) => {
return yargs
.positional("message", {
describe: "Message to send",
type: "string",
array: true,
default: [],
})
.option("session", {
describe: "Session ID to continue",
type: "string",
})
.option("share", {
type: "boolean",
describe: "Share the session",
})
},
handler: async (args) => {
const message = args.message.join(" ")
await App.provide(
{
cwd: process.cwd(),
},
async () => {
await Share.init()
const session = args.session
? await Session.get(args.session)
: await Session.create()
UI.empty()
UI.println(UI.logo())
UI.empty()
UI.println(UI.Style.TEXT_NORMAL_BOLD + "> ", message)
UI.empty()
const cfg = await Config.get()
if (cfg.autoshare || Flag.OPENCODE_AUTO_SHARE || args.share) {
await Session.share(session.id)
UI.println(
UI.Style.TEXT_INFO_BOLD +
"~ https://dev.opencode.ai/s/" +
session.id.slice(-8),
)
}
UI.empty()
const { providerID, modelID } = await Provider.defaultModel()
UI.println(
UI.Style.TEXT_NORMAL_BOLD + "@ ",
UI.Style.TEXT_NORMAL + `${providerID}/${modelID}`,
)
UI.empty()
function printEvent(color: string, type: string, title: string) {
UI.println(
color + `|`,
UI.Style.TEXT_NORMAL +
UI.Style.TEXT_DIM +
` ${type.padEnd(7, " ")}`,
"",
UI.Style.TEXT_NORMAL + title,
)
}
Bus.subscribe(Message.Event.PartUpdated, async (evt) => {
if (evt.properties.sessionID !== session.id) return
const part = evt.properties.part
const message = await Session.getMessage(
evt.properties.sessionID,
evt.properties.messageID,
)
if (
part.type === "tool-invocation" &&
part.toolInvocation.state === "result"
) {
const metadata =
message.metadata.tool[part.toolInvocation.toolCallId]
const [tool, color] = TOOL[part.toolInvocation.toolName] ?? [
part.toolInvocation.toolName,
UI.Style.TEXT_INFO_BOLD,
]
printEvent(color, tool, metadata.title)
}
if (part.type === "text") {
if (part.text.includes("\n")) {
UI.empty()
UI.println(part.text)
UI.empty()
return
}
printEvent(UI.Style.TEXT_NORMAL_BOLD, "Text", part.text)
}
})
await Session.chat({
sessionID: session.id,
providerID,
modelID,
parts: [
{
type: "text",
text: message,
},
],
})
UI.empty()
},
)
},
})

View File

@@ -0,0 +1,18 @@
import { App } from "../../app/app"
import { LSP } from "../../lsp"
import { cmd } from "./cmd"
export const ScrapCommand = cmd({
command: "scrap <file>",
builder: (yargs) =>
yargs.positional("file", { type: "string", demandOption: true }),
async handler(args) {
await App.provide(
{ cwd: process.cwd() },
async () => {
await LSP.touchFile(args.file, true)
console.log(await LSP.diagnostics())
},
)
},
})

View File

@@ -0,0 +1,44 @@
import type { Argv } from "yargs"
import { UI } from "../ui"
import * as prompts from "@clack/prompts"
import { Installation } from "../../installation"
export const UpgradeCommand = {
command: "upgrade [target]",
describe: "Upgrade opencode to the latest version or a specific version",
builder: (yargs: Argv) => {
return yargs.positional("target", {
describe: "Specific version to upgrade to (e.g., '0.1.48' or 'v0.1.48')",
type: "string",
})
},
handler: async (args: { target?: string }) => {
UI.empty()
UI.println(UI.logo(" "))
UI.empty()
prompts.intro("Upgrade")
const method = await Installation.method()
if (method === "unknown") {
prompts.log.error(
`opencode is installed to ${process.execPath} and seems to be managed by a package manager`,
)
prompts.outro("Done")
return
}
const target = args.target ?? (await Installation.latest())
prompts.log.info(`From ${Installation.VERSION}${target}`)
const spinner = prompts.spinner()
spinner.start("Upgrading...")
const err = await Installation.upgrade(method, target).catch((err) => err)
if (err) {
spinner.stop("Upgrade failed")
if (err instanceof Installation.UpgradeFailedError)
prompts.log.error(err.data.stderr)
else if (err instanceof Error) prompts.log.error(err.message)
prompts.outro("Done")
return
}
spinner.stop("Upgrade complete")
prompts.outro("Done")
},
}

View File

@@ -0,0 +1,74 @@
import { z } from "zod"
import { NamedError } from "../util/error"
export namespace UI {
const LOGO = [
[`█▀▀█ █▀▀█ █▀▀ █▀▀▄ `, `█▀▀ █▀▀█ █▀▀▄ █▀▀`],
[`█░░█ █░░█ █▀▀ █░░█ `, `█░░ █░░█ █░░█ █▀▀`],
[`▀▀▀▀ █▀▀▀ ▀▀▀ ▀ ▀ `, `▀▀▀ ▀▀▀▀ ▀▀▀ ▀▀▀`],
]
export const CancelledError = NamedError.create("UICancelledError", z.void())
export const Style = {
TEXT_HIGHLIGHT: "\x1b[96m",
TEXT_HIGHLIGHT_BOLD: "\x1b[96m\x1b[1m",
TEXT_DIM: "\x1b[90m",
TEXT_DIM_BOLD: "\x1b[90m\x1b[1m",
TEXT_NORMAL: "\x1b[0m",
TEXT_NORMAL_BOLD: "\x1b[1m",
TEXT_WARNING: "\x1b[93m",
TEXT_WARNING_BOLD: "\x1b[93m\x1b[1m",
TEXT_DANGER: "\x1b[91m",
TEXT_DANGER_BOLD: "\x1b[91m\x1b[1m",
TEXT_SUCCESS: "\x1b[92m",
TEXT_SUCCESS_BOLD: "\x1b[92m\x1b[1m",
TEXT_INFO: "\x1b[94m",
TEXT_INFO_BOLD: "\x1b[94m\x1b[1m",
}
export function println(...message: string[]) {
print(...message)
Bun.stderr.write("\n")
}
export function print(...message: string[]) {
blank = false
Bun.stderr.write(message.join(" "))
}
let blank = false
export function empty() {
if (blank) return
println("" + Style.TEXT_NORMAL)
blank = true
}
export function logo(pad?: string) {
const result = []
for (const row of LOGO) {
if (pad) result.push(pad)
result.push(Bun.color("gray", "ansi"))
result.push(row[0])
result.push("\x1b[0m")
result.push(row[1])
result.push("\n")
}
return result.join("").trimEnd()
}
export async function input(prompt: string): Promise<string> {
const readline = require("readline")
const rl = readline.createInterface({
input: process.stdin,
output: process.stdout,
})
return new Promise((resolve) => {
rl.question(prompt, (answer: string) => {
rl.close()
resolve(answer.trim())
})
})
}
}

View File

@@ -1,42 +1,30 @@
import path from "path"
import { Log } from "../util/log"
import path from "path"
import { z } from "zod"
import { App } from "../app/app"
import { Provider } from "../provider/provider"
import { Filesystem } from "../util/filesystem"
import { ModelsDev } from "../provider/models"
import { mergeDeep } from "remeda"
import { Global } from "../global"
import fs from "fs/promises"
import { lazy } from "../util/lazy"
export namespace Config {
const log = Log.create({ service: "config" })
export const state = App.state("config", async (app) => {
const result = await load(app.path.root)
return result
})
export const Info = z
.object({
provider: z.lazy(() => Provider.Info.array().optional()),
tool: z
.object({
provider: z.record(z.string(), z.string().array()).optional(),
})
.optional(),
})
.strict()
export type Info = z.output<typeof Info>
export function get() {
return state()
}
async function load(directory: string) {
let result: Info = {}
let result = await global()
for (const file of ["opencode.jsonc", "opencode.json"]) {
const resolved = path.join(directory, file)
log.info("searching", { path: resolved })
const [resolved] = await Filesystem.findUp(
file,
app.path.cwd,
app.path.root,
)
if (!resolved) continue
try {
result = await import(path.join(directory, file)).then((mod) =>
Info.parse(mod.default),
result = mergeDeep(
result,
await import(resolved).then((mod) => Info.parse(mod.default)),
)
log.info("found", { path: resolved })
break
@@ -52,5 +40,129 @@ export namespace Config {
}
log.info("loaded", result)
return result
})
export const McpLocal = z
.object({
type: z.literal("local"),
command: z.string().array(),
environment: z.record(z.string(), z.string()).optional(),
})
.openapi({
ref: "Config.McpLocal",
})
export const McpRemote = z
.object({
type: z.literal("remote"),
url: z.string(),
})
.openapi({
ref: "Config.McpRemote",
})
export const Mcp = z.discriminatedUnion("type", [McpLocal, McpRemote])
export type Mcp = z.infer<typeof Mcp>
export const Keybinds = z
.object({
leader: z.string().optional(),
help: z.string().optional(),
editor_open: z.string().optional(),
session_new: z.string().optional(),
session_list: z.string().optional(),
session_share: z.string().optional(),
session_interrupt: z.string().optional(),
session_compact: z.string().optional(),
tool_details: z.string().optional(),
model_list: z.string().optional(),
theme_list: z.string().optional(),
project_init: z.string().optional(),
input_clear: z.string().optional(),
input_paste: z.string().optional(),
input_submit: z.string().optional(),
input_newline: z.string().optional(),
history_previous: z.string().optional(),
history_next: z.string().optional(),
messages_page_up: z.string().optional(),
messages_page_down: z.string().optional(),
messages_half_page_up: z.string().optional(),
messages_half_page_down: z.string().optional(),
messages_previous: z.string().optional(),
messages_next: z.string().optional(),
messages_first: z.string().optional(),
messages_last: z.string().optional(),
app_exit: z.string().optional(),
})
.openapi({
ref: "Config.Keybinds",
})
export const Info = z
.object({
$schema: z.string().optional(),
theme: z.string().optional(),
keybinds: Keybinds.optional(),
autoshare: z
.boolean()
.optional()
.describe("Share newly created sessions automatically"),
autoupdate: z
.boolean()
.optional()
.describe("Automatically update to the latest version"),
disabled_providers: z
.array(z.string())
.optional()
.describe("Disable providers that are loaded automatically"),
model: z
.string()
.describe(
"Model to use in the format of provider/model, eg anthropic/claude-2",
)
.optional(),
provider: z
.record(
ModelsDev.Provider.partial().extend({
models: z.record(ModelsDev.Model.partial()),
options: z.record(z.any()).optional(),
}),
)
.optional(),
mcp: z.record(z.string(), Mcp).optional(),
})
.openapi({
ref: "Config.Info",
})
export type Info = z.output<typeof Info>
export const global = lazy(async () => {
let result = await Bun.file(path.join(Global.Path.config, "config.json"))
.json()
.then((mod) => Info.parse(mod))
.catch(() => ({}) as Info)
await import(path.join(Global.Path.config, "config"), {
with: {
type: "toml",
},
})
.then(async (mod) => {
const { provider, model, ...rest } = mod.default
if (provider && model) result.model = `${provider}/${model}`
result["$schema"] = "https://opencode.ai/config.json"
result = mergeDeep(result, rest)
await Bun.write(
path.join(Global.Path.config, "config.json"),
JSON.stringify(result, null, 2),
)
await fs.unlink(path.join(Global.Path.config, "config"))
})
.catch(() => {})
return Info.parse(result)
})
export function get() {
return state()
}
}

138
packages/opencode/src/external/fzf.ts vendored Normal file
View File

@@ -0,0 +1,138 @@
import path from "path"
import { Global } from "../global"
import fs from "fs/promises"
import { z } from "zod"
import { NamedError } from "../util/error"
import { lazy } from "../util/lazy"
import { Log } from "../util/log"
import { $ } from "bun"
export namespace Fzf {
const log = Log.create({ service: "fzf" })
const VERSION = "0.62.0"
const PLATFORM = {
darwin: { extension: "tar.gz" },
linux: { extension: "tar.gz" },
win32: { extension: "zip" },
} as const
export const ExtractionFailedError = NamedError.create(
"FzfExtractionFailedError",
z.object({
filepath: z.string(),
stderr: z.string(),
}),
)
export const UnsupportedPlatformError = NamedError.create(
"FzfUnsupportedPlatformError",
z.object({
platform: z.string(),
}),
)
export const DownloadFailedError = NamedError.create(
"FzfDownloadFailedError",
z.object({
url: z.string(),
status: z.number(),
}),
)
const state = lazy(async () => {
let filepath = Bun.which("fzf")
if (filepath) {
log.info("found", { filepath })
return { filepath }
}
filepath = path.join(
Global.Path.bin,
"fzf" + (process.platform === "win32" ? ".exe" : ""),
)
const file = Bun.file(filepath)
if (!(await file.exists())) {
const archMap = { x64: "amd64", arm64: "arm64" } as const
const arch = archMap[process.arch as keyof typeof archMap] ?? "amd64"
const config = PLATFORM[process.platform as keyof typeof PLATFORM]
if (!config)
throw new UnsupportedPlatformError({ platform: process.platform })
const version = VERSION
const platformName =
process.platform === "win32" ? "windows" : process.platform
const filename = `fzf-${version}-${platformName}_${arch}.${config.extension}`
const url = `https://github.com/junegunn/fzf/releases/download/v${version}/${filename}`
const response = await fetch(url)
if (!response.ok)
throw new DownloadFailedError({ url, status: response.status })
const buffer = await response.arrayBuffer()
const archivePath = path.join(Global.Path.bin, filename)
await Bun.write(archivePath, buffer)
if (config.extension === "tar.gz") {
const proc = Bun.spawn(["tar", "-xzf", archivePath, "fzf"], {
cwd: Global.Path.bin,
stderr: "pipe",
stdout: "pipe",
})
await proc.exited
if (proc.exitCode !== 0)
throw new ExtractionFailedError({
filepath,
stderr: await Bun.readableStreamToText(proc.stderr),
})
}
if (config.extension === "zip") {
const proc = Bun.spawn(
["unzip", "-j", archivePath, "fzf.exe", "-d", Global.Path.bin],
{
cwd: Global.Path.bin,
stderr: "pipe",
stdout: "ignore",
},
)
await proc.exited
if (proc.exitCode !== 0)
throw new ExtractionFailedError({
filepath: archivePath,
stderr: await Bun.readableStreamToText(proc.stderr),
})
}
await fs.unlink(archivePath)
if (process.platform !== "win32") await fs.chmod(filepath, 0o755)
}
return {
filepath,
}
})
export async function filepath() {
const { filepath } = await state()
return filepath
}
export async function search(input: {
cwd: string
query: string
limit?: number
}) {
const results = await $`${await filepath()} --filter=${input.query}`
.quiet()
.throws(false)
.cwd(input.cwd)
.text()
const split = results
.trim()
.split("\n")
.filter((line) => line.length > 0)
log.info("results", {
count: split.length,
})
return split
}
}

View File

@@ -0,0 +1,129 @@
import path from "path"
import { Global } from "../global"
import fs from "fs/promises"
import { z } from "zod"
import { NamedError } from "../util/error"
import { lazy } from "../util/lazy"
import { $ } from "bun"
import { Fzf } from "./fzf"
export namespace Ripgrep {
const PLATFORM = {
darwin: { platform: "apple-darwin", extension: "tar.gz" },
linux: { platform: "unknown-linux-musl", extension: "tar.gz" },
win32: { platform: "pc-windows-msvc", extension: "zip" },
} as const
export const ExtractionFailedError = NamedError.create(
"RipgrepExtractionFailedError",
z.object({
filepath: z.string(),
stderr: z.string(),
}),
)
export const UnsupportedPlatformError = NamedError.create(
"RipgrepUnsupportedPlatformError",
z.object({
platform: z.string(),
}),
)
export const DownloadFailedError = NamedError.create(
"RipgrepDownloadFailedError",
z.object({
url: z.string(),
status: z.number(),
}),
)
const state = lazy(async () => {
let filepath = Bun.which("rg")
if (filepath) return { filepath }
filepath = path.join(
Global.Path.bin,
"rg" + (process.platform === "win32" ? ".exe" : ""),
)
const file = Bun.file(filepath)
if (!(await file.exists())) {
const archMap = { x64: "x86_64", arm64: "aarch64" } as const
const arch = archMap[process.arch as keyof typeof archMap] ?? process.arch
const config = PLATFORM[process.platform as keyof typeof PLATFORM]
if (!config)
throw new UnsupportedPlatformError({ platform: process.platform })
const version = "14.1.1"
const filename = `ripgrep-${version}-${arch}-${config.platform}.${config.extension}`
const url = `https://github.com/BurntSushi/ripgrep/releases/download/${version}/${filename}`
const response = await fetch(url)
if (!response.ok)
throw new DownloadFailedError({ url, status: response.status })
const buffer = await response.arrayBuffer()
const archivePath = path.join(Global.Path.bin, filename)
await Bun.write(archivePath, buffer)
if (config.extension === "tar.gz") {
const args = ["tar", "-xzf", archivePath, "--strip-components=1"]
if (process.platform === "darwin") args.push("--include=*/rg")
if (process.platform === "linux") args.push("--wildcards", "*/rg")
const proc = Bun.spawn(args, {
cwd: Global.Path.bin,
stderr: "pipe",
stdout: "pipe",
})
await proc.exited
if (proc.exitCode !== 0)
throw new ExtractionFailedError({
filepath,
stderr: await Bun.readableStreamToText(proc.stderr),
})
}
if (config.extension === "zip") {
const proc = Bun.spawn(
["unzip", "-j", archivePath, "*/rg.exe", "-d", Global.Path.bin],
{
cwd: Global.Path.bin,
stderr: "pipe",
stdout: "ignore",
},
)
await proc.exited
if (proc.exitCode !== 0)
throw new ExtractionFailedError({
filepath: archivePath,
stderr: await Bun.readableStreamToText(proc.stderr),
})
}
await fs.unlink(archivePath)
if (process.platform !== "win32") await fs.chmod(filepath, 0o755)
}
return {
filepath,
}
})
export async function filepath() {
const { filepath } = await state()
return filepath
}
export async function files(input: {
cwd: string
query?: string
limit?: number
}) {
const commands = [`${await filepath()} --files --hidden --glob='!.git/*'`]
if (input.query)
commands.push(`${await Fzf.filepath()} --filter=${input.query}`)
if (input.limit) commands.push(`head -n ${input.limit}`)
const joined = commands.join(" | ")
const result = await $`${{ raw: joined }}`.cwd(input.cwd).text()
return result.split("\n").filter(Boolean)
}
}

View File

@@ -0,0 +1,8 @@
export namespace Flag {
export const OPENCODE_AUTO_SHARE = truthy("OPENCODE_AUTO_SHARE")
function truthy(key: string) {
const value = process.env[key]?.toLowerCase()
return value === "true" || value === "1"
}
}

View File

@@ -1,24 +1,29 @@
import envpaths from "env-paths"
import fs from "fs/promises"
const paths = envpaths("opencode", {
suffix: "",
})
import { xdgData, xdgCache, xdgConfig, xdgState } from "xdg-basedir"
import path from "path"
await Promise.all([
fs.mkdir(paths.config, { recursive: true }),
fs.mkdir(paths.cache, { recursive: true }),
])
const app = "opencode"
const data = path.join(xdgData!, app)
const cache = path.join(xdgCache!, app)
const config = path.join(xdgConfig!, app)
const state = path.join(xdgState!, app)
export namespace Global {
export function config() {
return paths.config
}
export function cache() {
return paths.cache
}
export function data() {
return paths.data
}
export const Path = {
data,
bin: path.join(data, "bin"),
providers: path.join(config, "providers"),
cache,
config,
state,
} as const
}
await Promise.all([
fs.mkdir(Global.Path.data, { recursive: true }),
fs.mkdir(Global.Path.config, { recursive: true }),
fs.mkdir(Global.Path.cache, { recursive: true }),
fs.mkdir(Global.Path.providers, { recursive: true }),
fs.mkdir(Global.Path.state, { recursive: true }),
])

View File

@@ -3,118 +3,137 @@ import { App } from "./app/app"
import { Server } from "./server/server"
import fs from "fs/promises"
import path from "path"
import { Bus } from "./bus"
import { Session } from "./session/session"
import cac from "cac"
import { Share } from "./share/share"
import { Message } from "./session/message"
import { Global } from "./global"
import yargs from "yargs"
import { hideBin } from "yargs/helpers"
import { RunCommand } from "./cli/cmd/run"
import { GenerateCommand } from "./cli/cmd/generate"
import { ScrapCommand } from "./cli/cmd/scrap"
import { Log } from "./util/log"
import { AuthCommand, AuthLoginCommand } from "./cli/cmd/auth"
import { UpgradeCommand } from "./cli/cmd/upgrade"
import { Provider } from "./provider/provider"
import { UI } from "./cli/ui"
import { Installation } from "./installation"
import { Bus } from "./bus"
import { Config } from "./config/config"
declare global {
const OPENCODE_VERSION: string
}
const cli = cac("opencode")
const version = typeof OPENCODE_VERSION === "string" ? OPENCODE_VERSION : "dev"
cli.command("", "Start the opencode in interactive mode").action(async () => {
await App.provide({ cwd: process.cwd(), version }, async () => {
await Share.init()
const server = Server.listen()
let cmd = ["go", "run", "./main.go"]
let cwd = new URL("../../tui", import.meta.url).pathname
if (Bun.embeddedFiles.length > 0) {
const blob = Bun.embeddedFiles[0] as File
const binary = path.join(Global.cache(), "tui", blob.name)
const file = Bun.file(binary)
if (!(await file.exists())) {
console.log("installing tui binary...")
await Bun.write(file, blob, { mode: 0o755 })
await fs.chmod(binary, 0o755)
}
cwd = process.cwd()
cmd = [binary]
}
const proc = Bun.spawn({
cmd,
cwd,
stdout: "inherit",
stderr: "inherit",
stdin: "inherit",
onExit: () => {
server.stop()
},
})
await proc.exited
await server.stop()
const cli = yargs(hideBin(process.argv))
.scriptName("opencode")
.version(Installation.VERSION)
.option("print-logs", {
describe: "Print logs to stderr",
type: "boolean",
})
})
.middleware(async () => {
await Log.init({ print: process.argv.includes("--print-logs") })
Log.Default.info("opencode", {
version: Installation.VERSION,
args: process.argv.slice(2),
})
})
.usage("\n" + UI.logo())
.command({
command: "$0 [project]",
describe: "Start opencode TUI",
builder: (yargs) =>
yargs.positional("project", {
type: "string",
describe: "path to start opencode in",
}),
handler: async (args) => {
while (true) {
const cwd = args.project ? path.resolve(args.project) : process.cwd()
process.chdir(cwd)
const result = await App.provide({ cwd }, async (app) => {
const providers = await Provider.list()
if (Object.keys(providers).length === 0) {
return "needs_provider"
}
cli.command("generate", "Generate OpenAPI and event specs").action(async () => {
const specs = await Server.openapi()
const dir = "gen"
await fs.rmdir(dir, { recursive: true }).catch(() => {})
await fs.mkdir(dir, { recursive: true })
await Bun.write(
path.join(dir, "openapi.json"),
JSON.stringify(specs, null, 2),
)
})
await Share.init()
const server = Server.listen()
cli
.command("run [...message]", "Run a chat message")
.option("--session <id>", "Session ID")
.action(async (message: string[], options) => {
await App.provide({ cwd: process.cwd(), version }, async () => {
await Share.init()
const session = options.session
? await Session.get(options.session)
: await Session.create()
console.log("Session:", session.id)
let cmd = ["go", "run", "./main.go"]
let cwd = new URL("../../tui/cmd/opencode", import.meta.url).pathname
if (Bun.embeddedFiles.length > 0) {
const blob = Bun.embeddedFiles[0] as File
const binary = path.join(Global.Path.cache, "tui", blob.name)
const file = Bun.file(binary)
if (!(await file.exists())) {
await Bun.write(file, blob, { mode: 0o755 })
await fs.chmod(binary, 0o755)
}
cwd = process.cwd()
cmd = [binary]
}
const proc = Bun.spawn({
cmd: [...cmd, ...process.argv.slice(2)],
cwd,
stdout: "inherit",
stderr: "inherit",
stdin: "inherit",
env: {
...process.env,
OPENCODE_SERVER: server.url.toString(),
OPENCODE_APP_INFO: JSON.stringify(app),
},
onExit: () => {
server.stop()
},
})
Bus.subscribe(Message.Event.Updated, async () => {
console.log("Thinking...")
})
;(async () => {
if (Installation.VERSION === "dev") return
if (Installation.isSnapshot()) return
const config = await Config.global()
if (config.autoupdate === false) return
const latest = await Installation.latest()
if (Installation.VERSION === latest) return
const method = await Installation.method()
if (method === "unknown") return
await Installation.upgrade(method, latest)
.then(() => {
Bus.publish(Installation.Event.Updated, { version: latest })
})
.catch(() => {})
})()
const unsub = Bus.subscribe(Session.Event.Updated, async (message) => {
if (message.properties.info.share?.url)
console.log("Share:", message.properties.info.share.url)
unsub()
})
await proc.exited
server.stop()
const [provider] = await Provider.active().then((val) =>
val.values().toArray(),
)
if (!provider) throw new Error("no providers found")
const model = provider.models[0]
if (!model) throw new Error("no models found")
console.log("using", provider.id, model.id)
const result = await Session.chat({
sessionID: session.id,
providerID: provider.id,
modelID: model.id,
parts: [
{
type: "text",
text: message.join(" "),
},
],
})
for (const part of result.parts) {
if (part.type === "text") {
console.log("opencode:", part.text)
return "done"
})
if (result === "done") break
if (result === "needs_provider") {
UI.empty()
UI.println(UI.logo(" "))
UI.empty()
await AuthLoginCommand.handler(args)
}
}
console.log({
cost: result.metadata.assistant?.cost,
tokens: result.metadata.assistant?.tokens,
})
})
},
})
.command(RunCommand)
.command(GenerateCommand)
.command(ScrapCommand)
.command(AuthCommand)
.command(UpgradeCommand)
.fail((msg) => {
if (
msg.startsWith("Unknown argument") ||
msg.startsWith("Not enough non-option arguments")
) {
cli.showHelp("log")
}
})
.strict()
cli.version(typeof OPENCODE_VERSION === "string" ? OPENCODE_VERSION : "dev")
cli.help()
cli.parse()
try {
await cli.parse()
} catch (e) {
Log.Default.error(e, {
stack: e instanceof Error ? e.stack : undefined,
})
}

View File

@@ -0,0 +1,122 @@
import path from "path"
import { $ } from "bun"
import { z } from "zod"
import { NamedError } from "../util/error"
import { Bus } from "../bus"
declare global {
const OPENCODE_VERSION: string
}
export namespace Installation {
export type Method = Awaited<ReturnType<typeof method>>
export const Event = {
Updated: Bus.event(
"installation.updated",
z.object({
version: z.string(),
}),
),
}
export const Info = z
.object({
version: z.string(),
latest: z.string(),
})
.openapi({
ref: "InstallationInfo",
})
export type Info = z.infer<typeof Info>
export async function info() {
return {
version: VERSION,
latest: await latest(),
}
}
export function isSnapshot() {
return VERSION.startsWith("0.0.0")
}
export async function method() {
if (process.execPath.includes(path.join(".opencode", "bin"))) return "curl"
const exec = process.execPath.toLowerCase()
const checks = [
{
name: "npm" as const,
command: () => $`npm list -g --depth=0`.throws(false).text(),
},
{
name: "yarn" as const,
command: () => $`yarn global list`.throws(false).text(),
},
{
name: "pnpm" as const,
command: () => $`pnpm list -g --depth=0`.throws(false).text(),
},
{
name: "bun" as const,
command: () => $`bun pm ls -g`.throws(false).text(),
},
]
checks.sort((a, b) => {
const aMatches = exec.includes(a.name)
const bMatches = exec.includes(b.name)
if (aMatches && !bMatches) return -1
if (!aMatches && bMatches) return 1
return 0
})
for (const check of checks) {
const output = await check.command()
if (output.includes("opencode-ai")) {
return check.name
}
}
return "unknown"
}
export const UpgradeFailedError = NamedError.create(
"UpgradeFailedError",
z.object({
stderr: z.string(),
}),
)
export async function upgrade(method: Method, target: string) {
const cmd = (() => {
switch (method) {
case "curl":
return $`curl -fsSL https://opencode.ai/install | bash`
case "npm":
return $`npm install -g opencode-ai@${target}`
case "pnpm":
return $`pnpm install -g opencode-ai@${target}`
case "bun":
return $`bun install -g opencode-ai@${target}`
default:
throw new Error(`Unknown method: ${method}`)
}
})()
const result = await cmd.quiet().throws(false)
if (result.exitCode !== 0)
throw new UpgradeFailedError({
stderr: result.stderr.toString("utf8"),
})
}
export const VERSION =
typeof OPENCODE_VERSION === "string" ? OPENCODE_VERSION : "dev"
export async function latest() {
return fetch("https://api.github.com/repos/sst/opencode/releases/latest")
.then((res) => res.json())
.then((data) => data.tag_name.slice(1) as string)
}
}

View File

@@ -1,4 +1,3 @@
import { spawn } from "child_process"
import path from "path"
import {
createMessageConnection,
@@ -11,14 +10,23 @@ import { Log } from "../util/log"
import { LANGUAGE_EXTENSIONS } from "./language"
import { Bus } from "../bus"
import z from "zod"
import type { LSPServer } from "./server"
import { NamedError } from "../util/error"
export namespace LSPClient {
const log = Log.create({ service: "lsp.client" })
export type Info = Awaited<ReturnType<typeof create>>
export type Info = NonNullable<Awaited<ReturnType<typeof create>>>
export type Diagnostic = VSCodeDiagnostic
export const InitializeError = NamedError.create(
"LSPInitializeError",
z.object({
serverID: z.string(),
}),
)
export const Event = {
Diagnostics: Bus.event(
"lsp.client.diagnostics",
@@ -29,19 +37,13 @@ export namespace LSPClient {
),
}
export async function create(input: { cmd: string[]; serverID: string }) {
log.info("starting client", input)
export async function create(serverID: string, server: LSPServer.Handle) {
const app = App.info()
const [command, ...args] = input.cmd
const server = spawn(command, args, {
stdio: ["pipe", "pipe", "pipe"],
cwd: app.path.cwd,
})
log.info("starting client", { id: serverID })
const connection = createMessageConnection(
new StreamMessageReader(server.stdout),
new StreamMessageWriter(server.stdin),
new StreamMessageReader(server.process.stdout),
new StreamMessageWriter(server.process.stdin),
)
const diagnostics = new Map<string, Diagnostic[]>()
@@ -50,91 +52,71 @@ export namespace LSPClient {
log.info("textDocument/publishDiagnostics", {
path,
})
const exists = diagnostics.has(path)
diagnostics.set(path, params.diagnostics)
// servers seem to send one blank publishDiagnostics event before the first real one
if (!exists && !params.diagnostics.length) return
Bus.publish(Event.Diagnostics, { path, serverID: input.serverID })
Bus.publish(Event.Diagnostics, { path, serverID })
})
connection.onRequest("workspace/configuration", async () => {
return [{}]
})
connection.listen()
await connection.sendRequest("initialize", {
processId: server.pid,
initializationOptions: {
log.info("sending initialize", { id: serverID })
await Promise.race([
connection.sendRequest("initialize", {
processId: server.process.pid,
workspaceFolders: [
{
name: "workspace",
uri: "file://" + app.path.cwd,
},
],
tsserver: {
path: require.resolve("typescript/lib/tsserver.js"),
initializationOptions: {
...server.initialization,
},
},
capabilities: {
workspace: {
configuration: true,
didChangeConfiguration: {
dynamicRegistration: true,
capabilities: {
workspace: {
configuration: true,
},
didChangeWatchedFiles: {
dynamicRegistration: true,
relativePatternSupport: true,
},
},
textDocument: {
synchronization: {
dynamicRegistration: true,
didSave: true,
},
completion: {
completionItem: {},
},
codeLens: {
dynamicRegistration: true,
},
documentSymbol: {},
codeAction: {
codeActionLiteralSupport: {
codeActionKind: {
valueSet: [],
},
textDocument: {
synchronization: {
didOpen: true,
didChange: true,
},
publishDiagnostics: {
versionSupport: true,
},
},
publishDiagnostics: {
versionSupport: true,
},
semanticTokens: {
requests: {
range: {},
full: {},
},
tokenTypes: [],
tokenModifiers: [],
formats: [],
},
},
window: {},
},
})
}),
new Promise((_, reject) => {
setTimeout(() => {
reject(new InitializeError({ serverID }))
}, 5_000)
}),
])
await connection.sendNotification("initialized", {})
log.info("initialized")
const files = new Set<string>()
const files: {
[path: string]: number
} = {}
const result = {
get clientID() {
return input.serverID
get serverID() {
return serverID
},
get connection() {
return connection
},
notify: {
async open(input: { path: string }) {
input.path = path.isAbsolute(input.path)
? input.path
: path.resolve(app.path.cwd, input.path)
const file = Bun.file(input.path)
const text = await file.text()
const opened = files.has(input.path)
if (!opened) {
const version = files[input.path]
if (version === undefined) {
log.info("textDocument/didOpen", input)
diagnostics.delete(input.path)
const extension = path.extname(input.path)
@@ -143,11 +125,11 @@ export namespace LSPClient {
textDocument: {
uri: `file://` + input.path,
languageId,
version: Date.now(),
version: 0,
text,
},
})
files.add(input.path)
files[input.path] = 0
return
}
@@ -156,7 +138,7 @@ export namespace LSPClient {
await connection.sendNotification("textDocument/didChange", {
textDocument: {
uri: `file://` + input.path,
version: Date.now(),
version: ++files[input.path],
},
contentChanges: [
{
@@ -170,6 +152,9 @@ export namespace LSPClient {
return diagnostics
},
async waitForDiagnostics(input: { path: string }) {
input.path = path.isAbsolute(input.path)
? input.path
: path.resolve(app.path.cwd, input.path)
log.info("waiting for diagnostics", input)
let unsub: () => void
let timeout: NodeJS.Timeout
@@ -178,7 +163,7 @@ export namespace LSPClient {
unsub = Bus.subscribe(Event.Diagnostics, (event) => {
if (
event.properties.path === input.path &&
event.properties.serverID === result.clientID
event.properties.serverID === result.serverID
) {
log.info("got diagnostics", input)
clearTimeout(timeout)
@@ -200,6 +185,7 @@ export namespace LSPClient {
log.info("shutting down")
connection.end()
connection.dispose()
server.process.kill("SIGKILL")
},
}

View File

@@ -2,6 +2,7 @@ import { App } from "../app/app"
import { Log } from "../util/log"
import { LSPClient } from "./client"
import path from "path"
import { LSPServer } from "./server"
export namespace LSP {
const log = Log.create({ service: "lsp" })
@@ -11,9 +12,10 @@ export namespace LSP {
async () => {
log.info("initializing")
const clients = new Map<string, LSPClient.Info>()
const skip = new Set<string>()
return {
clients,
skip,
}
},
async (state) => {
@@ -23,24 +25,35 @@ export namespace LSP {
},
)
export async function file(input: string) {
export async function touchFile(input: string, waitForDiagnostics?: boolean) {
const extension = path.parse(input).ext
const s = await state()
const matches = AUTO.filter((x) => x.extensions.includes(extension))
const matches = LSPServer.All.filter((x) =>
x.extensions.includes(extension),
)
for (const match of matches) {
if (s.skip.has(match.id)) continue
const existing = s.clients.get(match.id)
if (existing) continue
const client = await LSPClient.create({
cmd: match.command,
serverID: match.id,
})
const handle = await match.spawn(App.info())
if (!handle) {
s.skip.add(match.id)
continue
}
const client = await LSPClient.create(match.id, handle).catch(() => {})
if (!client) {
s.skip.add(match.id)
continue
}
s.clients.set(match.id, client)
}
await run(async (client) => {
const wait = client.waitForDiagnostics({ path: input })
await client.notify.open({ path: input })
return wait
})
if (waitForDiagnostics) {
await run(async (client) => {
const wait = client.waitForDiagnostics({ path: input })
await client.notify.open({ path: input })
return wait
})
}
}
export async function diagnostics() {
@@ -81,37 +94,6 @@ export namespace LSP {
return Promise.all(tasks)
}
const AUTO: {
id: string
command: string[]
extensions: string[]
install?: () => Promise<void>
}[] = [
{
id: "typescript",
command: ["bun", "x", "typescript-language-server", "--stdio"],
extensions: [
".ts",
".tsx",
".js",
".jsx",
".mjs",
".cjs",
".mts",
".cts",
".mtsx",
".ctsx",
],
},
/*
{
id: "golang",
command: ["gopls"],
extensions: [".go"],
},
*/
]
export namespace Diagnostic {
export function pretty(diagnostic: LSPClient.Diagnostic) {
const severityMap = {

View File

@@ -0,0 +1,93 @@
import { spawn, type ChildProcessWithoutNullStreams } from "child_process"
import type { App } from "../app/app"
import path from "path"
import { Global } from "../global"
import { Log } from "../util/log"
import { BunProc } from "../bun"
export namespace LSPServer {
const log = Log.create({ service: "lsp.server" })
export interface Handle {
process: ChildProcessWithoutNullStreams
initialization?: Record<string, any>
}
export interface Info {
id: string
extensions: string[]
spawn(app: App.Info): Promise<Handle | undefined>
}
export const All: Info[] = [
{
id: "typescript",
extensions: [
".ts",
".tsx",
".js",
".jsx",
".mjs",
".cjs",
".mts",
".cts",
],
async spawn(app) {
const tsserver = await Bun.resolve(
"typescript/lib/tsserver.js",
app.path.cwd,
).catch(() => {})
if (!tsserver) return
const proc = spawn(
BunProc.which(),
["x", "typescript-language-server", "--stdio"],
{
env: {
...process.env,
BUN_BE_BUN: "1",
},
},
)
return {
process: proc,
initialization: {
tsserver: {
path: tsserver,
},
},
}
},
},
{
id: "golang",
extensions: [".go"],
async spawn() {
let bin = Bun.which("gopls", {
PATH: process.env["PATH"] + ":" + Global.Path.bin,
})
if (!bin) {
log.info("installing gopls")
const proc = Bun.spawn({
cmd: ["go", "install", "golang.org/x/tools/gopls@latest"],
env: { ...process.env, GOBIN: Global.Path.bin },
})
const exit = await proc.exited
if (exit !== 0) {
log.error("Failed to install gopls")
return
}
bin = path.join(
Global.Path.bin,
"gopls" + (process.platform === "win32" ? ".exe" : ""),
)
log.info(`installed gopls`, {
bin,
})
}
return {
process: spawn(bin!),
}
},
},
]
}

View File

@@ -0,0 +1,63 @@
import { experimental_createMCPClient, type Tool } from "ai"
import { Experimental_StdioMCPTransport } from "ai/mcp-stdio"
import { App } from "../app/app"
import { Config } from "../config/config"
export namespace MCP {
const state = App.state(
"mcp",
async () => {
const cfg = await Config.get()
const clients: {
[name: string]: Awaited<ReturnType<typeof experimental_createMCPClient>>
} = {}
for (const [key, mcp] of Object.entries(cfg.mcp ?? {})) {
if (mcp.type === "remote") {
clients[key] = await experimental_createMCPClient({
name: key,
transport: {
type: "sse",
url: mcp.url,
},
})
}
if (mcp.type === "local") {
const [cmd, ...args] = mcp.command
clients[key] = await experimental_createMCPClient({
name: key,
transport: new Experimental_StdioMCPTransport({
stderr: "ignore",
command: cmd,
args,
env: mcp.environment,
}),
})
}
}
return {
clients,
}
},
async (state) => {
for (const client of Object.values(state.clients)) {
client.close()
}
},
)
export async function clients() {
return state().then((state) => state.clients)
}
export async function tools() {
const result: Record<string, Tool> = {}
for (const [clientName, client] of Object.entries(await clients())) {
for (const [toolName, tool] of Object.entries(await client.tools())) {
result[clientName + "_" + toolName] = tool
}
}
return result
}
}

View File

@@ -1,62 +0,0 @@
import type { Provider } from "./provider"
export const PROVIDER_DATABASE: Provider.Info[] = [
{
id: "anthropic",
name: "Anthropic",
models: [
{
id: "claude-sonnet-4-20250514",
name: "Claude Sonnet 4",
cost: {
input: 3.0 / 1_000_000,
output: 15.0 / 1_000_000,
inputCached: 3.75 / 1_000_000,
outputCached: 0.3 / 1_000_000,
},
contextWindow: 200_000,
maxOutputTokens: 50_000,
attachment: true,
},
],
},
{
id: "openai",
name: "OpenAI",
models: [
{
id: "codex-mini-latest",
name: "Codex Mini",
cost: {
input: 1.5 / 1_000_000,
inputCached: 0.375 / 1_000_000,
output: 6.0 / 1_000_000,
outputCached: 0.0 / 1_000_000,
},
contextWindow: 200_000,
maxOutputTokens: 100_000,
attachment: true,
reasoning: true,
},
],
},
{
id: "google",
name: "Google",
models: [
{
id: "gemini-2.5-pro-preview-03-25",
name: "Gemini 2.5 Pro",
cost: {
input: 1.25 / 1_000_000,
inputCached: 0 / 1_000_000,
output: 10 / 1_000_000,
outputCached: 0 / 1_000_000,
},
contextWindow: 1_000_000,
maxOutputTokens: 50_000,
attachment: true,
},
],
},
]

View File

@@ -0,0 +1,67 @@
import { Global } from "../global"
import { Log } from "../util/log"
import path from "path"
import { z } from "zod"
export namespace ModelsDev {
const log = Log.create({ service: "models.dev" })
const filepath = path.join(Global.Path.cache, "models.json")
export const Model = z
.object({
name: z.string(),
attachment: z.boolean(),
reasoning: z.boolean(),
temperature: z.boolean(),
cost: z.object({
input: z.number(),
output: z.number(),
cache_read: z.number().optional(),
cache_write: z.number().optional(),
}),
limit: z.object({
context: z.number(),
output: z.number(),
}),
id: z.string(),
})
.openapi({
ref: "Model.Info",
})
export type Model = z.infer<typeof Model>
export const Provider = z
.object({
api: z.string().optional(),
name: z.string(),
env: z.array(z.string()),
id: z.string(),
npm: z.string().optional(),
models: z.record(Model),
})
.openapi({
ref: "Provider.Info",
})
export type Provider = z.infer<typeof Provider>
export async function get() {
const file = Bun.file(filepath)
const result = await file.json().catch(() => {})
if (result) {
refresh()
return result as Record<string, Provider>
}
await refresh()
return get()
}
async function refresh() {
const file = Bun.file(filepath)
log.info("refreshing")
const result = await fetch("https://models.dev/api.json")
if (!result.ok)
throw new Error(`Failed to fetch models.dev: ${result.statusText}`)
await Bun.write(file, result)
}
}

View File

@@ -1,78 +1,188 @@
import z from "zod"
import { App } from "../app/app"
import { Config } from "../config/config"
import { PROVIDER_DATABASE } from "./database"
import { mergeDeep, sortBy } from "remeda"
import { NoSuchModelError, type LanguageModel, type Provider as SDK } from "ai"
import { Log } from "../util/log"
import path from "path"
import { Global } from "../global"
import { BunProc } from "../bun"
import { BashTool } from "../tool/bash"
import { EditTool } from "../tool/edit"
import { FetchTool } from "../tool/fetch"
import { WebFetchTool } from "../tool/webfetch"
import { GlobTool } from "../tool/glob"
import { GrepTool } from "../tool/grep"
import { ListTool } from "../tool/ls"
import { LspDiagnosticTool } from "../tool/lsp-diagnostics"
import { LspHoverTool } from "../tool/lsp-hover"
import { PatchTool } from "../tool/patch"
import { ViewTool } from "../tool/view"
import { ReadTool } from "../tool/read"
import type { Tool } from "../tool/tool"
import { WriteTool } from "../tool/write"
import { TodoReadTool, TodoWriteTool } from "../tool/todo"
import { AuthAnthropic } from "../auth/anthropic"
import { ModelsDev } from "./models"
import { NamedError } from "../util/error"
import { Auth } from "../auth"
import { TaskTool } from "../tool/task"
export namespace Provider {
const log = Log.create({ service: "provider" })
export const Model = z
.object({
id: z.string(),
name: z.string().optional(),
cost: z.object({
input: z.number(),
inputCached: z.number(),
output: z.number(),
outputCached: z.number(),
}),
contextWindow: z.number(),
maxOutputTokens: z.number().optional(),
attachment: z.boolean(),
reasoning: z.boolean().optional(),
})
.openapi({
ref: "Provider.Model",
})
export type Model = z.output<typeof Model>
type CustomLoader = (
provider: ModelsDev.Provider,
) => Promise<Record<string, any> | false>
export const Info = z
.object({
id: z.string(),
name: z.string(),
options: z.record(z.string(), z.any()).optional(),
models: Model.array(),
})
.openapi({
ref: "Provider.Info",
})
export type Info = z.output<typeof Info>
type Source = "env" | "config" | "custom" | "api"
const AUTODETECT: Record<string, string[]> = {
anthropic: ["ANTHROPIC_API_KEY"],
openai: ["OPENAI_API_KEY"],
google: ["GOOGLE_GENERATIVE_AI_API_KEY", "GEMINI_API_KEY"],
const CUSTOM_LOADERS: Record<string, CustomLoader> = {
async anthropic(provider) {
const access = await AuthAnthropic.access()
if (!access) return false
for (const model of Object.values(provider.models)) {
model.cost = {
input: 0,
output: 0,
}
}
return {
apiKey: "",
async fetch(input: any, init: any) {
const access = await AuthAnthropic.access()
const headers = {
...init.headers,
authorization: `Bearer ${access}`,
"anthropic-beta": "oauth-2025-04-20",
}
delete headers["x-api-key"]
return fetch(input, {
...init,
headers,
})
},
}
},
"amazon-bedrock": async () => {
if (!process.env["AWS_PROFILE"]) return false
const { fromNodeProviderChain } = await import(
await BunProc.install("@aws-sdk/credential-providers")
)
return {
region: process.env["AWS_REGION"] ?? "us-east-1",
credentialProvider: fromNodeProviderChain(),
}
},
}
const state = App.state("provider", async () => {
const config = await Config.get()
const providers = new Map<string, Info>()
const models = new Map<string, { info: Model; language: LanguageModel }>()
const database = await ModelsDev.get()
const providers: {
[providerID: string]: {
source: Source
info: ModelsDev.Provider
options: Record<string, any>
}
} = {}
const models = new Map<
string,
{ info: ModelsDev.Model; language: LanguageModel }
>()
const sdk = new Map<string, SDK>()
for (const item of PROVIDER_DATABASE) {
if (!AUTODETECT[item.id].some((env) => process.env[env])) continue
providers.set(item.id, item)
log.info("init")
function mergeProvider(
id: string,
options: Record<string, any>,
source: Source,
) {
const provider = providers[id]
if (!provider) {
const info = database[id]
if (!info) return
if (info.api) options["baseURL"] = info.api
providers[id] = {
source,
info,
options,
}
return
}
provider.options = mergeDeep(provider.options, options)
provider.source = source
}
for (const item of config.provider ?? []) {
providers.set(item.id, item)
const configProviders = Object.entries(config.provider ?? {})
for (const [providerID, provider] of configProviders) {
const existing = database[providerID]
const parsed: ModelsDev.Provider = {
id: providerID,
npm: provider.npm ?? existing?.npm,
name: provider.name ?? existing?.name ?? providerID,
env: provider.env ?? existing?.env ?? [],
models: existing?.models ?? {},
}
for (const [modelID, model] of Object.entries(provider.models ?? {})) {
const existing = parsed.models[modelID]
const parsedModel: ModelsDev.Model = {
id: modelID,
name: model.name ?? existing?.name ?? modelID,
attachment: model.attachment ?? existing?.attachment ?? false,
reasoning: model.reasoning ?? existing?.reasoning ?? false,
temperature: model.temperature ?? existing?.temperature ?? false,
cost: model.cost ??
existing?.cost ?? {
input: 0,
output: 0,
inputCached: 0,
outputCached: 0,
},
limit: model.limit ??
existing?.limit ?? {
context: 0,
output: 0,
},
}
parsed.models[modelID] = parsedModel
}
database[providerID] = parsed
}
const disabled = await Config.get().then(
(cfg) => new Set(cfg.disabled_providers ?? []),
)
// load env
for (const [providerID, provider] of Object.entries(database)) {
if (disabled.has(providerID)) continue
if (provider.env.some((item) => process.env[item])) {
mergeProvider(providerID, {}, "env")
}
}
// load apikeys
for (const [providerID, provider] of Object.entries(await Auth.all())) {
if (disabled.has(providerID)) continue
if (provider.type === "api") {
mergeProvider(providerID, { apiKey: provider.key }, "api")
}
}
// load custom
for (const [providerID, fn] of Object.entries(CUSTOM_LOADERS)) {
if (disabled.has(providerID)) continue
const result = await fn(database[providerID])
if (result) mergeProvider(providerID, result, "custom")
}
// load config
for (const [providerID, provider] of configProviders) {
mergeProvider(providerID, provider.options ?? {}, "config")
}
for (const providerID of Object.keys(providers)) {
log.info("found", { providerID })
}
return {
@@ -82,28 +192,27 @@ export namespace Provider {
}
})
export async function active() {
export async function list() {
return state().then((state) => state.providers)
}
async function getSDK(providerID: string) {
const s = await state()
if (s.sdk.has(providerID)) return s.sdk.get(providerID)!
const dir = path.join(Global.cache(), `node_modules`, `@ai-sdk`, providerID)
if (!(await Bun.file(path.join(dir, "package.json")).exists())) {
log.info("installing", {
providerID,
async function getSDK(provider: ModelsDev.Provider) {
return (async () => {
using _ = log.time("getSDK", {
providerID: provider.id,
})
BunProc.run(["add", `@ai-sdk/${providerID}@alpha`], {
cwd: Global.cache(),
})
}
const mod = await import(path.join(dir))
const fn = mod[Object.keys(mod).find((key) => key.startsWith("create"))!]
const loaded = fn(s.providers.get(providerID)?.options)
s.sdk.set(providerID, loaded)
return loaded as SDK
const s = await state()
const existing = s.sdk.get(provider.id)
if (existing) return existing
const pkg = provider.npm ?? provider.id
const mod = await import(await BunProc.install(pkg, "latest"))
const fn = mod[Object.keys(mod).find((key) => key.startsWith("create"))!]
const loaded = fn(s.providers[provider.id]?.options)
s.sdk.set(provider.id, loaded)
return loaded as SDK
})().catch((e) => {
throw new InitError({ providerID: provider.id }, { cause: e })
})
}
export async function getModel(providerID: string, modelID: string) {
@@ -111,21 +220,21 @@ export namespace Provider {
const s = await state()
if (s.models.has(key)) return s.models.get(key)!
log.info("loading", {
log.info("getModel", {
providerID,
modelID,
})
const provider = s.providers.get(providerID)
if (!provider) throw new ModelNotFoundError(modelID)
const info = provider.models.find((m) => m.id === modelID)
if (!info) throw new ModelNotFoundError(modelID)
const sdk = await getSDK(providerID)
if (!sdk) throw new ModelNotFoundError(modelID)
const provider = s.providers[providerID]
if (!provider) throw new ModelNotFoundError({ providerID, modelID })
const info = provider.info.models[modelID]
if (!info) throw new ModelNotFoundError({ providerID, modelID })
const sdk = await getSDK(provider.info)
try {
const language = sdk.languageModel(modelID)
const language =
// @ts-expect-error
"responses" in sdk ? sdk.responses(modelID) : sdk.languageModel(modelID)
log.info("found", { providerID, modelID })
s.models.set(key, {
info,
@@ -136,41 +245,136 @@ export namespace Provider {
language,
}
} catch (e) {
if (e instanceof NoSuchModelError) throw new ModelNotFoundError(modelID)
if (e instanceof NoSuchModelError)
throw new ModelNotFoundError(
{
modelID: modelID,
providerID,
},
{ cause: e },
)
throw e
}
}
const priority = ["gemini-2.5-pro-preview", "codex-mini", "claude-sonnet-4"]
export function sort(models: ModelsDev.Model[]) {
return sortBy(
models,
[
(model) => priority.findIndex((filter) => model.id.includes(filter)),
"desc",
],
[(model) => (model.id.includes("latest") ? 0 : 1), "asc"],
[(model) => model.id, "desc"],
)
}
export async function defaultModel() {
const cfg = await Config.get()
const provider = await list()
.then((val) => Object.values(val))
.then((x) => x.find((p) => !cfg.provider || Object.keys(cfg.provider).includes(p.info.id)))
if (!provider) throw new Error("no providers found")
const [model] = sort(Object.values(provider.info.models))
if (!model) throw new Error("no models found")
return {
providerID: provider.info.id,
modelID: model.id,
}
}
const TOOLS = [
BashTool,
EditTool,
FetchTool,
WebFetchTool,
GlobTool,
GrepTool,
ListTool,
LspDiagnosticTool,
LspHoverTool,
PatchTool,
ViewTool,
ReadTool,
EditTool,
// MultiEditTool,
WriteTool,
TodoWriteTool,
TaskTool,
TodoReadTool,
]
const TOOL_MAPPING: Record<string, Tool.Info[]> = {
anthropic: TOOLS,
openai: TOOLS,
anthropic: TOOLS.filter((t) => t.id !== "patch"),
openai: TOOLS.map((t) => ({
...t,
parameters: optionalToNullable(t.parameters),
})),
google: TOOLS,
}
export async function tools(providerID: string) {
/*
const cfg = await Config.get()
if (cfg.tool?.provider?.[providerID])
return cfg.tool.provider[providerID].map(
(id) => TOOLS.find((t) => t.id === id)!,
)
*/
return TOOL_MAPPING[providerID] ?? TOOLS
}
class ModelNotFoundError extends Error {
constructor(public readonly model: string) {
super()
function optionalToNullable(schema: z.ZodTypeAny): z.ZodTypeAny {
if (schema instanceof z.ZodObject) {
const shape = schema.shape
const newShape: Record<string, z.ZodTypeAny> = {}
for (const [key, value] of Object.entries(shape)) {
const zodValue = value as z.ZodTypeAny
if (zodValue instanceof z.ZodOptional) {
newShape[key] = zodValue.unwrap().nullable()
} else {
newShape[key] = optionalToNullable(zodValue)
}
}
return z.object(newShape)
}
if (schema instanceof z.ZodArray) {
return z.array(optionalToNullable(schema.element))
}
if (schema instanceof z.ZodUnion) {
return z.union(
schema.options.map((option: z.ZodTypeAny) =>
optionalToNullable(option),
) as [z.ZodTypeAny, z.ZodTypeAny, ...z.ZodTypeAny[]],
)
}
return schema
}
export const ModelNotFoundError = NamedError.create(
"ProviderModelNotFoundError",
z.object({
providerID: z.string(),
modelID: z.string(),
}),
)
export const InitError = NamedError.create(
"ProviderInitError",
z.object({
providerID: z.string(),
}),
)
export const AuthError = NamedError.create(
"ProviderAuthError",
z.object({
providerID: z.string(),
message: z.string(),
}),
)
}

View File

@@ -0,0 +1,24 @@
import type { CoreMessage } from "ai"
export namespace ProviderTransform {
export function message(
msg: CoreMessage,
index: number,
providerID: string,
modelID: string,
) {
if (
(providerID === "anthropic" || modelID.includes("anthropic")) &&
index < 4
) {
msg.providerOptions = {
...msg.providerOptions,
anthropic: {
cacheControl: { type: "ephemeral" },
},
}
}
return msg
}
}

View File

@@ -3,17 +3,41 @@ import { Bus } from "../bus"
import { describeRoute, generateSpecs, openAPISpecs } from "hono-openapi"
import { Hono } from "hono"
import { streamSSE } from "hono/streaming"
import { Session } from "../session/session"
import { Session } from "../session"
import { resolver, validator as zValidator } from "hono-openapi/zod"
import { z } from "zod"
import { Message } from "../session/message"
import { Provider } from "../provider/provider"
import { App } from "../app/app"
import { Global } from "../global"
import { mapValues } from "remeda"
import { NamedError } from "../util/error"
import { ModelsDev } from "../provider/models"
import { Ripgrep } from "../external/ripgrep"
import { Installation } from "../installation"
import { Config } from "../config/config"
const ERRORS = {
400: {
description: "Bad request",
content: {
"application/json": {
schema: resolver(
z
.object({
data: z.record(z.string(), z.any()),
})
.openapi({
ref: "Error",
}),
),
},
},
},
} as const
export namespace Server {
const log = Log.create({ service: "server" })
const PORT = 16713
export type Routes = ReturnType<typeof app>
@@ -21,6 +45,30 @@ export namespace Server {
const app = new Hono()
const result = app
.onError((err, c) => {
if (err instanceof NamedError) {
return c.json(err.toObject(), {
status: 400,
})
}
return c.json(
new NamedError.Unknown({ message: err.toString() }).toObject(),
{
status: 400,
},
)
})
.use(async (c, next) => {
log.info("request", {
method: c.req.method,
path: c.req.path,
})
const start = Date.now()
await next()
log.info("response", {
duration: Date.now() - start,
})
})
.get(
"/openapi",
openAPISpecs(app, {
@@ -93,6 +141,74 @@ export namespace Server {
return c.json(App.info())
},
)
.post(
"/config_get",
describeRoute({
description: "Get config info",
responses: {
200: {
description: "Get config info",
content: {
"application/json": {
schema: resolver(Config.Info),
},
},
},
},
}),
async (c) => {
return c.json(await Config.get())
},
)
.post(
"/app_initialize",
describeRoute({
description: "Initialize the app",
responses: {
200: {
description: "Initialize the app",
content: {
"application/json": {
schema: resolver(z.boolean()),
},
},
},
},
}),
async (c) => {
await App.initialize()
return c.json(true)
},
)
.post(
"/session_initialize",
describeRoute({
description: "Analyze the app and create an AGENTS.md file",
responses: {
200: {
description: "200",
content: {
"application/json": {
schema: resolver(z.boolean()),
},
},
},
},
}),
zValidator(
"json",
z.object({
sessionID: z.string(),
providerID: z.string(),
modelID: z.string(),
}),
),
async (c) => {
const body = c.req.valid("json")
await Session.initialize(body)
return c.json(true)
},
)
.post(
"/path_get",
describeRoute({
@@ -121,7 +237,7 @@ export namespace Server {
root: app.path.root,
data: app.path.data,
cwd: app.path.cwd,
config: Global.config(),
config: Global.Path.data,
})
},
)
@@ -130,6 +246,7 @@ export namespace Server {
describeRoute({
description: "Create a new session",
responses: {
...ERRORS,
200: {
description: "Successfully created session",
content: {
@@ -313,15 +430,79 @@ export namespace Server {
description: "List of providers",
content: {
"application/json": {
schema: resolver(Provider.Info.array()),
schema: resolver(
z.object({
providers: ModelsDev.Provider.array(),
default: z.record(z.string(), z.string()),
}),
),
},
},
},
},
}),
async (c) => {
const providers = await Provider.active()
return c.json(providers.values().toArray())
const providers = await Provider.list().then((x) =>
mapValues(x, (item) => item.info),
)
return c.json({
providers: Object.values(providers),
default: mapValues(
providers,
(item) => Provider.sort(Object.values(item.models))[0].id,
),
})
},
)
.post(
"/file_search",
describeRoute({
description: "Search for files",
responses: {
200: {
description: "Search for files",
content: {
"application/json": {
schema: resolver(z.string().array()),
},
},
},
},
}),
zValidator(
"json",
z.object({
query: z.string(),
}),
),
async (c) => {
const body = c.req.valid("json")
const app = App.info()
const result = await Ripgrep.files({
cwd: app.path.cwd,
query: body.query,
limit: 10,
})
return c.json(result)
},
)
.post(
"installation_info",
describeRoute({
description: "Get installation info",
responses: {
200: {
description: "Get installation info",
content: {
"application/json": {
schema: resolver(Installation.Info),
},
},
},
},
}),
async (c) => {
return c.json(Installation.info())
},
)
@@ -345,7 +526,7 @@ export namespace Server {
export function listen() {
const server = Bun.serve({
port: PORT,
port: 0,
hostname: "0.0.0.0",
idleTimeout: 0,
fetch: app().fetch,

View File

@@ -1,5 +1,5 @@
import { App } from "../app/app"
import path from "path"
import { Filesystem } from "../util/filesystem"
export namespace SessionContext {
const FILES = [
@@ -9,20 +9,10 @@ export namespace SessionContext {
]
export async function find() {
const { cwd, root } = App.info().path
let current = cwd
const found = []
while (true) {
for (const item of FILES) {
const file = Bun.file(path.join(current, item))
if (await file.exists()) {
found.push(file.text())
}
}
if (current === root) break
const parent = path.dirname(current)
if (parent === current) break
current = parent
for (const item of FILES) {
const matches = await Filesystem.findUp(item, cwd, root)
found.push(...matches.map((x) => Bun.file(x).text()))
}
return Promise.all(found).then((parts) => parts.join("\n\n"))
}

View File

@@ -0,0 +1,878 @@
import path from "path"
import { App } from "../app/app"
import { Identifier } from "../id/id"
import { Storage } from "../storage/storage"
import { Log } from "../util/log"
import {
generateText,
LoadAPIKeyError,
convertToCoreMessages,
streamText,
tool,
type Tool as AITool,
type LanguageModelUsage,
type CoreMessage,
type UIMessage,
type ProviderMetadata,
} from "ai"
import { z, ZodSchema } from "zod"
import { Decimal } from "decimal.js"
import PROMPT_INITIALIZE from "../session/prompt/initialize.txt"
import { Share } from "../share/share"
import { Message } from "./message"
import { Bus } from "../bus"
import { Provider } from "../provider/provider"
import { MCP } from "../mcp"
import { NamedError } from "../util/error"
import type { Tool } from "../tool/tool"
import { SystemPrompt } from "./system"
import { Flag } from "../flag/flag"
import type { ModelsDev } from "../provider/models"
import { Installation } from "../installation"
import { Config } from "../config/config"
import { ProviderTransform } from "../provider/transform"
export namespace Session {
const log = Log.create({ service: "session" })
export const Info = z
.object({
id: Identifier.schema("session"),
parentID: Identifier.schema("session").optional(),
share: z
.object({
url: z.string(),
})
.optional(),
title: z.string(),
version: z.string(),
time: z.object({
created: z.number(),
updated: z.number(),
}),
})
.openapi({
ref: "session.info",
})
export type Info = z.output<typeof Info>
export const ShareInfo = z.object({
secret: z.string(),
url: z.string(),
})
export type ShareInfo = z.output<typeof ShareInfo>
export const Event = {
Updated: Bus.event(
"session.updated",
z.object({
info: Info,
}),
),
Error: Bus.event(
"session.error",
z.object({
error: Message.Info.shape.metadata.shape.error,
}),
),
}
const state = App.state(
"session",
() => {
const sessions = new Map<string, Info>()
const messages = new Map<string, Message.Info[]>()
const pending = new Map<string, AbortController>()
return {
sessions,
messages,
pending,
}
},
async (state) => {
for (const [_, controller] of state.pending) {
controller.abort()
}
},
)
export async function create(parentID?: string) {
const result: Info = {
id: Identifier.descending("session"),
version: Installation.VERSION,
parentID,
title:
(parentID ? "Child session - " : "New Session - ") +
new Date().toISOString(),
time: {
created: Date.now(),
updated: Date.now(),
},
}
log.info("created", result)
state().sessions.set(result.id, result)
await Storage.writeJSON("session/info/" + result.id, result)
const cfg = await Config.get()
if (!result.parentID && (Flag.OPENCODE_AUTO_SHARE || cfg.autoshare))
share(result.id).then((share) => {
update(result.id, (draft) => {
draft.share = share
})
})
Bus.publish(Event.Updated, {
info: result,
})
return result
}
export async function get(id: string) {
const result = state().sessions.get(id)
if (result) {
return result
}
const read = await Storage.readJSON<Info>("session/info/" + id)
state().sessions.set(id, read)
return read as Info
}
export async function getShare(id: string) {
return Storage.readJSON<ShareInfo>("session/share/" + id)
}
export async function share(id: string) {
const session = await get(id)
if (session.share) return session.share
const share = await Share.create(id)
await update(id, (draft) => {
draft.share = {
url: share.url,
}
})
await Storage.writeJSON<ShareInfo>("session/share/" + id, share)
await Share.sync("session/info/" + id, session)
for (const msg of await messages(id)) {
await Share.sync("session/message/" + id + "/" + msg.id, msg)
}
return share
}
export async function update(id: string, editor: (session: Info) => void) {
const { sessions } = state()
const session = await get(id)
if (!session) return
editor(session)
session.time.updated = Date.now()
sessions.set(id, session)
await Storage.writeJSON("session/info/" + id, session)
Bus.publish(Event.Updated, {
info: session,
})
return session
}
export async function messages(sessionID: string) {
const result = [] as Message.Info[]
const list = Storage.list("session/message/" + sessionID)
for await (const p of list) {
const read = await Storage.readJSON<Message.Info>(p)
result.push(read)
}
result.sort((a, b) => (a.id > b.id ? 1 : -1))
return result
}
export async function getMessage(sessionID: string, messageID: string) {
return Storage.readJSON<Message.Info>(
"session/message/" + sessionID + "/" + messageID,
)
}
export async function* list() {
for await (const item of Storage.list("session/info")) {
const sessionID = path.basename(item, ".json")
yield get(sessionID)
}
}
export function abort(sessionID: string) {
const controller = state().pending.get(sessionID)
if (!controller) return false
controller.abort()
state().pending.delete(sessionID)
return true
}
async function updateMessage(msg: Message.Info) {
await Storage.writeJSON(
"session/message/" + msg.metadata.sessionID + "/" + msg.id,
msg,
)
Bus.publish(Message.Event.Updated, {
info: msg,
})
}
export async function chat(input: {
sessionID: string
providerID: string
modelID: string
parts: Message.Part[]
system?: string[]
tools?: Tool.Info[]
}) {
const l = log.clone().tag("session", input.sessionID)
l.info("chatting")
const model = await Provider.getModel(input.providerID, input.modelID)
let msgs = await messages(input.sessionID)
const previous = msgs.at(-1)
// auto summarize if too long
if (previous?.metadata.assistant) {
const tokens =
previous.metadata.assistant.tokens.input +
previous.metadata.assistant.tokens.cache.read +
previous.metadata.assistant.tokens.cache.write +
previous.metadata.assistant.tokens.output
if (
model.info.limit.context &&
tokens >
(model.info.limit.context - (model.info.limit.output ?? 0)) * 0.9
) {
await summarize({
sessionID: input.sessionID,
providerID: input.providerID,
modelID: input.modelID,
})
return chat(input)
}
}
using abort = lock(input.sessionID)
const lastSummary = msgs.findLast(
(msg) => msg.metadata.assistant?.summary === true,
)
if (lastSummary) msgs = msgs.filter((msg) => msg.id >= lastSummary.id)
const app = App.info()
const session = await get(input.sessionID)
if (msgs.length === 0 && !session.parentID) {
generateText({
maxTokens: input.providerID === "google" ? 1024 : 20,
messages: [
...SystemPrompt.title(input.providerID).map(
(x): CoreMessage => ({
role: "system",
content: x,
}),
),
...convertToCoreMessages([
{
role: "user",
content: "",
parts: toParts(input.parts),
},
]),
].map((msg, i) =>
ProviderTransform.message(msg, i, input.providerID, input.modelID),
),
model: model.language,
})
.then((result) => {
if (result.text)
return Session.update(input.sessionID, (draft) => {
draft.title = result.text
})
})
.catch(() => {})
}
const msg: Message.Info = {
role: "user",
id: Identifier.ascending("message"),
parts: input.parts,
metadata: {
time: {
created: Date.now(),
},
sessionID: input.sessionID,
tool: {},
},
}
await updateMessage(msg)
msgs.push(msg)
const system = input.system ?? SystemPrompt.provider(input.providerID)
system.push(...(await SystemPrompt.environment()))
system.push(...(await SystemPrompt.custom()))
const next: Message.Info = {
id: Identifier.ascending("message"),
role: "assistant",
parts: [],
metadata: {
assistant: {
system,
path: {
cwd: app.path.cwd,
root: app.path.root,
},
cost: 0,
tokens: {
input: 0,
output: 0,
reasoning: 0,
cache: { read: 0, write: 0 },
},
modelID: input.modelID,
providerID: input.providerID,
},
time: {
created: Date.now(),
},
sessionID: input.sessionID,
tool: {},
},
}
await updateMessage(next)
const tools: Record<string, AITool> = {}
for (const item of await Provider.tools(input.providerID)) {
tools[item.id.replaceAll(".", "_")] = tool({
id: item.id as any,
description: item.description,
parameters: item.parameters as ZodSchema,
async execute(args, opts) {
const start = Date.now()
try {
const result = await item.execute(args, {
sessionID: input.sessionID,
abort: abort.signal,
messageID: next.id,
metadata: async (val) => {
next.metadata.tool[opts.toolCallId] = {
...val,
time: {
start: 0,
end: 0,
},
}
await updateMessage(next)
},
})
next.metadata!.tool![opts.toolCallId] = {
...result.metadata,
time: {
start,
end: Date.now(),
},
}
await updateMessage(next)
return result.output
} catch (e: any) {
next.metadata!.tool![opts.toolCallId] = {
error: true,
message: e.toString(),
title: e.toString(),
time: {
start,
end: Date.now(),
},
}
await updateMessage(next)
return e.toString()
}
},
})
}
for (const [key, item] of Object.entries(await MCP.tools())) {
const execute = item.execute
if (!execute) continue
item.execute = async (args, opts) => {
const start = Date.now()
try {
const result = await execute(args, opts)
next.metadata!.tool![opts.toolCallId] = {
...result.metadata,
time: {
start,
end: Date.now(),
},
}
await updateMessage(next)
return result.content
.filter((x: any) => x.type === "text")
.map((x: any) => x.text)
.join("\n\n")
} catch (e: any) {
next.metadata!.tool![opts.toolCallId] = {
error: true,
message: e.toString(),
title: "mcp",
time: {
start,
end: Date.now(),
},
}
await updateMessage(next)
return e.toString()
}
}
tools[key] = item
}
let text: Message.TextPart | undefined
await Bun.write(
"/tmp/message.json",
JSON.stringify(
[
...system.map(
(x): CoreMessage => ({
role: "system",
content: x,
}),
),
...convertToCoreMessages(
msgs.map(toUIMessage).filter((x) => x.parts.length > 0),
),
],
null,
2,
),
)
const result = streamText({
onStepFinish: async (step) => {
log.info("step finish", { finishReason: step.finishReason })
const assistant = next.metadata!.assistant!
const usage = getUsage(model.info, step.usage, step.providerMetadata)
assistant.cost += usage.cost
assistant.tokens = usage.tokens
await updateMessage(next)
if (text) {
Bus.publish(Message.Event.PartUpdated, {
part: text,
messageID: next.id,
sessionID: next.metadata.sessionID,
})
}
text = undefined
},
async onFinish(input) {
log.info("message finish", {
reason: input.finishReason,
})
const assistant = next.metadata!.assistant!
const usage = getUsage(model.info, input.usage, input.providerMetadata)
assistant.cost = usage.cost
await updateMessage(next)
},
onError(err) {
log.error("callback error", err)
switch (true) {
case LoadAPIKeyError.isInstance(err.error):
next.metadata.error = new Provider.AuthError(
{
providerID: input.providerID,
message: err.error.message,
},
{ cause: err.error },
).toObject()
break
case err.error instanceof Error:
next.metadata.error = new NamedError.Unknown(
{ message: err.error.toString() },
{ cause: err.error },
).toObject()
break
default:
next.metadata.error = new NamedError.Unknown(
{ message: JSON.stringify(err.error) },
{ cause: err.error },
)
}
Bus.publish(Event.Error, {
error: next.metadata.error,
})
},
// async prepareStep(step) {
// next.parts.push({
// type: "step-start",
// })
// await updateMessage(next)
// return step
// },
toolCallStreaming: true,
abortSignal: abort.signal,
maxSteps: 1000,
messages: [
...system.map(
(x): CoreMessage => ({
role: "system",
content: x,
}),
),
...convertToCoreMessages(
msgs.map(toUIMessage).filter((x) => x.parts.length > 0),
),
].map((msg, i) =>
ProviderTransform.message(msg, i, input.providerID, input.modelID),
),
temperature: model.info.temperature ? 0 : undefined,
tools: {
...tools,
},
model: model.language,
})
try {
for await (const value of result.fullStream) {
l.info("part", {
type: value.type,
})
switch (value.type) {
case "step-start":
next.parts.push({
type: "step-start",
})
break
case "text-delta":
if (!text) {
text = {
type: "text",
text: value.textDelta,
}
next.parts.push(text)
break
} else text.text += value.textDelta
break
case "tool-call": {
const [match] = next.parts.flatMap((p) =>
p.type === "tool-invocation" &&
p.toolInvocation.toolCallId === value.toolCallId
? [p]
: [],
)
if (!match) break
match.toolInvocation.args = value.args
match.toolInvocation.state = "call"
Bus.publish(Message.Event.PartUpdated, {
part: match,
messageID: next.id,
sessionID: next.metadata.sessionID,
})
break
}
case "tool-call-streaming-start":
next.parts.push({
type: "tool-invocation",
toolInvocation: {
state: "partial-call",
toolName: value.toolName,
toolCallId: value.toolCallId,
args: {},
},
})
Bus.publish(Message.Event.PartUpdated, {
part: next.parts[next.parts.length - 1],
messageID: next.id,
sessionID: next.metadata.sessionID,
})
break
case "tool-call-delta":
break
// for some reason ai sdk claims to not send this part but it does
// @ts-expect-error
case "tool-result":
const match = next.parts.find(
(p) =>
p.type === "tool-invocation" &&
// @ts-expect-error
p.toolInvocation.toolCallId === value.toolCallId,
)
if (match && match.type === "tool-invocation") {
match.toolInvocation = {
// @ts-expect-error
args: value.args,
// @ts-expect-error
toolCallId: value.toolCallId,
// @ts-expect-error
toolName: value.toolName,
state: "result",
// @ts-expect-error
result: value.result as string,
}
Bus.publish(Message.Event.PartUpdated, {
part: match,
messageID: next.id,
sessionID: next.metadata.sessionID,
})
}
break
default:
l.info("unhandled", {
type: value.type,
})
}
await updateMessage(next)
}
} catch (e: any) {
log.error("stream error", {
error: e,
})
switch (true) {
case LoadAPIKeyError.isInstance(e):
next.metadata.error = new Provider.AuthError(
{
providerID: input.providerID,
message: e.message,
},
{ cause: e },
).toObject()
break
case e instanceof Error:
next.metadata.error = new NamedError.Unknown(
{ message: e.toString() },
{ cause: e },
).toObject()
break
default:
next.metadata.error = new NamedError.Unknown(
{ message: JSON.stringify(e) },
{ cause: e },
)
}
Bus.publish(Event.Error, {
error: next.metadata.error,
})
}
next.metadata!.time.completed = Date.now()
for (const part of next.parts) {
if (
part.type === "tool-invocation" &&
part.toolInvocation.state !== "result"
) {
part.toolInvocation = {
...part.toolInvocation,
state: "result",
result: "request was aborted",
}
}
}
await updateMessage(next)
return next
}
export async function summarize(input: {
sessionID: string
providerID: string
modelID: string
}) {
using abort = lock(input.sessionID)
const msgs = await messages(input.sessionID)
const lastSummary = msgs.findLast(
(msg) => msg.metadata.assistant?.summary === true,
)?.id
const filtered = msgs.filter((msg) => !lastSummary || msg.id >= lastSummary)
const model = await Provider.getModel(input.providerID, input.modelID)
const app = App.info()
const system = SystemPrompt.summarize(input.providerID)
const next: Message.Info = {
id: Identifier.ascending("message"),
role: "assistant",
parts: [],
metadata: {
tool: {},
sessionID: input.sessionID,
assistant: {
system,
path: {
cwd: app.path.cwd,
root: app.path.root,
},
summary: true,
cost: 0,
modelID: input.modelID,
providerID: input.providerID,
tokens: {
input: 0,
output: 0,
reasoning: 0,
cache: { read: 0, write: 0 },
},
},
time: {
created: Date.now(),
},
},
}
await updateMessage(next)
const result = await generateText({
abortSignal: abort.signal,
model: model.language,
messages: [
...system.map(
(x): CoreMessage => ({
role: "system",
content: x,
}),
),
...convertToCoreMessages(filtered.map(toUIMessage)),
{
role: "user",
content: [
{
type: "text",
text: "Provide a detailed but concise summary of our conversation above. Focus on information that would be helpful for continuing the conversation, including what we did, what we're doing, which files we're working on, and what we're going to do next.",
},
],
},
],
})
next.parts.push({
type: "text",
text: result.text,
})
const assistant = next.metadata!.assistant!
const usage = getUsage(model.info, result.usage, result.providerMetadata)
assistant.cost = usage.cost
assistant.tokens = usage.tokens
await updateMessage(next)
}
function lock(sessionID: string) {
log.info("locking", { sessionID })
if (state().pending.has(sessionID)) throw new BusyError(sessionID)
const controller = new AbortController()
state().pending.set(sessionID, controller)
return {
signal: controller.signal,
[Symbol.dispose]() {
log.info("unlocking", { sessionID })
state().pending.delete(sessionID)
},
}
}
function getUsage(
model: ModelsDev.Model,
usage: LanguageModelUsage,
metadata?: ProviderMetadata,
) {
const tokens = {
input: usage.promptTokens ?? 0,
output: usage.completionTokens ?? 0,
reasoning: 0,
cache: {
write: (metadata?.["anthropic"]?.["cacheCreationInputTokens"] ??
0) as number,
read: (metadata?.["anthropic"]?.["cacheReadInputTokens"] ??
0) as number,
},
}
return {
cost: new Decimal(0)
.add(new Decimal(tokens.input).mul(model.cost.input).div(1_000_000))
.add(new Decimal(tokens.output).mul(model.cost.output).div(1_000_000))
.add(
new Decimal(tokens.cache.read)
.mul(model.cost.cache_read ?? 0)
.div(1_000_000),
)
.add(
new Decimal(tokens.cache.write)
.mul(model.cost.cache_write ?? 0)
.div(1_000_000),
)
.toNumber(),
tokens,
}
}
export class BusyError extends Error {
constructor(public readonly sessionID: string) {
super(`Session ${sessionID} is busy`)
}
}
export async function initialize(input: {
sessionID: string
modelID: string
providerID: string
}) {
const app = App.info()
await Session.chat({
sessionID: input.sessionID,
providerID: input.providerID,
modelID: input.modelID,
parts: [
{
type: "text",
text: PROMPT_INITIALIZE.replace("${path}", app.path.root),
},
],
})
await App.initialize()
}
}
function toUIMessage(msg: Message.Info): UIMessage {
if (msg.role === "assistant") {
return {
id: msg.id,
role: "assistant",
content: "",
parts: toParts(msg.parts),
}
}
if (msg.role === "user") {
return {
id: msg.id,
role: "user",
content: "",
parts: toParts(msg.parts),
}
}
throw new Error("not implemented")
}
function toParts(parts: Message.Part[]): UIMessage["parts"] {
const result: UIMessage["parts"] = []
for (const part of parts) {
switch (part.type) {
case "text":
result.push({ type: "text", text: part.text })
break
case "file":
result.push({
type: "file",
data: part.url,
mimeType: part.mediaType,
})
break
case "tool-invocation":
result.push({
type: "tool-invocation",
toolInvocation: part.toolInvocation,
})
break
case "step-start":
result.push({
type: "step-start",
})
break
default:
break
}
}
return result
}

View File

@@ -1,5 +1,7 @@
import z from "zod"
import { Bus } from "../bus"
import { Provider } from "../provider/provider"
import { NamedError } from "../util/error"
export namespace Message {
export const ToolCall = z
@@ -131,25 +133,51 @@ export namespace Message {
export const Info = z
.object({
id: z.string(),
role: z.enum(["system", "user", "assistant"]),
role: z.enum(["user", "assistant"]),
parts: z.array(Part),
metadata: z.object({
time: z.object({
created: z.number(),
completed: z.number().optional(),
}),
error: z
.discriminatedUnion("name", [
Provider.AuthError.Schema,
NamedError.Unknown.Schema,
])
.optional(),
sessionID: z.string(),
tool: z.record(z.string(), z.any()),
tool: z.record(
z.string(),
z
.object({
title: z.string(),
time: z.object({
start: z.number(),
end: z.number(),
}),
})
.catchall(z.any()),
),
assistant: z
.object({
system: z.string().array(),
modelID: z.string(),
providerID: z.string(),
path: z.object({
cwd: z.string(),
root: z.string(),
}),
cost: z.number(),
summary: z.boolean().optional(),
tokens: z.object({
input: z.number(),
output: z.number(),
reasoning: z.number(),
cache: z.object({
read: z.number(),
write: z.number(),
}),
}),
})
.optional(),
@@ -167,5 +195,9 @@ export namespace Message {
info: Info,
}),
),
PartUpdated: Bus.event(
"message.part.updated",
z.object({ part: Part, sessionID: z.string(), messageID: z.string() }),
),
}
}

View File

@@ -1,20 +1,21 @@
You are OpenCode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.
You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.
IMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure.
IMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.
IMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).
IMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files.
# Memory
If the current working directory contains a file called OpenCode.md, it will be automatically added to your context. This file serves multiple purposes:
1. Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time
2. Recording the user's code style preferences (naming conventions, preferred libraries, etc.)
3. Maintaining useful information about the codebase structure and organization
If the user asks for help or wants to give feedback inform them of the following:
- /help: Get help with using opencode
- To give feedback, users should report the issue at https://github.com/sst/opencode/issues
When you spend time searching for commands to typecheck, lint, build, or test, you should ask the user if it's okay to add those commands to CONTEXT.md. Similarly, when learning about code style preferences or important codebase information, ask if it's okay to add that to CONTEXT.md so you can remember it for next time.
When the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai
# Tone and style
You should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).
Remember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.
Output text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.
If you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.
Only use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.
IMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.
IMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.
IMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as "The answer is <answer>.", "Here is the content of the file..." or "Based on the information provided, the answer is..." or "Here is what I will do next...". Here are some examples to demonstrate appropriate verbosity:
@@ -30,7 +31,7 @@ assistant: 4
<example>
user: is 11 a prime number?
assistant: yes
assistant: Yes
</example>
<example>
@@ -58,7 +59,7 @@ assistant: src/foo.c
<example>
user: write tests for new feature
assistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit/patch file tool to write new tests]
assistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]
</example>
# Proactiveness
@@ -76,20 +77,85 @@ When making changes to files, first understand the file's code conventions. Mimi
- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.
# Code style
- Do not add comments to the code you write, unless the user asks you to, or the code is complex and requires additional context.
- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked
# Task Management
You have access to the TodoWrite and TodoRead tools to help you manage and plan tasks. Use these tools VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.
These tools are also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use this tool when planning, you may forget to do important tasks - and that is unacceptable.
It is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.
Examples:
<example>
user: Run the build and fix any type errors
assistant: I'm going to use the TodoWrite tool to write the following items to the todo list:
- Run the build
- Fix any type errors
I'm now going to run the build using Bash.
Looks like I found 10 type errors. I'm going to use the TodoWrite tool to write 10 items to the todo list.
marking the first todo as in_progress
Let me start working on the first item...
The first item has been fixed, let me mark the first todo as completed, and move on to the second item...
..
..
</example>
In the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors.
<example>
user: Help me write a new feature that allows users to track their usage metrics and export them to various formats
assistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the TodoWrite tool to plan this task.
Adding the following todos to the todo list:
1. Research existing metrics tracking in the codebase
2. Design the metrics collection system
3. Implement core metrics tracking functionality
4. Create export functionality for different formats
Let me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.
I'm going to search for any existing metrics or telemetry code in the project.
I've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned...
[Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go]
</example>
# Doing tasks
The user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:
1. Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.
2. Implement the solution using all tools available to you
3. Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.
4. VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to opencode.md so that you will know to run it next time.
- Use the TodoWrite tool to plan the task if required
- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.
- Implement the solution using all tools available to you
- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.
- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CLAUDE.md so that you will know to run it next time.
NEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.
- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are NOT part of the user's provided input or the tool result.
# Tool usage policy
- When doing file search, prefer to use the Agent tool in order to reduce context usage.
- If you intend to call multiple tools and there are no dependencies between the calls, make all of the independent calls in the same function_calls block.
- IMPORTANT: The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.
- When doing file search, prefer to use the Task tool in order to reduce context usage.
- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run "git status" and "git diff", send a single message with two tool calls to run the calls in parallel.
You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.
IMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.
IMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).
IMPORTANT: Always use the TodoWrite tool to plan and track tasks throughout the conversation.
# Code References
When referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.
<example>
user: Where are errors from the client handled?
assistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.
</example>

View File

@@ -0,0 +1 @@
You are Claude Code, Anthropic's official CLI for Claude.

View File

@@ -0,0 +1,8 @@
Please analyze this codebase and create an AGENTS.md file containing:
1. Build/lint/test commands - especially for running a single test
2. Code style guidelines including imports, formatting, types, naming conventions, error handling, etc.
The file you create will be given to agentic coding agents (such as yourself) that operate in this repository. Make it about 20 lines long.
If there are Cursor rules (in .cursor/rules/ or .cursorrules) or Copilot rules (in .github/copilot-instructions.md), make sure to include them.
If there's already an AGENTS.md, improve it if it's located in ${path}

View File

@@ -1,4 +1,4 @@
you will generate a short title based on the first message a user begins a conversation with
You will generate a short title based on the first message a user begins a conversation with
- ensure it is not more than 50 characters long
- the title should be a summary of the user's message
- it should be one line long

View File

@@ -1,534 +0,0 @@
import path from "path"
import { App } from "../app/app"
import { Identifier } from "../id/id"
import { Storage } from "../storage/storage"
import { Log } from "../util/log"
import {
convertToModelMessages,
generateText,
stepCountIs,
streamText,
tool,
type Tool as AITool,
type LanguageModelUsage,
} from "ai"
import { z, ZodSchema } from "zod"
import { Decimal } from "decimal.js"
import PROMPT_ANTHROPIC from "./prompt/anthropic.txt"
import PROMPT_TITLE from "./prompt/title.txt"
import PROMPT_SUMMARIZE from "./prompt/summarize.txt"
import { Share } from "../share/share"
import { Message } from "./message"
import { Bus } from "../bus"
import { Provider } from "../provider/provider"
import { SessionContext } from "./context"
export namespace Session {
const log = Log.create({ service: "session" })
export const Info = z
.object({
id: Identifier.schema("session"),
share: z
.object({
secret: z.string(),
url: z.string(),
})
.optional(),
title: z.string(),
time: z.object({
created: z.number(),
updated: z.number(),
}),
})
.openapi({
ref: "session.info",
})
export type Info = z.output<typeof Info>
export const Event = {
Updated: Bus.event(
"session.updated",
z.object({
info: Info,
}),
),
}
const state = App.state("session", () => {
const sessions = new Map<string, Info>()
const messages = new Map<string, Message.Info[]>()
return {
sessions,
messages,
}
})
export async function create() {
const result: Info = {
id: Identifier.descending("session"),
title: "New Session - " + new Date().toISOString(),
time: {
created: Date.now(),
updated: Date.now(),
},
}
log.info("created", result)
state().sessions.set(result.id, result)
await Storage.writeJSON("session/info/" + result.id, result)
share(result.id).then((share) => {
update(result.id, (draft) => {
draft.share = share
})
})
Bus.publish(Event.Updated, {
info: result,
})
return result
}
export async function get(id: string) {
const result = state().sessions.get(id)
if (result) {
return result
}
const read = await Storage.readJSON<Info>("session/info/" + id)
state().sessions.set(id, read)
return read as Info
}
export async function share(id: string) {
const session = await get(id)
if (session.share) return session.share
const share = await Share.create(id)
await update(id, (draft) => {
draft.share = share
})
for (const msg of await messages(id)) {
await Share.sync("session/message/" + id + "/" + msg.id, msg)
}
return share
}
export async function update(id: string, editor: (session: Info) => void) {
const { sessions } = state()
const session = await get(id)
if (!session) return
editor(session)
session.time.updated = Date.now()
sessions.set(id, session)
await Storage.writeJSON("session/info/" + id, session)
Bus.publish(Event.Updated, {
info: session,
})
return session
}
export async function messages(sessionID: string) {
const result = [] as Message.Info[]
const list = Storage.list("session/message/" + sessionID)
for await (const p of list) {
const read = await Storage.readJSON<Message.Info>(p).catch(() => {})
if (!read) continue
result.push(read)
}
result.sort((a, b) => (a.id > b.id ? 1 : -1))
return result
}
export async function* list() {
for await (const item of Storage.list("session/info")) {
const sessionID = path.basename(item, ".json")
yield get(sessionID)
}
}
export function abort(sessionID: string) {
const controller = pending.get(sessionID)
if (!controller) return false
controller.abort()
pending.delete(sessionID)
return true
}
async function updateMessage(msg: Message.Info) {
await Storage.writeJSON(
"session/message/" + msg.metadata.sessionID + "/" + msg.id,
msg,
)
Bus.publish(Message.Event.Updated, {
info: msg,
})
}
export async function chat(input: {
sessionID: string
providerID: string
modelID: string
parts: Message.Part[]
}) {
const l = log.clone().tag("session", input.sessionID)
l.info("chatting")
const model = await Provider.getModel(input.providerID, input.modelID)
let msgs = await messages(input.sessionID)
const previous = msgs.at(-1)
if (previous?.metadata.assistant) {
const tokens =
previous.metadata.assistant.tokens.input +
previous.metadata.assistant.tokens.output
if (
tokens >
(model.info.contextWindow - (model.info.maxOutputTokens ?? 0)) * 0.9
) {
await summarize({
sessionID: input.sessionID,
providerID: input.providerID,
modelID: input.modelID,
})
return chat(input)
}
}
using abort = lock(input.sessionID)
const lastSummary = msgs.findLast(
(msg) => msg.metadata.assistant?.summary === true,
)
if (lastSummary)
msgs = msgs.filter(
(msg) => msg.role === "system" || msg.id >= lastSummary.id,
)
if (msgs.length === 0) {
const system: Message.Info = {
id: Identifier.ascending("message"),
role: "system",
parts: [
{
type: "text",
text: PROMPT_ANTHROPIC,
},
],
metadata: {
sessionID: input.sessionID,
time: {
created: Date.now(),
},
tool: {},
},
}
const context = await SessionContext.find()
if (context) {
system.parts.push({
type: "text",
text: context,
})
}
msgs.push(system)
generateText({
messages: convertToModelMessages([
{
role: "system",
parts: [
{
type: "text",
text: PROMPT_TITLE,
},
],
},
{
role: "user",
parts: input.parts,
},
]),
model: model.language,
}).then((result) => {
return Session.update(input.sessionID, (draft) => {
draft.title = result.text
})
})
await updateMessage(system)
}
const msg: Message.Info = {
role: "user",
id: Identifier.ascending("message"),
parts: input.parts,
metadata: {
time: {
created: Date.now(),
},
sessionID: input.sessionID,
tool: {},
},
}
await updateMessage(msg)
msgs.push(msg)
const next: Message.Info = {
id: Identifier.ascending("message"),
role: "assistant",
parts: [],
metadata: {
assistant: {
cost: 0,
tokens: {
input: 0,
output: 0,
reasoning: 0,
},
modelID: input.modelID,
providerID: input.providerID,
},
time: {
created: Date.now(),
},
sessionID: input.sessionID,
tool: {},
},
}
await updateMessage(next)
const tools: Record<string, AITool> = {}
for (const item of await Provider.tools(input.providerID)) {
tools[item.id.replaceAll(".", "_")] = tool({
id: item.id as any,
description: item.description,
parameters: item.parameters as ZodSchema,
async execute(args, opts) {
const start = Date.now()
try {
const result = await item.execute(args, {
sessionID: input.sessionID,
})
next.metadata!.tool![opts.toolCallId] = {
...result.metadata,
time: {
start,
end: Date.now(),
},
}
return result.output
} catch (e: any) {
next.metadata!.tool![opts.toolCallId] = {
error: true,
message: e.toString(),
time: {
start,
end: Date.now(),
},
}
return e.toString()
}
},
})
}
const result = streamText({
onStepFinish: async (step) => {
const assistant = next.metadata!.assistant!
const usage = getUsage(step.usage, model.info)
assistant.cost = usage.cost
assistant.tokens = usage.tokens
await updateMessage(next)
},
abortSignal: abort.signal,
maxRetries: 6,
stopWhen: stepCountIs(1000),
messages: convertToModelMessages(msgs),
temperature: 0,
tools,
model: model.language,
})
let text: Message.TextPart | undefined
const reader = result.toUIMessageStream().getReader()
while (true) {
const result = await reader.read().catch((e) => {
if (e instanceof DOMException && e.name === "AbortError") {
return
}
throw e
})
if (!result) break
const { done, value } = result
if (done) break
l.info("part", {
type: value.type,
})
switch (value.type) {
case "start":
break
case "start-step":
text = undefined
next.parts.push({
type: "step-start",
})
break
case "text":
if (!text) {
text = value
next.parts.push(value)
break
}
text.text += value.text
break
case "tool-call":
next.parts.push({
type: "tool-invocation",
toolInvocation: {
state: "call",
...value,
// hack until zod v4
args: value.args as any,
},
})
break
case "tool-result":
const match = next.parts.find(
(p) =>
p.type === "tool-invocation" &&
p.toolInvocation.toolCallId === value.toolCallId,
)
if (match && match.type === "tool-invocation") {
match.toolInvocation = {
args: match.toolInvocation.args,
toolCallId: match.toolInvocation.toolCallId,
toolName: match.toolInvocation.toolName,
state: "result",
result: value.result as string,
}
}
break
case "finish":
break
case "finish-step":
break
case "error":
log.error("error", value)
break
default:
l.info("unhandled", {
type: value.type,
})
}
await updateMessage(next)
}
next.metadata!.time.completed = Date.now()
await updateMessage(next)
return next
}
export async function summarize(input: {
sessionID: string
providerID: string
modelID: string
}) {
using abort = lock(input.sessionID)
const msgs = await messages(input.sessionID)
const lastSummary = msgs.findLast(
(msg) => msg.metadata.assistant?.summary === true,
)?.id
const filtered = msgs.filter(
(msg) => msg.role !== "system" && (!lastSummary || msg.id >= lastSummary),
)
const model = await Provider.getModel(input.providerID, input.modelID)
const next: Message.Info = {
id: Identifier.ascending("message"),
role: "assistant",
parts: [],
metadata: {
tool: {},
sessionID: input.sessionID,
assistant: {
summary: true,
cost: 0,
modelID: input.modelID,
providerID: input.providerID,
tokens: {
input: 0,
output: 0,
reasoning: 0,
},
},
time: {
created: Date.now(),
},
},
}
await updateMessage(next)
const result = await generateText({
abortSignal: abort.signal,
model: model.language,
messages: convertToModelMessages([
{
role: "system",
parts: [
{
type: "text",
text: PROMPT_SUMMARIZE,
},
],
},
...filtered,
{
role: "user",
parts: [
{
type: "text",
text: "Provide a detailed but concise summary of our conversation above. Focus on information that would be helpful for continuing the conversation, including what we did, what we're doing, which files we're working on, and what we're going to do next.",
},
],
},
]),
})
next.parts.push({
type: "text",
text: result.text,
})
const assistant = next.metadata!.assistant!
const usage = getUsage(result.usage, model.info)
assistant.cost = usage.cost
assistant.tokens = usage.tokens
await updateMessage(next)
}
const pending = new Map<string, AbortController>()
function lock(sessionID: string) {
log.info("locking", { sessionID })
if (pending.has(sessionID)) throw new BusyError(sessionID)
const controller = new AbortController()
pending.set(sessionID, controller)
return {
signal: controller.signal,
[Symbol.dispose]() {
log.info("unlocking", { sessionID })
pending.delete(sessionID)
},
}
}
function getUsage(usage: LanguageModelUsage, model: Provider.Model) {
const tokens = {
input: usage.inputTokens ?? 0,
output: usage.outputTokens ?? 0,
reasoning: usage.reasoningTokens ?? 0,
}
return {
cost: new Decimal(0)
.add(new Decimal(tokens.input).mul(model.cost.input))
.add(new Decimal(tokens.output).mul(model.cost.output))
.toNumber(),
tokens,
}
}
export class BusyError extends Error {
constructor(public readonly sessionID: string) {
super(`Session ${sessionID} is busy`)
}
}
}

View File

@@ -0,0 +1,124 @@
import { App } from "../app/app"
import { Ripgrep } from "../external/ripgrep"
import { Filesystem } from "../util/filesystem"
import PROMPT_ANTHROPIC from "./prompt/anthropic.txt"
import PROMPT_ANTHROPIC_SPOOF from "./prompt/anthropic_spoof.txt"
import PROMPT_SUMMARIZE from "./prompt/summarize.txt"
import PROMPT_TITLE from "./prompt/title.txt"
export namespace SystemPrompt {
export function provider(providerID: string) {
const result = []
switch (providerID) {
case "anthropic":
result.push(PROMPT_ANTHROPIC_SPOOF.trim())
result.push(PROMPT_ANTHROPIC)
break
default:
result.push(PROMPT_ANTHROPIC)
break
}
return result
}
export async function environment() {
const app = App.info()
const tree = async () => {
const files = await Ripgrep.files({
cwd: app.path.cwd,
})
type Node = {
children: Record<string, Node>
}
const root: Node = {
children: {},
}
for (const file of files) {
const parts = file.split("/")
let node = root
for (const part of parts) {
const existing = node.children[part]
if (existing) {
node = existing
continue
}
node.children[part] = {
children: {},
}
node = node.children[part]
}
}
function render(path: string[], node: Node): string {
// if (path.length === 3) return "\t".repeat(path.length) + "..."
const lines: string[] = []
const entries = Object.entries(node.children).sort(([a], [b]) =>
a.localeCompare(b),
)
for (const [name, child] of entries) {
const currentPath = [...path, name]
const indent = "\t".repeat(path.length)
const hasChildren = Object.keys(child.children).length > 0
lines.push(`${indent}${name}` + (hasChildren ? "/" : ""))
if (hasChildren) lines.push(render(currentPath, child))
}
return lines.join("\n")
}
const result = render([], root)
return result
}
return [
[
`Here is some useful information about the environment you are running in:`,
`<env>`,
` Working directory: ${app.path.cwd}`,
` Is directory a git repo: ${app.git ? "yes" : "no"}`,
` Platform: ${process.platform}`,
` Today's date: ${new Date().toDateString()}`,
`</env>`,
`<project>`,
` ${app.git ? await tree() : ""}`,
`</project>`,
].join("\n"),
]
}
const CUSTOM_FILES = [
"AGENTS.md",
"CLAUDE.md",
"CONTEXT.md", // deprecated
]
export async function custom() {
const { cwd, root } = App.info().path
const found = []
for (const item of CUSTOM_FILES) {
const matches = await Filesystem.findUp(item, cwd, root)
found.push(...matches.map((x) => Bun.file(x).text()))
}
return Promise.all(found)
}
export function summarize(providerID: string) {
switch (providerID) {
case "anthropic":
return [PROMPT_ANTHROPIC_SPOOF.trim(), PROMPT_SUMMARIZE]
default:
return [PROMPT_SUMMARIZE]
}
}
export function title(providerID: string) {
switch (providerID) {
case "anthropic":
return [PROMPT_ANTHROPIC_SPOOF.trim(), PROMPT_TITLE]
default:
return [PROMPT_TITLE]
}
}
}

View File

@@ -1,6 +1,6 @@
import { App } from "../app/app"
import { Bus } from "../bus"
import { Session } from "../session/session"
import { Session } from "../session"
import { Storage } from "../storage/storage"
import { Log } from "../util/log"
@@ -19,10 +19,11 @@ export namespace Share {
export async function sync(key: string, content: any) {
const [root, ...splits] = key.split("/")
if (root !== "session") return
const [, sessionID] = splits
const session = await Session.get(sessionID)
if (!session.share) return
const { secret } = session.share
const [sub, sessionID] = splits
if (sub === "share") return
const share = await Session.getShare(sessionID).catch(() => {})
if (!share) return
const { secret } = share
pending.set(key, content)
queue = queue
.then(async () => {

View File

@@ -1,11 +1,9 @@
import { FileStorage } from "@flystorage/file-storage"
import { LocalStorageAdapter } from "@flystorage/local-fs"
import fs from "fs/promises"
import { Log } from "../util/log"
import { App } from "../app/app"
import { Bus } from "../bus"
import path from "path"
import z from "zod"
import fs from "fs/promises"
export namespace Storage {
const log = Log.create({ service: "storage" })
@@ -17,36 +15,37 @@ export namespace Storage {
),
}
const state = App.state("storage", async () => {
const state = App.state("storage", () => {
const app = App.info()
const storageDir = path.join(app.path.data, "storage")
await fs.mkdir(storageDir, { recursive: true })
const storage = new FileStorage(new LocalStorageAdapter(storageDir))
log.info("created", { path: storageDir })
const dir = path.join(app.path.data, "storage")
log.info("init", { path: dir })
return {
storage,
dir,
}
})
export async function readJSON<T>(key: string) {
const storage = await state().then((x) => x.storage)
const data = await storage.readToString(key + ".json")
return JSON.parse(data) as T
return Bun.file(path.join(state().dir, key + ".json")).json() as Promise<T>
}
export async function writeJSON<T>(key: string, content: T) {
const storage = await state().then((x) => x.storage)
const json = JSON.stringify(content)
await storage.write(key + ".json", json)
const target = path.join(state().dir, key + ".json")
const tmp = target + Date.now() + ".tmp"
await Bun.write(tmp, JSON.stringify(content))
await fs.rename(tmp, target).catch(() => {})
await fs.unlink(tmp).catch(() => {})
Bus.publish(Event.Write, { key, content })
}
const glob = new Bun.Glob("**/*")
export async function* list(prefix: string) {
try {
const storage = await state().then((x) => x.storage)
const list = storage.list(prefix)
for await (const item of list) {
yield item.path.slice(0, -5)
for await (const item of glob.scan({
cwd: path.join(state().dir, prefix),
onlyFiles: true,
})) {
const result = path.join(prefix, item.slice(0, -5))
yield result
}
} catch {
return

View File

@@ -1,5 +1,6 @@
import { z } from "zod"
import { Tool } from "./tool"
import DESCRIPTION from "./bash.txt"
const MAX_OUTPUT_LENGTH = 30000
const BANNED_COMMANDS = [
@@ -24,177 +25,48 @@ const BANNED_COMMANDS = [
const DEFAULT_TIMEOUT = 1 * 60 * 1000
const MAX_TIMEOUT = 10 * 60 * 1000
const DESCRIPTION = `Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.
Before executing the command, please follow these steps:
1. Directory Verification:
- If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location
- For example, before running "mkdir foo/bar", first use LS to check that "foo" exists and is the intended parent directory
2. Security Check:
- For security and to limit the threat of a prompt injection attack, some commands are limited or banned. If you use a disallowed command, you will receive an error message explaining the restriction. Explain the error to the User.
- Verify that the command is not one of the banned commands: ${BANNED_COMMANDS.join(", ")}.
3. Command Execution:
- After ensuring proper quoting, execute the command.
- Capture the output of the command.
4. Output Processing:
- If the output exceeds ${MAX_OUTPUT_LENGTH} characters, output will be truncated before being returned to you.
- Prepare the output for display to the user.
5. Return Result:
- Provide the processed output of the command.
- If any errors occurred during execution, include those in the output.
Usage notes:
- The command argument is required.
- You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 30 minutes.
- VERY IMPORTANT: You MUST avoid using search commands like 'find' and 'grep'. Instead use Grep, Glob, or Agent tools to search. You MUST avoid read tools like 'cat', 'head', 'tail', and 'ls', and use FileRead and LS tools to read files.
- When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).
- IMPORTANT: All commands share the same shell session. Shell state (environment variables, virtual environments, current directory, etc.) persist between commands. For example, if you set an environment variable as part of a command, the environment variable will persist for subsequent commands.
- Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of 'cd'. You may use 'cd' if the User explicitly requests it.
<good-example>
pytest /foo/bar/tests
</good-example>
<bad-example>
cd /foo/bar && pytest tests
</bad-example>
# Committing changes with git
When the user asks you to create a new git commit, follow these steps carefully:
1. Start with a single message that contains exactly three tool_use blocks that do the following (it is VERY IMPORTANT that you send these tool_use blocks in a single message, otherwise it will feel slow to the user!):
- Run a git status command to see all untracked files.
- Run a git diff command to see both staged and unstaged changes that will be committed.
- Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.
2. Use the git context at the start of this conversation to determine which files are relevant to your commit. Add relevant untracked files to the staging area. Do not commit files that were already modified at the start of this conversation, if they are not relevant to your commit.
3. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:
<commit_analysis>
- List the files that have been changed or added
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Do not use tools to explore code, beyond what is available in the git context
- Assess the impact of these changes on the overall project
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 sentences) commit message that focuses on the "why" rather than the "what"
- Ensure your language is clear, concise, and to the point
- Ensure the message accurately reflects the changes and their purpose (i.e. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the message is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft message to ensure it accurately reflects the changes and their purpose
</commit_analysis>
4. Create the commit with a message ending with:
🤖 Generated with opencode
Co-Authored-By: opencode <noreply@opencode.ai>
- In order to ensure good formatting, ALWAYS pass the commit message via a HEREDOC, a la this example:
<example>
git commit -m "$(cat <<'EOF'
Commit message here.
🤖 Generated with opencode
Co-Authored-By: opencode <noreply@opencode.ai>
EOF
)"
</example>
5. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.
6. Finally, run git status to make sure the commit succeeded.
Important notes:
- When possible, combine the "git add" and "git commit" commands into a single "git commit -am" command, to speed things up
- However, be careful not to stage files (e.g. with 'git add .') for commits that aren't part of the change, they may have untracked files they want to keep around, but not commit.
- NEVER update the git config
- DO NOT push to the remote repository
- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.
- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit
- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.
- Return an empty response - the user will see the git output directly
# Creating pull requests
Use the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.
IMPORTANT: When the user asks you to create a pull request, follow these steps carefully:
1. Understand the current state of the branch. Remember to send a single message that contains multiple tool_use blocks (it is VERY IMPORTANT that you do this in a single message, otherwise it will feel slow to the user!):
- Run a git status command to see all untracked files.
- Run a git diff command to see both staged and unstaged changes that will be committed.
- Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote
- Run a git log command and 'git diff main...HEAD' to understand the full commit history for the current branch (from the time it diverged from the 'main' branch.)
2. Create new branch if needed
3. Commit changes if needed
4. Push to remote with -u flag if needed
5. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (not just the latest commit, but all commits that will be included in the pull request!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:
<pr_analysis>
- List the commits since diverging from the main branch
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Assess the impact of these changes on the overall project
- Do not use tools to explore code, beyond what is available in the git context
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 bullet points) pull request summary that focuses on the "why" rather than the "what"
- Ensure the summary accurately reflects all changes since diverging from the main branch
- Ensure your language is clear, concise, and to the point
- Ensure the summary accurately reflects the changes and their purpose (ie. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the summary is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft summary to ensure it accurately reflects the changes and their purpose
</pr_analysis>
6. Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.
<example>
gh pr create --title "the pr title" --body "$(cat <<'EOF'
## Summary
<1-3 bullet points>
## Test plan
[Checklist of TODOs for testing the pull request...]
🤖 Generated with opencode
EOF
)"
</example>
Important:
- Return an empty response - the user will see the gh output directly
- Never update git config`
export const BashTool = Tool.define({
id: "opencode.bash",
id: "bash",
description: DESCRIPTION,
parameters: z.object({
command: z.string(),
command: z.string().describe("The command to execute"),
timeout: z
.number()
.min(0)
.max(MAX_TIMEOUT)
.describe("Optional timeout in milliseconds")
.optional(),
description: z
.string()
.describe(
"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
),
}),
async execute(params) {
async execute(params, ctx) {
const timeout = Math.min(params.timeout ?? DEFAULT_TIMEOUT, MAX_TIMEOUT)
if (BANNED_COMMANDS.some((item) => params.command.startsWith(item)))
throw new Error(`Command '${params.command}' is not allowed`)
const process = Bun.spawnSync({
const process = Bun.spawn({
cmd: ["bash", "-c", params.command],
maxBuffer: MAX_OUTPUT_LENGTH,
signal: ctx.abort,
timeout: timeout,
stdout: "pipe",
stderr: "pipe",
})
await process.exited
const stdout = await new Response(process.stdout).text()
const stderr = await new Response(process.stderr).text()
return {
metadata: {},
output: process.stdout.toString("utf-8"),
metadata: {
stderr,
stdout,
description: params.description,
title: params.command,
},
output: stdout.replaceAll(/\x1b\[[0-9;]*m/g, ""),
}
},
})

View File

@@ -0,0 +1,141 @@
Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.
Before executing the command, please follow these steps:
1. Directory Verification:
- If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location
- For example, before running "mkdir foo/bar", first use LS to check that "foo" exists and is the intended parent directory
2. Command Execution:
- Always quote file paths that contain spaces with double quotes (e.g., cd "path with spaces/file.txt")
- Examples of proper quoting:
- cd "/Users/name/My Documents" (correct)
- cd /Users/name/My Documents (incorrect - will fail)
- python "/path/with spaces/script.py" (correct)
- python /path/with spaces/script.py (incorrect - will fail)
- After ensuring proper quoting, execute the command.
- Capture the output of the command.
Usage notes:
- The command argument is required.
- You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).
- It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
- If the output exceeds 30000 characters, output will be truncated before being returned to you.
- VERY IMPORTANT: You MUST avoid using search commands like `find` and `grep`. Instead use Grep, Glob, or Task to search. You MUST avoid read tools like `cat`, `head`, `tail`, and `ls`, and use Read and LS to read files.
- If you _still_ need to run `grep`, STOP. ALWAYS USE ripgrep at `rg` (or /usr/bin/rg) first, which all opencode users have pre-installed.
- When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).
- Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of `cd`. You may use `cd` if the User explicitly requests it.
<good-example>
pytest /foo/bar/tests
</good-example>
<bad-example>
cd /foo/bar && pytest tests
</bad-example>
# Committing changes with git
When the user asks you to create a new git commit, follow these steps carefully:
1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel, each using the Bash tool:
- Run a git status command to see all untracked files.
- Run a git diff command to see both staged and unstaged changes that will be committed.
- Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.
2. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:
<commit_analysis>
- List the files that have been changed or added
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Assess the impact of these changes on the overall project
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 sentences) commit message that focuses on the "why" rather than the "what"
- Ensure your language is clear, concise, and to the point
- Ensure the message accurately reflects the changes and their purpose (i.e. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the message is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft message to ensure it accurately reflects the changes and their purpose
</commit_analysis>
3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:
- Add relevant untracked files to the staging area.
- Create the commit with a message ending with:
🤖 Generated with [opencode](https://opencode.ai)
Co-Authored-By: opencode <noreply@opencode.ai>
- Run git status to make sure the commit succeeded.
4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.
Important notes:
- Use the git context at the start of this conversation to determine which files are relevant to your commit. Be careful not to stage and commit files (e.g. with `git add .`) that aren't relevant to your commit.
- NEVER update the git config
- DO NOT run additional commands to read or explore code, beyond what is available in the git context
- DO NOT push to the remote repository
- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.
- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit
- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.
- Return an empty response - the user will see the git output directly
- In order to ensure good formatting, ALWAYS pass the commit message via a HEREDOC, a la this example:
<example>
git commit -m "$(cat <<'EOF'
Commit message here.
🤖 Generated with [opencode](https://opencode.ai)
Co-Authored-By: opencode <noreply@opencode.ai>
EOF
)"
</example>
# Creating pull requests
Use the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.
IMPORTANT: When the user asks you to create a pull request, follow these steps carefully:
1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:
- Run a git status command to see all untracked files
- Run a git diff command to see both staged and unstaged changes that will be committed
- Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote
- Run a git log command and `git diff main...HEAD` to understand the full commit history for the current branch (from the time it diverged from the `main` branch)
2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:
<pr_analysis>
- List the commits since diverging from the main branch
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Assess the impact of these changes on the overall project
- Do not use tools to explore code, beyond what is available in the git context
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 bullet points) pull request summary that focuses on the "why" rather than the "what"
- Ensure the summary accurately reflects all changes since diverging from the main branch
- Ensure your language is clear, concise, and to the point
- Ensure the summary accurately reflects the changes and their purpose (ie. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the summary is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft summary to ensure it accurately reflects the changes and their purpose
</pr_analysis>
3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:
- Create new branch if needed
- Push to remote with -u flag if needed
- Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.
<example>
gh pr create --title "the pr title" --body "$(cat <<'EOF'
## Summary
<1-3 bullet points>
## Test plan
[Checklist of TODOs for testing the pull request...]
🤖 Generated with [opencode](https://opencode.ai)
EOF
)"
</example>
Important:
- NEVER update the git config
- Return the PR URL when you're done, so the user can see it
# Other common operations
- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments

View File

@@ -3,81 +3,43 @@ import * as path from "path"
import { Tool } from "./tool"
import { FileTimes } from "./util/file-times"
import { LSP } from "../lsp"
import { diffLines } from "diff"
import { createTwoFilesPatch } from "diff"
import { Permission } from "../permission"
const DESCRIPTION = `Edits files by replacing text, creating new files, or deleting content. For moving or renaming files, use the Bash tool with the 'mv' command instead. For larger file edits, use the FileWrite tool to overwrite files.
Before using this tool:
1. Use the FileRead tool to understand the file's contents and context
2. Verify the directory path is correct (only applicable when creating new files):
- Use the LS tool to verify the parent directory exists and is the correct location
To make a file edit, provide the following:
1. file_path: The relative path to the file to modify (must be relative, not absolute)
2. old_string: The text to replace (must be unique within the file, and must match the file contents exactly, including all whitespace and indentation)
3. new_string: The edited text to replace the old_string
Special cases:
- To create a new file: provide file_path and new_string, leave old_string empty
- To delete content: provide file_path and old_string, leave new_string empty
The tool will replace ONE occurrence of old_string with new_string in the specified file.
CRITICAL REQUIREMENTS FOR USING THIS TOOL:
1. UNIQUENESS: The old_string MUST uniquely identify the specific instance you want to change. This means:
- Include AT LEAST 3-5 lines of context BEFORE the change point
- Include AT LEAST 3-5 lines of context AFTER the change point
- Include all whitespace, indentation, and surrounding code exactly as it appears in the file
2. SINGLE INSTANCE: This tool can only change ONE instance at a time. If you need to change multiple instances:
- Make separate calls to this tool for each instance
- Each call must uniquely identify its specific instance using extensive context
3. VERIFICATION: Before using this tool:
- Check how many instances of the target text exist in the file
- If multiple instances exist, gather enough context to uniquely identify each one
- Plan separate tool calls for each instance
WARNING: If you do not follow these requirements:
- The tool will fail if old_string matches multiple locations
- The tool will fail if old_string doesn't match exactly (including whitespace)
- You may change the wrong instance if you don't include enough context
When making edits:
- Ensure the edit results in idiomatic, correct code
- Do not leave the code in a broken state
- Always use relative file paths
Remember: when making multiple file edits in a row to the same file, you should prefer to send all edits in a single message with multiple calls to this tool, rather than multiple messages with a single call each.`
import DESCRIPTION from "./edit.txt"
import { App } from "../app/app"
export const EditTool = Tool.define({
id: "opencode.edit",
id: "edit",
description: DESCRIPTION,
parameters: z.object({
filePath: z.string().describe("The absolute path to the file to modify"),
oldString: z.string().describe("The text to replace"),
newString: z.string().describe("The text to replace it with"),
newString: z
.string()
.describe(
"The text to replace it with (must be different from old_string)",
),
replaceAll: z
.boolean()
.optional()
.describe("Replace all occurences of old_string (default false)"),
}),
async execute(params, ctx) {
if (!params.filePath) {
throw new Error("filePath is required")
}
let filePath = params.filePath
if (!path.isAbsolute(filePath)) {
filePath = path.join(process.cwd(), filePath)
}
const app = App.info()
const filepath = path.isAbsolute(params.filePath)
? params.filePath
: path.join(app.path.cwd, params.filePath)
await Permission.ask({
id: "opencode.edit",
id: "edit",
sessionID: ctx.sessionID,
title: "Edit this file: " + filePath,
title: "Edit this file: " + filepath,
metadata: {
filePath,
filePath: filepath,
oldString: params.oldString,
newString: params.newString,
},
@@ -88,55 +50,55 @@ export const EditTool = Tool.define({
await (async () => {
if (params.oldString === "") {
contentNew = params.newString
await Bun.write(filePath, params.newString)
await Bun.write(filepath, params.newString)
return
}
const read = FileTimes.get(ctx.sessionID, filePath)
if (!read)
throw new Error(
`You must read the file ${filePath} before editing it. Use the View tool first`,
)
const file = Bun.file(filePath)
if (!(await file.exists())) throw new Error(`File ${filePath} not found`)
const file = Bun.file(filepath)
if (!(await file.exists())) throw new Error(`File ${filepath} not found`)
const stats = await file.stat()
if (stats.isDirectory())
throw new Error(`Path is a directory, not a file: ${filePath}`)
if (stats.mtime.getTime() > read.getTime())
throw new Error(
`File ${filePath} has been modified since it was last read.\nLast modification: ${read.toISOString()}\nLast read: ${stats.mtime.toISOString()}\n\nPlease read the file again before modifying it.`,
)
throw new Error(`Path is a directory, not a file: ${filepath}`)
await FileTimes.assert(ctx.sessionID, filepath)
contentOld = await file.text()
const index = contentOld.indexOf(params.oldString)
if (index === -1)
throw new Error(
`oldString not found in file. Make sure it matches exactly, including whitespace and line breaks`,
)
const lastIndex = contentOld.lastIndexOf(params.oldString)
if (index !== lastIndex)
throw new Error(
`oldString appears multiple times in the file. Please provide more context to ensure a unique match`,
)
contentNew =
contentOld.substring(0, index) +
params.newString +
contentOld.substring(index + params.oldString.length)
if (params.replaceAll) {
contentNew = contentOld.replaceAll(params.oldString, params.newString)
}
if (!params.replaceAll) {
const lastIndex = contentOld.lastIndexOf(params.oldString)
if (index !== lastIndex)
throw new Error(
`oldString appears multiple times in the file. Please provide more context to ensure a unique match`,
)
contentNew =
contentOld.substring(0, index) +
params.newString +
contentOld.substring(index + params.oldString.length)
}
await file.write(contentNew)
})()
const changes = diffLines(contentOld, contentNew)
const diff = trimDiff(
createTwoFilesPatch(filepath, filepath, contentOld, contentNew),
)
FileTimes.read(ctx.sessionID, filePath)
FileTimes.read(ctx.sessionID, filepath)
let output = ""
await LSP.file(filePath)
await LSP.touchFile(filepath, true)
const diagnostics = await LSP.diagnostics()
for (const [file, issues] of Object.entries(diagnostics)) {
if (issues.length === 0) continue
if (file === filePath) {
if (file === filepath) {
output += `\nThis file has errors, please fix\n<file_diagnostics>\n${issues.map(LSP.Diagnostic.pretty).join("\n")}\n</file_diagnostics>\n`
continue
}
@@ -146,9 +108,46 @@ export const EditTool = Tool.define({
return {
metadata: {
diagnostics,
changes,
diff,
title: `${path.relative(app.path.root, filepath)}`,
},
output,
}
},
})
function trimDiff(diff: string): string {
const lines = diff.split("\n")
const contentLines = lines.filter(
(line) =>
(line.startsWith("+") || line.startsWith("-") || line.startsWith(" ")) &&
!line.startsWith("---") &&
!line.startsWith("+++"),
)
if (contentLines.length === 0) return diff
let min = Infinity
for (const line of contentLines) {
const content = line.slice(1)
if (content.trim().length > 0) {
const match = content.match(/^(\s*)/)
if (match) min = Math.min(min, match[1].length)
}
}
if (min === Infinity || min === 0) return diff
const trimmedLines = lines.map((line) => {
if (
(line.startsWith("+") || line.startsWith("-") || line.startsWith(" ")) &&
!line.startsWith("---") &&
!line.startsWith("+++")
) {
const prefix = line[0]
const content = line.slice(1)
return prefix + content.slice(min)
}
return line
})
return trimmedLines.join("\n")
}

View File

@@ -0,0 +1,9 @@
Performs exact string replacements in files.
Usage:
- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file.
- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.
- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.
- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.
- The edit will FAIL if `old_string` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replace_all` to change every instance of `old_string`.
- Use `replace_all` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.

View File

@@ -1,19 +0,0 @@
import { z } from "zod"
import { Tool } from "./tool"
export const ExampleTool = Tool.define({
id: "opencode.example",
description: "Example tool",
parameters: z.object({
foo: z.string().describe("The foo parameter"),
bar: z.number().describe("The bar parameter"),
}),
async execute() {
return {
metadata: {
lol: "hey",
},
output: "Hello, world!",
}
},
})

View File

@@ -1,133 +0,0 @@
import { z } from "zod"
import { Tool } from "./tool"
import TurndownService from "turndown"
const MAX_RESPONSE_SIZE = 5 * 1024 * 1024 // 5MB
const DEFAULT_TIMEOUT = 30 * 1000 // 30 seconds
const MAX_TIMEOUT = 120 * 1000 // 2 minutes
const DESCRIPTION = `Fetches content from a URL and returns it in the specified format.
WHEN TO USE THIS TOOL:
- Use when you need to download content from a URL
- Helpful for retrieving documentation, API responses, or web content
- Useful for getting external information to assist with tasks
HOW TO USE:
- Provide the URL to fetch content from
- Specify the desired output format (text, markdown, or html)
- Optionally set a timeout for the request
FEATURES:
- Supports three output formats: text, markdown, and html
- Automatically handles HTTP redirects
- Sets reasonable timeouts to prevent hanging
- Validates input parameters before making requests
LIMITATIONS:
- Maximum response size is 5MB
- Only supports HTTP and HTTPS protocols
- Cannot handle authentication or cookies
- Some websites may block automated requests
TIPS:
- Use text format for plain text content or simple API responses
- Use markdown format for content that should be rendered with formatting
- Use html format when you need the raw HTML structure
- Set appropriate timeouts for potentially slow websites`
export const FetchTool = Tool.define({
id: "opencode.fetch",
description: DESCRIPTION,
parameters: z.object({
url: z.string().describe("The URL to fetch content from"),
format: z
.enum(["text", "markdown", "html"])
.describe(
"The format to return the content in (text, markdown, or html)",
),
timeout: z
.number()
.min(0)
.max(MAX_TIMEOUT / 1000)
.describe("Optional timeout in seconds (max 120)")
.optional(),
}),
async execute(params) {
// Validate URL
if (
!params.url.startsWith("http://") &&
!params.url.startsWith("https://")
) {
throw new Error("URL must start with http:// or https://")
}
const timeout = Math.min(
(params.timeout ?? DEFAULT_TIMEOUT / 1000) * 1000,
MAX_TIMEOUT,
)
const controller = new AbortController()
const timeoutId = setTimeout(() => controller.abort(), timeout)
const response = await fetch(params.url, {
signal: controller.signal,
headers: {
"User-Agent": "opencode/1.0",
},
})
clearTimeout(timeoutId)
if (!response.ok) {
throw new Error(`Request failed with status code: ${response.status}`)
}
// Check content length
const contentLength = response.headers.get("content-length")
if (contentLength && parseInt(contentLength) > MAX_RESPONSE_SIZE) {
throw new Error("Response too large (exceeds 5MB limit)")
}
const arrayBuffer = await response.arrayBuffer()
if (arrayBuffer.byteLength > MAX_RESPONSE_SIZE) {
throw new Error("Response too large (exceeds 5MB limit)")
}
const content = new TextDecoder().decode(arrayBuffer)
const contentType = response.headers.get("content-type") || ""
switch (params.format) {
case "text":
if (contentType.includes("text/html")) {
const text = extractTextFromHTML(content)
return { output: text, metadata: {} }
}
return { output: content, metadata: {} }
case "markdown":
if (contentType.includes("text/html")) {
const markdown = convertHTMLToMarkdown(content)
return { output: markdown, metadata: {} }
}
return { output: "```\n" + content + "\n```", metadata: {} }
case "html":
return { output: content, metadata: {} }
default:
return { output: content, metadata: {} }
}
},
})
function extractTextFromHTML(html: string): string {
const doc = new DOMParser().parseFromString(html, "text/html")
const text = doc.body.textContent || doc.body.innerText || ""
return text.replace(/\s+/g, " ").trim()
}
function convertHTMLToMarkdown(html: string): string {
const turndownService = new TurndownService()
return turndownService.turndown(html)
}

View File

@@ -1,72 +1,44 @@
import { z } from "zod"
import path from "path"
import { Tool } from "./tool"
import { App } from "../app/app"
const DESCRIPTION = `Fast file pattern matching tool that finds files by name and pattern, returning matching paths sorted by modification time (newest first).
WHEN TO USE THIS TOOL:
- Use when you need to find files by name patterns or extensions
- Great for finding specific file types across a directory structure
- Useful for discovering files that match certain naming conventions
HOW TO USE:
- Provide a glob pattern to match against file paths
- Optionally specify a starting directory (defaults to current working directory)
- Results are sorted with most recently modified files first
GLOB PATTERN SYNTAX:
- '*' matches any sequence of non-separator characters
- '**' matches any sequence of characters, including separators
- '?' matches any single non-separator character
- '[...]' matches any character in the brackets
- '[!...]' matches any character not in the brackets
COMMON PATTERN EXAMPLES:
- '*.js' - Find all JavaScript files in the current directory
- '**/*.js' - Find all JavaScript files in any subdirectory
- 'src/**/*.{ts,tsx}' - Find all TypeScript files in the src directory
- '*.{html,css,js}' - Find all HTML, CSS, and JS files
LIMITATIONS:
- Results are limited to 100 files (newest first)
- Does not search file contents (use Grep tool for that)
- Hidden files (starting with '.') are skipped
TIPS:
- For the most useful results, combine with the Grep tool: first find files with Glob, then search their contents with Grep
- When doing iterative exploration that may require multiple rounds of searching, consider using the Agent tool instead
- Always check if results are truncated and refine your search pattern if needed`
import DESCRIPTION from "./glob.txt"
export const GlobTool = Tool.define({
id: "opencode.glob",
id: "glob",
description: DESCRIPTION,
parameters: z.object({
pattern: z.string().describe("The glob pattern to match files against"),
path: z
.string()
.optional()
.describe(
"The directory to search in. Defaults to the current working directory.",
)
.optional(),
`The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter "undefined" or "null" - simply omit it for the default behavior. Must be a valid directory path if provided.`,
),
}),
async execute(params) {
const app = App.info()
const search = params.path || app.path.cwd
let search = params.path ?? app.path.cwd
search = path.isAbsolute(search)
? search
: path.resolve(app.path.cwd, search)
const limit = 100
const glob = new Bun.Glob(params.pattern)
const files = []
let truncated = false
for await (const file of glob.scan({ cwd: search })) {
for await (const file of glob.scan({ cwd: search, dot: true })) {
if (files.length >= limit) {
truncated = true
break
}
const stats = await Bun.file(file)
const full = path.resolve(search, file)
const stats = await Bun.file(full)
.stat()
.then((x) => x.mtime.getTime())
.catch(() => 0)
files.push({
path: file,
path: full,
mtime: stats,
})
}
@@ -88,6 +60,7 @@ export const GlobTool = Tool.define({
metadata: {
count: files.length,
truncated,
title: path.relative(app.path.root, search),
},
output: output.join("\n"),
}

View File

@@ -0,0 +1,6 @@
- Fast file pattern matching tool that works with any codebase size
- Supports glob patterns like "**/*.js" or "src/**/*.ts"
- Returns matching file paths sorted by modification time
- Use this tool when you need to find files by name patterns
- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead
- You have the capability to call multiple tools in a single response. It is always better to speculatively perform multiple searches as a batch that are potentially useful.

View File

@@ -1,262 +1,12 @@
import { z } from "zod"
import { Tool } from "./tool"
import { App } from "../app/app"
import { spawn } from "child_process"
import { promises as fs } from "fs"
import path from "path"
import { Ripgrep } from "../external/ripgrep"
const DESCRIPTION = `Fast content search tool that finds files containing specific text or patterns, returning matching file paths sorted by modification time (newest first).
WHEN TO USE THIS TOOL:
- Use when you need to find files containing specific text or patterns
- Great for searching code bases for function names, variable declarations, or error messages
- Useful for finding all files that use a particular API or pattern
HOW TO USE:
- Provide a regex pattern to search for within file contents
- Set literal_text=true if you want to search for the exact text with special characters (recommended for non-regex users)
- Optionally specify a starting directory (defaults to current working directory)
- Optionally provide an include pattern to filter which files to search
- Results are sorted with most recently modified files first
REGEX PATTERN SYNTAX (when literal_text=false):
- Supports standard regular expression syntax
- 'function' searches for the literal text "function"
- 'log\\..*Error' finds text starting with "log." and ending with "Error"
- 'import\\s+.*\\s+from' finds import statements in JavaScript/TypeScript
COMMON INCLUDE PATTERN EXAMPLES:
- '*.js' - Only search JavaScript files
- '*.{ts,tsx}' - Only search TypeScript files
- '*.go' - Only search Go files
LIMITATIONS:
- Results are limited to 100 files (newest first)
- Performance depends on the number of files being searched
- Very large binary files may be skipped
- Hidden files (starting with '.') are skipped
TIPS:
- For faster, more targeted searches, first use Glob to find relevant files, then use Grep
- When doing iterative exploration that may require multiple rounds of searching, consider using the Agent tool instead
- Always check if results are truncated and refine your search pattern if needed
- Use literal_text=true when searching for exact text containing special characters like dots, parentheses, etc.`
interface GrepMatch {
path: string
modTime: number
lineNum: number
lineText: string
}
function escapeRegexPattern(pattern: string): string {
const specialChars = [
"\\",
".",
"+",
"*",
"?",
"(",
")",
"[",
"]",
"{",
"}",
"^",
"$",
"|",
]
let escaped = pattern
for (const char of specialChars) {
escaped = escaped.replaceAll(char, "\\" + char)
}
return escaped
}
function globToRegex(glob: string): string {
let regexPattern = glob.replaceAll(".", "\\.")
regexPattern = regexPattern.replaceAll("*", ".*")
regexPattern = regexPattern.replaceAll("?", ".")
// Handle {a,b,c} patterns
regexPattern = regexPattern.replace(/\{([^}]+)\}/g, (_, inner) => {
return "(" + inner.replace(/,/g, "|") + ")"
})
return regexPattern
}
async function searchWithRipgrep(
pattern: string,
searchPath: string,
include?: string,
): Promise<GrepMatch[]> {
return new Promise((resolve, reject) => {
const args = ["-n", pattern]
if (include) {
args.push("--glob", include)
}
args.push(searchPath)
const rg = spawn("rg", args)
let output = ""
let errorOutput = ""
rg.stdout.on("data", (data) => {
output += data.toString()
})
rg.stderr.on("data", (data) => {
errorOutput += data.toString()
})
rg.on("close", async (code) => {
if (code === 1) {
// No matches found
resolve([])
return
}
if (code !== 0) {
reject(new Error(`ripgrep failed: ${errorOutput}`))
return
}
const lines = output.trim().split("\n")
const matches: GrepMatch[] = []
for (const line of lines) {
if (!line) continue
// Parse ripgrep output format: file:line:content
const parts = line.split(":", 3)
if (parts.length < 3) continue
const filePath = parts[0]
const lineNum = parseInt(parts[1], 10)
const lineText = parts[2]
try {
const stats = await fs.stat(filePath)
matches.push({
path: filePath,
modTime: stats.mtime.getTime(),
lineNum,
lineText,
})
} catch {
// Skip files we can't access
continue
}
}
resolve(matches)
})
rg.on("error", (err) => {
reject(err)
})
})
}
async function searchFilesWithRegex(
pattern: string,
rootPath: string,
include?: string,
): Promise<GrepMatch[]> {
const matches: GrepMatch[] = []
const regex = new RegExp(pattern)
let includePattern: RegExp | undefined
if (include) {
const regexPattern = globToRegex(include)
includePattern = new RegExp(regexPattern)
}
async function walkDir(dir: string) {
if (matches.length >= 200) return
try {
const entries = await fs.readdir(dir, { withFileTypes: true })
for (const entry of entries) {
if (matches.length >= 200) break
const fullPath = path.join(dir, entry.name)
if (entry.isDirectory()) {
// Skip hidden directories
if (entry.name.startsWith(".")) continue
await walkDir(fullPath)
} else if (entry.isFile()) {
// Skip hidden files
if (entry.name.startsWith(".")) continue
if (includePattern && !includePattern.test(fullPath)) {
continue
}
try {
const content = await fs.readFile(fullPath, "utf-8")
const lines = content.split("\n")
for (let i = 0; i < lines.length; i++) {
if (regex.test(lines[i])) {
const stats = await fs.stat(fullPath)
matches.push({
path: fullPath,
modTime: stats.mtime.getTime(),
lineNum: i + 1,
lineText: lines[i],
})
break // Only first match per file
}
}
} catch {
// Skip files we can't read
continue
}
}
}
} catch {
// Skip directories we can't read
return
}
}
await walkDir(rootPath)
return matches
}
async function searchFiles(
pattern: string,
rootPath: string,
include?: string,
limit: number = 100,
): Promise<{ matches: GrepMatch[]; truncated: boolean }> {
let matches: GrepMatch[]
try {
matches = await searchWithRipgrep(pattern, rootPath, include)
} catch {
matches = await searchFilesWithRegex(pattern, rootPath, include)
}
// Sort by modification time (newest first)
matches.sort((a, b) => b.modTime - a.modTime)
const truncated = matches.length > limit
if (truncated) {
matches = matches.slice(0, limit)
}
return { matches, truncated }
}
import DESCRIPTION from "./grep.txt"
export const GrepTool = Tool.define({
id: "opencode.grep",
id: "grep",
description: DESCRIPTION,
parameters: z.object({
pattern: z
@@ -264,22 +14,16 @@ export const GrepTool = Tool.define({
.describe("The regex pattern to search for in file contents"),
path: z
.string()
.optional()
.describe(
"The directory to search in. Defaults to the current working directory.",
)
.optional(),
),
include: z
.string()
.optional()
.describe(
'File pattern to include in the search (e.g. "*.js", "*.{ts,tsx}")',
)
.optional(),
literalText: z
.boolean()
.describe(
"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.",
)
.optional(),
),
}),
async execute(params) {
if (!params.pattern) {
@@ -289,56 +33,99 @@ export const GrepTool = Tool.define({
const app = App.info()
const searchPath = params.path || app.path.cwd
// If literalText is true, escape the pattern
const searchPattern = params.literalText
? escapeRegexPattern(params.pattern)
: params.pattern
const rgPath = await Ripgrep.filepath()
const args = ["-n", params.pattern]
if (params.include) {
args.push("--glob", params.include)
}
args.push(searchPath)
const { matches, truncated } = await searchFiles(
searchPattern,
searchPath,
params.include,
100,
)
const proc = Bun.spawn([rgPath, ...args], {
stdout: "pipe",
stderr: "pipe",
})
if (matches.length === 0) {
const output = await new Response(proc.stdout).text()
const errorOutput = await new Response(proc.stderr).text()
const exitCode = await proc.exited
if (exitCode === 1) {
return {
metadata: { matches: 0, truncated },
metadata: { matches: 0, truncated: false, title: params.pattern },
output: "No files found",
}
}
const lines = [`Found ${matches.length} matches`]
if (exitCode !== 0) {
throw new Error(`ripgrep failed: ${errorOutput}`)
}
let currentFile = ""
for (const match of matches) {
if (currentFile !== match.path) {
if (currentFile !== "") {
lines.push("")
}
currentFile = match.path
lines.push(`${match.path}:`)
}
if (match.lineNum > 0) {
lines.push(` Line ${match.lineNum}: ${match.lineText}`)
} else {
lines.push(` ${match.path}`)
const lines = output.trim().split("\n")
const matches = []
for (const line of lines) {
if (!line) continue
const parts = line.split(":", 3)
if (parts.length < 3) continue
const filePath = parts[0]
const lineNum = parseInt(parts[1], 10)
const lineText = parts[2]
const file = Bun.file(filePath)
const stats = await file.stat().catch(() => null)
if (!stats) continue
matches.push({
path: filePath,
modTime: stats.mtime.getTime(),
lineNum,
lineText,
})
}
matches.sort((a, b) => b.modTime - a.modTime)
const limit = 100
const truncated = matches.length > limit
const finalMatches = truncated ? matches.slice(0, limit) : matches
if (finalMatches.length === 0) {
return {
metadata: { matches: 0, truncated: false, title: params.pattern },
output: "No files found",
}
}
const outputLines = [`Found ${finalMatches.length} matches`]
let currentFile = ""
for (const match of finalMatches) {
if (currentFile !== match.path) {
if (currentFile !== "") {
outputLines.push("")
}
currentFile = match.path
outputLines.push(`${match.path}:`)
}
outputLines.push(` Line ${match.lineNum}: ${match.lineText}`)
}
if (truncated) {
lines.push("")
lines.push(
outputLines.push("")
outputLines.push(
"(Results are truncated. Consider using a more specific path or pattern.)",
)
}
return {
metadata: {
matches: matches.length,
matches: finalMatches.length,
truncated,
title: params.pattern,
},
output: lines.join("\n"),
output: outputLines.join("\n"),
}
},
})

View File

@@ -0,0 +1,8 @@
- Fast content search tool that works with any codebase size
- Searches file contents using regular expressions
- Supports full regex syntax (eg. "log.*Error", "function\s+\w+", etc.)
- Filter files by pattern with the include parameter (eg. "*.js", "*.{ts,tsx}")
- Returns file paths with at least one match sorted by modification time
- Use this tool when you need to find files containing specific patterns
- If you need to identify/count the number of matches within files, use the Bash tool with `rg` (ripgrep) directly. Do NOT use `grep`.
- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead

View File

@@ -2,8 +2,9 @@ import { z } from "zod"
import { Tool } from "./tool"
import { App } from "../app/app"
import * as path from "path"
import DESCRIPTION from "./ls.txt"
const IGNORE_PATTERNS = [
export const IGNORE_PATTERNS = [
"node_modules/",
"__pycache__/",
".git/",
@@ -17,12 +18,22 @@ const IGNORE_PATTERNS = [
".vscode/",
]
const LIMIT = 100
export const ListTool = Tool.define({
id: "opencode.list",
description: "List directory contents",
id: "list",
description: DESCRIPTION,
parameters: z.object({
path: z.string().optional(),
ignore: z.array(z.string()).optional(),
path: z
.string()
.describe(
"The absolute path to the directory to list (must be absolute, not relative)",
)
.optional(),
ignore: z
.array(z.string())
.describe("List of glob patterns to ignore")
.optional(),
}),
async execute(params) {
const app = App.info()
@@ -31,13 +42,12 @@ export const ListTool = Tool.define({
const glob = new Bun.Glob("**/*")
const files = []
for await (const file of glob.scan({ cwd: searchPath })) {
if (file.startsWith(".") || IGNORE_PATTERNS.some((p) => file.includes(p)))
continue
for await (const file of glob.scan({ cwd: searchPath, dot: true })) {
if (IGNORE_PATTERNS.some((p) => file.includes(p))) continue
if (params.ignore?.some((pattern) => new Bun.Glob(pattern).match(file)))
continue
files.push(file)
if (files.length >= 1000) break
if (files.length >= LIMIT) break
}
// Build directory structure
@@ -89,7 +99,11 @@ export const ListTool = Tool.define({
const output = `${searchPath}/\n` + renderDir(".", 0)
return {
metadata: { count: files.length, truncated: files.length >= 1000 },
metadata: {
count: files.length,
truncated: files.length >= LIMIT,
title: path.relative(app.path.root, searchPath),
},
output,
}
},

View File

@@ -0,0 +1 @@
Lists files and directories in a given path. The path parameter must be an absolute path, not a relative path. You can optionally provide an array of glob patterns to ignore with the ignore parameter. You should generally prefer the Glob and Grep tools, if you know which directories to search.

View File

@@ -3,33 +3,11 @@ import { Tool } from "./tool"
import path from "path"
import { LSP } from "../lsp"
import { App } from "../app/app"
import DESCRIPTION from "./lsp-diagnostics.txt"
export const LspDiagnosticTool = Tool.define({
id: "opencode.lsp_diagnostics",
description: `Get diagnostics for a file and/or project.
WHEN TO USE THIS TOOL:
- Use when you need to check for errors or warnings in your code
- Helpful for debugging and ensuring code quality
- Good for getting a quick overview of issues in a file or project
HOW TO USE:
- Provide a path to a file to get diagnostics for that file
- Results are displayed in a structured format with severity levels
FEATURES:
- Displays errors, warnings, and hints
- Groups diagnostics by severity
- Provides detailed information about each diagnostic
LIMITATIONS:
- Results are limited to the diagnostics provided by the LSP clients
- May not cover all possible issues in the code
- Does not provide suggestions for fixing issues
TIPS:
- Use in conjunction with other tools for a comprehensive code review
- Combine with the LSP client for real-time diagnostics`,
id: "lsp_diagnostics",
description: DESCRIPTION,
parameters: z.object({
path: z.string().describe("The path to the file to get diagnostics."),
}),
@@ -38,12 +16,13 @@ TIPS:
const normalized = path.isAbsolute(args.path)
? args.path
: path.join(app.path.cwd, args.path)
await LSP.file(normalized)
await LSP.touchFile(normalized, true)
const diagnostics = await LSP.diagnostics()
const file = diagnostics[normalized]
return {
metadata: {
diagnostics,
title: path.relative(app.path.root, normalized),
},
output: file?.length
? file.map(LSP.Diagnostic.pretty).join("\n")

View File

@@ -0,0 +1 @@
do not use

View File

@@ -3,14 +3,11 @@ import { Tool } from "./tool"
import path from "path"
import { LSP } from "../lsp"
import { App } from "../app/app"
import DESCRIPTION from "./lsp-hover.txt"
export const LspHoverTool = Tool.define({
id: "opencode.lsp_hover",
description: `
Looks up hover information for a given position in a source file using the Language Server Protocol (LSP).
This includes type information, documentation, or symbol details at the specified line and character.
Useful for providing code insights, explanations, or context-aware assistance based on the user's current cursor location.
`,
id: "lsp_hover",
description: DESCRIPTION,
parameters: z.object({
file: z.string().describe("The path to the file to get diagnostics."),
line: z.number().describe("The line number to get diagnostics."),
@@ -21,15 +18,21 @@ export const LspHoverTool = Tool.define({
const file = path.isAbsolute(args.file)
? args.file
: path.join(app.path.cwd, args.file)
await LSP.file(file)
await LSP.touchFile(file, true)
const result = await LSP.hover({
...args,
file,
})
console.log(result)
return {
metadata: {
result,
title:
path.relative(app.path.root, file) +
":" +
args.line +
":" +
args.character,
},
output: JSON.stringify(result, null, 2),
}

View File

@@ -0,0 +1 @@
do not use

View File

@@ -0,0 +1,40 @@
import { z } from "zod"
import { Tool } from "./tool"
import { EditTool } from "./edit"
import DESCRIPTION from "./multiedit.txt"
import path from "path"
import { App } from "../app/app"
export const MultiEditTool = Tool.define({
id: "multiedit",
description: DESCRIPTION,
parameters: z.object({
filePath: z.string().describe("The absolute path to the file to modify"),
edits: z
.array(EditTool.parameters)
.describe("Array of edit operations to perform sequentially on the file"),
}),
async execute(params, ctx) {
const results = []
for (const [, edit] of params.edits.entries()) {
const result = await EditTool.execute(
{
filePath: params.filePath,
oldString: edit.oldString,
newString: edit.newString,
replaceAll: edit.replaceAll,
},
ctx,
)
results.push(result)
}
const app = App.info()
return {
metadata: {
results: results.map((r) => r.metadata),
title: path.relative(app.path.root, params.filePath),
},
output: results.at(-1)!.output,
}
},
})

View File

@@ -0,0 +1,41 @@
This is a tool for making multiple edits to a single file in one operation. It is built on top of the Edit tool and allows you to perform multiple find-and-replace operations efficiently. Prefer this tool over the Edit tool when you need to make multiple edits to the same file.
Before using this tool:
1. Use the Read tool to understand the file's contents and context
2. Verify the directory path is correct
To make multiple file edits, provide the following:
1. file_path: The absolute path to the file to modify (must be absolute, not relative)
2. edits: An array of edit operations to perform, where each edit contains:
- old_string: The text to replace (must match the file contents exactly, including all whitespace and indentation)
- new_string: The edited text to replace the old_string
- replace_all: Replace all occurences of old_string. This parameter is optional and defaults to false.
IMPORTANT:
- All edits are applied in sequence, in the order they are provided
- Each edit operates on the result of the previous edit
- All edits must be valid for the operation to succeed - if any edit fails, none will be applied
- This tool is ideal when you need to make several changes to different parts of the same file
CRITICAL REQUIREMENTS:
1. All edits follow the same requirements as the single Edit tool
2. The edits are atomic - either all succeed or none are applied
3. Plan your edits carefully to avoid conflicts between sequential operations
WARNING:
- The tool will fail if edits.old_string doesn't match the file contents exactly (including whitespace)
- The tool will fail if edits.old_string and edits.new_string are the same
- Since edits are applied in sequence, ensure that earlier edits don't affect the text that later edits are trying to find
When making edits:
- Ensure all edits result in idiomatic, correct code
- Do not leave the code in a broken state
- Always use absolute file paths (starting with /)
- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.
- Use replace_all for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.
If you want to create a new file, use:
- A new file path, including dir name if needed
- First edit: empty old_string and the new file's contents as new_string
- Subsequent edits: normal edit operations on the created content

View File

@@ -3,35 +3,7 @@ import * as path from "path"
import * as fs from "fs/promises"
import { Tool } from "./tool"
import { FileTimes } from "./util/file-times"
const DESCRIPTION = `Applies a patch to multiple files in one operation. This tool is useful for making coordinated changes across multiple files.
The patch text must follow this format:
*** Begin Patch
*** Update File: /path/to/file
@@ Context line (unique within the file)
Line to keep
-Line to remove
+Line to add
Line to keep
*** Add File: /path/to/new/file
+Content of the new file
+More content
*** Delete File: /path/to/file/to/delete
*** End Patch
Before using this tool:
1. Use the FileRead tool to understand the files' contents and context
2. Verify all file paths are correct (use the LS tool)
CRITICAL REQUIREMENTS FOR USING THIS TOOL:
1. UNIQUENESS: Context lines MUST uniquely identify the specific sections you want to change
2. PRECISION: All whitespace, indentation, and surrounding code must match exactly
3. VALIDATION: Ensure edits result in idiomatic, correct code
4. PATHS: Always use absolute file paths (starting with /)
The tool will apply all changes in a single atomic operation.`
import DESCRIPTION from "./patch.txt"
const PatchParams = z.object({
patchText: z
@@ -39,12 +11,6 @@ const PatchParams = z.object({
.describe("The full patch text that describes all changes to be made"),
})
interface PatchResponseMetadata {
changed: string[]
additions: number
removals: number
}
interface Change {
type: "add" | "update" | "delete"
old_content?: string
@@ -266,14 +232,10 @@ async function applyCommit(
}
export const PatchTool = Tool.define({
id: "opencode.patch",
id: "patch",
description: DESCRIPTION,
parameters: PatchParams,
execute: async (params, ctx) => {
if (!params.patchText) {
throw new Error("patchText is required")
}
// Identify all files needed for the patch and verify they've been read
const filesToRead = identifyFilesNeeded(params.patchText)
for (const filePath of filesToRead) {
@@ -282,24 +244,13 @@ export const PatchTool = Tool.define({
absPath = path.resolve(process.cwd(), absPath)
}
if (!FileTimes.get(ctx.sessionID, absPath)) {
throw new Error(
`you must read the file ${filePath} before patching it. Use the FileRead tool first`,
)
}
await FileTimes.assert(ctx.sessionID, absPath)
try {
const stats = await fs.stat(absPath)
if (stats.isDirectory()) {
throw new Error(`path is a directory, not a file: ${absPath}`)
}
const lastRead = FileTimes.get(ctx.sessionID, absPath)
if (lastRead && stats.mtime > lastRead) {
throw new Error(
`file ${absPath} has been modified since it was last read (mod time: ${stats.mtime.toISOString()}, last read: ${lastRead.toISOString()})`,
)
}
} catch (error: any) {
if (error.code === "ENOENT") {
throw new Error(`file not found: ${absPath}`)
@@ -411,7 +362,8 @@ export const PatchTool = Tool.define({
changed: changedFiles,
additions: totalAdditions,
removals: totalRemovals,
} satisfies PatchResponseMetadata,
title: `${filesToRead.length} files`,
},
output,
}
},

View File

@@ -0,0 +1 @@
do not use

View File

@@ -4,44 +4,15 @@ import * as path from "path"
import { Tool } from "./tool"
import { LSP } from "../lsp"
import { FileTimes } from "./util/file-times"
import DESCRIPTION from "./read.txt"
import { App } from "../app/app"
const MAX_READ_SIZE = 250 * 1024
const DEFAULT_READ_LIMIT = 2000
const MAX_LINE_LENGTH = 2000
const DESCRIPTION = `File viewing tool that reads and displays the contents of files with line numbers, allowing you to examine code, logs, or text data.
WHEN TO USE THIS TOOL:
- Use when you need to read the contents of a specific file
- Helpful for examining source code, configuration files, or log files
- Perfect for looking at text-based file formats
HOW TO USE:
- Provide the path to the file you want to view
- Optionally specify an offset to start reading from a specific line
- Optionally specify a limit to control how many lines are read
FEATURES:
- Displays file contents with line numbers for easy reference
- Can read from any position in a file using the offset parameter
- Handles large files by limiting the number of lines read
- Automatically truncates very long lines for better display
- Suggests similar file names when the requested file isn't found
LIMITATIONS:
- Maximum file size is 250KB
- Default reading limit is 2000 lines
- Lines longer than 2000 characters are truncated
- Cannot display binary files or images
- Images can be identified but not displayed
TIPS:
- Use with Glob tool to first find files you want to view
- For code exploration, first use Grep to find relevant files, then View to examine them
- When viewing large files, use the offset parameter to read specific sections`
export const ViewTool = Tool.define({
id: "opencode.view",
export const ReadTool = Tool.define({
id: "read",
description: DESCRIPTION,
parameters: z.object({
filePath: z.string().describe("The path to the file to read"),
@@ -118,13 +89,14 @@ export const ViewTool = Tool.define({
output += "\n</file>"
// just warms the lsp client
LSP.file(filePath)
await LSP.touchFile(filePath, true)
FileTimes.read(ctx.sessionID, filePath)
return {
output,
metadata: {
preview,
title: path.relative(App.info().path.root, filePath),
},
}
},

View File

@@ -0,0 +1,13 @@
Reads a file from the local filesystem. You can access any file directly by using this tool.
Assume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.
Usage:
- The file_path parameter must be an absolute path, not a relative path
- By default, it reads up to 2000 lines starting from the beginning of the file
- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters
- Any lines longer than 2000 characters will be truncated
- Results are returned using cat -n format, with line numbers starting at 1
- This tool allows OpenCode to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as OpenCode is a multimodal LLM.
- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful.
- You will regularly be asked to read screenshots. If the user provides a path to a screenshot ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths like /var/folders/123/abc/T/TemporaryItems/NSIRD_screencaptureui_ZfB1tD/Screenshot.png
- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.

View File

@@ -0,0 +1,64 @@
import { Tool } from "./tool"
import DESCRIPTION from "./task.txt"
import { z } from "zod"
import { Session } from "../session"
import { Bus } from "../bus"
import { Message } from "../session/message"
export const TaskTool = Tool.define({
id: "task",
description: DESCRIPTION,
parameters: z.object({
description: z
.string()
.describe("A short (3-5 words) description of the task"),
prompt: z.string().describe("The task for the agent to perform"),
}),
async execute(params, ctx) {
const session = await Session.create(ctx.sessionID)
const msg = await Session.getMessage(ctx.sessionID, ctx.messageID)
const metadata = msg.metadata.assistant!
function summary(input: Message.Info) {
const result = []
for (const part of input.parts) {
if (part.type === "tool-invocation") {
result.push({
toolInvocation: part.toolInvocation,
metadata: input.metadata.tool[part.toolInvocation.toolCallId],
})
}
}
return result
}
const unsub = Bus.subscribe(Message.Event.Updated, async (evt) => {
if (evt.properties.info.metadata.sessionID !== ctx.sessionID) return
ctx.metadata({
title: params.description,
summary: summary(evt.properties.info),
})
})
const result = await Session.chat({
sessionID: session.id,
modelID: metadata.modelID,
providerID: metadata.providerID,
parts: [
{
type: "text",
text: params.prompt,
},
],
})
unsub()
return {
metadata: {
title: params.description,
summary: summary(result),
},
output: result.parts.findLast((x) => x.type === "text")!.text,
}
},
})

View File

@@ -0,0 +1,16 @@
Launch a new agent that has access to the following tools: Bash, Glob, Grep, LS, Read, Edit, MultiEdit, Write, NotebookRead, NotebookEdit, WebFetch, TodoRead, TodoWrite, WebSearch. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use the Agent tool to perform the search for you.
When to use the Agent tool:
- If you are searching for a keyword like "config" or "logger", or for questions like "which file does X?", the Agent tool is strongly recommended
When NOT to use the Agent tool:
- If you want to read a specific file path, use the Read or Glob tool instead of the Agent tool, to find the match more quickly
- If you are searching for a specific class definition like "class Foo", use the Glob tool instead, to find the match more quickly
- If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Agent tool, to find the match more quickly
Usage notes:
1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses
2. When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.
3. Each agent invocation is stateless. You will not be able to send additional messages to the agent, nor will the agent be able to communicate with you outside of its final report. Therefore, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.
4. The agent's outputs should generally be trusted
5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent

View File

@@ -0,0 +1,58 @@
import { z } from "zod"
import { Tool } from "./tool"
import DESCRIPTION_WRITE from "./todowrite.txt"
import { App } from "../app/app"
const TodoInfo = z.object({
content: z.string().min(1).describe("Brief description of the task"),
status: z
.enum(["pending", "in_progress", "completed"])
.describe("Current status of the task"),
priority: z
.enum(["high", "medium", "low"])
.describe("Priority level of the task"),
id: z.string().describe("Unique identifier for the todo item"),
})
type TodoInfo = z.infer<typeof TodoInfo>
const state = App.state("todo-tool", () => {
const todos: {
[sessionId: string]: TodoInfo[]
} = {}
return todos
})
export const TodoWriteTool = Tool.define({
id: "todowrite",
description: DESCRIPTION_WRITE,
parameters: z.object({
todos: z.array(TodoInfo).describe("The updated todo list"),
}),
async execute(params, opts) {
const todos = state()
todos[opts.sessionID] = params.todos
return {
output: JSON.stringify(params.todos, null, 2),
metadata: {
title: `${params.todos.filter((x) => x.status !== "completed").length} todos`,
todos: params.todos,
},
}
},
})
export const TodoReadTool = Tool.define({
id: "todoread",
description: "Use this tool to read your todo list",
parameters: z.object({}),
async execute(_params, opts) {
const todos = state()[opts.sessionID] ?? []
return {
metadata: {
todos,
title: `${todos.filter((x) => x.status !== "completed").length} todos`,
},
output: JSON.stringify(todos, null, 2),
}
},
})

View File

@@ -0,0 +1,14 @@
Use this tool to read the current to-do list for the session. This tool should be used proactively and frequently to ensure that you are aware of
the status of the current task list. You should make use of this tool as often as possible, especially in the following situations:
- At the beginning of conversations to see what's pending
- Before starting new tasks to prioritize work
- When the user asks about previous tasks or plans
- Whenever you're uncertain about what to do next
- After completing tasks to update your understanding of remaining work
- After every few messages to ensure you're on track
Usage:
- This tool takes in no parameters. So leave the input blank or empty. DO NOT include a dummy object, placeholder string or a key like "input" or "empty". LEAVE IT BLANK.
- Returns a list of todo items with their status, priority, and content
- Use this information to track progress and plan next steps
- If no todos exist yet, an empty list will be returned

View File

@@ -0,0 +1,167 @@
Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.
It also helps the user understand the progress of the task and overall progress of their requests.
## When to Use This Tool
Use this tool proactively in these scenarios:
1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions
2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations
3. User explicitly requests todo list - When the user directly asks you to use the todo list
4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)
5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.
6. After completing a task - Mark it complete and add any new follow-up tasks
7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.
## When NOT to Use This Tool
Skip using this tool when:
1. There is only a single, straightforward task
2. The task is trivial and tracking it provides no organizational benefit
3. The task can be completed in less than 3 trivial steps
4. The task is purely conversational or informational
NOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.
## Examples of When to Use the Todo List
<example>
User: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!
Assistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.
*Creates todo list with the following items:*
1. Create dark mode toggle component in Settings page
2. Add dark mode state management (context/store)
3. Implement CSS-in-JS styles for dark theme
4. Update existing components to support theme switching
5. Run tests and build process, addressing any failures or errors that occur
*Begins working on the first task*
<reasoning>
The assistant used the todo list because:
1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes
2. The user explicitly requested tests and build be run afterward
3. The assistant inferred that tests and build need to pass by adding "Ensure tests and build succeed" as the final task
</reasoning>
</example>
<example>
User: Help me rename the function getCwd to getCurrentWorkingDirectory across my project
Assistant: Let me first search through your codebase to find all occurrences of 'getCwd'.
*Uses grep or search tools to locate all instances of getCwd in the codebase*
Assistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.
*Creates todo list with specific items for each file that needs updating*
<reasoning>
The assistant used the todo list because:
1. First, the assistant searched to understand the scope of the task
2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps
3. The todo list helps ensure every instance is tracked and updated systematically
4. This approach prevents missing any occurrences and maintains code consistency
</reasoning>
</example>
<example>
User: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.
Assistant: I'll help implement these features. First, let's add all the features to the todo list.
*Creates a todo list breaking down each feature into specific tasks based on the project architecture*
Assistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.
<reasoning>
The assistant used the todo list because:
1. The user provided multiple complex features to implement in a comma separated list
2. The todo list helps organize these large features into manageable tasks
3. This approach allows for tracking progress across the entire implementation
</reasoning>
</example>
<example>
User: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>
Assistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.
*Reviews component structure, render patterns, state management, and data fetching*
Assistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.
*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*
Let's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>
<reasoning>
The assistant used the todo list because:
1. First, the assistant examined the codebase to identify specific performance issues
2. Based on this analysis, it identified multiple optimization opportunities
3. Performance optimization is a non-trivial task requiring multiple steps
4. The todo list helps methodically track improvements across different components
5. This systematic approach ensures all performance bottlenecks are addressed
</reasoning>
</example>
## Examples of When NOT to Use the Todo List
<example>
User: How do I print 'Hello World' in Python?
Assistant: In Python, you can print "Hello World" with this simple code:
python
print("Hello World")
This will output the text "Hello World" to the console when executed.</assistant>
<reasoning>
The assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.
</reasoning>
</example>
<example>
User: What does the git status command do?
Assistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.
<reasoning>
The assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.
</reasoning>
</example>
<example>
User: Can you add a comment to the calculateTotal function to explain what it does?
Assistant: Sure, let me add a comment to the calculateTotal function to explain what it does.
* Uses the Edit tool to add a comment to the calculateTotal function *
<reasoning>
The assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.
</reasoning>
</example>
<example>
User: Run npm install for me and tell me what happens.
Assistant: I'll run the npm install command for you.
*Executes: npm install*
The command completed successfully. Here's the output:
[Output of npm install command]
All dependencies have been installed according to your package.json file.
<reasoning>
The assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.
</reasoning>
</example>
## Task States and Management
1. **Task States**: Use these states to track progress:
- pending: Task not yet started
- in_progress: Currently working on (limit to ONE task at a time)
- completed: Task finished successfully
- cancelled: Task no longer needed
2. **Task Management**:
- Update task status in real-time as you work
- Mark tasks complete IMMEDIATELY after finishing (don't batch completions)
- Only have ONE task in_progress at any time
- Complete current tasks before starting new ones
- Cancel tasks that become irrelevant
3. **Task Breakdown**:
- Create specific, actionable items
- Break complex tasks into smaller, manageable steps
- Use clear, descriptive task names
When in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.

View File

@@ -1,12 +1,19 @@
import type { StandardSchemaV1 } from "@standard-schema/spec"
export namespace Tool {
export type Context = {
interface Metadata {
title: string
[key: string]: any
}
export type Context<M extends Metadata = Metadata> = {
sessionID: string
messageID: string
abort: AbortSignal
metadata(meta: M): void
}
export interface Info<
Parameters extends StandardSchemaV1 = StandardSchemaV1,
Metadata extends Record<string, any> = Record<string, any>,
M extends Metadata = Metadata,
> {
id: string
description: string
@@ -15,14 +22,14 @@ export namespace Tool {
args: StandardSchemaV1.InferOutput<Parameters>,
ctx: Context,
): Promise<{
metadata: Metadata
metadata: M
output: string
}>
}
export function define<
Parameters extends StandardSchemaV1,
Result extends Record<string, any>,
Result extends Metadata,
>(input: Info<Parameters, Result>): Info<Parameters, Result> {
return input
}

View File

@@ -21,4 +21,18 @@ export namespace FileTimes {
export function get(sessionID: string, file: string) {
return state().read[sessionID]?.[file]
}
export async function assert(sessionID: string, filepath: string) {
const time = get(sessionID, filepath)
if (!time)
throw new Error(
`You must read the file ${filepath} before overwriting it. Use the Read tool first`,
)
const stats = await Bun.file(filepath).stat()
if (stats.mtime.getTime() > time.getTime()) {
throw new Error(
`File ${filepath} has been modified since it was last read.\nLast modification: ${stats.mtime.toISOString()}\nLast read: ${time.toISOString()}\n\nPlease read the file again before modifying it.`,
)
}
}
}

View File

@@ -0,0 +1,181 @@
import { z } from "zod"
import { Tool } from "./tool"
import TurndownService from "turndown"
import DESCRIPTION from "./webfetch.txt"
const MAX_RESPONSE_SIZE = 5 * 1024 * 1024 // 5MB
const DEFAULT_TIMEOUT = 30 * 1000 // 30 seconds
const MAX_TIMEOUT = 120 * 1000 // 2 minutes
export const WebFetchTool = Tool.define({
id: "webfetch",
description: DESCRIPTION,
parameters: z.object({
url: z.string().describe("The URL to fetch content from"),
format: z
.enum(["text", "markdown", "html"])
.describe(
"The format to return the content in (text, markdown, or html)",
),
timeout: z
.number()
.min(0)
.max(MAX_TIMEOUT / 1000)
.describe("Optional timeout in seconds (max 120)")
.optional(),
}),
async execute(params, ctx) {
// Validate URL
if (
!params.url.startsWith("http://") &&
!params.url.startsWith("https://")
) {
throw new Error("URL must start with http:// or https://")
}
const timeout = Math.min(
(params.timeout ?? DEFAULT_TIMEOUT / 1000) * 1000,
MAX_TIMEOUT,
)
const controller = new AbortController()
const timeoutId = setTimeout(() => controller.abort(), timeout)
const response = await fetch(params.url, {
signal: AbortSignal.any([controller.signal, ctx.abort]),
headers: {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
Accept:
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "en-US,en;q=0.9",
},
})
clearTimeout(timeoutId)
if (!response.ok) {
throw new Error(`Request failed with status code: ${response.status}`)
}
// Check content length
const contentLength = response.headers.get("content-length")
if (contentLength && parseInt(contentLength) > MAX_RESPONSE_SIZE) {
throw new Error("Response too large (exceeds 5MB limit)")
}
const arrayBuffer = await response.arrayBuffer()
if (arrayBuffer.byteLength > MAX_RESPONSE_SIZE) {
throw new Error("Response too large (exceeds 5MB limit)")
}
const content = new TextDecoder().decode(arrayBuffer)
const contentType = response.headers.get("content-type") || ""
const title = `${params.url} (${contentType})`
switch (params.format) {
case "text":
if (contentType.includes("text/html")) {
const text = await extractTextFromHTML(content)
return {
output: text,
metadata: {
title,
},
}
}
return {
output: content,
metadata: {
title,
},
}
case "markdown":
if (contentType.includes("text/html")) {
const markdown = convertHTMLToMarkdown(content)
return {
output: markdown,
metadata: {
title,
},
}
}
return {
output: "```\n" + content + "\n```",
metadata: {
title,
},
}
case "html":
return {
output: content,
metadata: {
title,
},
}
default:
return {
output: content,
metadata: {
title,
},
}
}
},
})
async function extractTextFromHTML(html: string) {
let text = ""
let skipContent = false
const rewriter = new HTMLRewriter()
.on("script, style, noscript, iframe, object, embed", {
element() {
skipContent = true
},
text() {
// Skip text content inside these elements
},
})
.on("*", {
element(element) {
// Reset skip flag when entering other elements
if (
![
"script",
"style",
"noscript",
"iframe",
"object",
"embed",
].includes(element.tagName)
) {
skipContent = false
}
},
text(input) {
if (!skipContent) {
text += input.text
}
},
})
.transform(new Response(html))
await rewriter.text()
return text.trim()
}
function convertHTMLToMarkdown(html: string): string {
const turndownService = new TurndownService({
headingStyle: "atx",
hr: "---",
bulletListMarker: "-",
codeBlockStyle: "fenced",
emDelimiter: "*",
})
turndownService.remove(["script", "style", "meta", "link"])
return turndownService.turndown(html)
}

View File

@@ -0,0 +1,14 @@
- Fetches content from a specified URL
- Takes a URL and a prompt as input
- Fetches the URL content, converts HTML to markdown
- Returns the model's response about the content
- Use this tool when you need to retrieve and analyze web content
Usage notes:
- IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with "mcp__".
- The URL must be a fully-formed valid URL
- HTTP URLs will be automatically upgraded to HTTPS
- The prompt should describe what information you want to extract from the page
- This tool is read-only and does not modify any files
- Results may be summarized if the content is very large
- Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL

View File

@@ -0,0 +1,11 @@
- Allows OpenCode to search the web and use the results to inform responses
- Provides up-to-date information for current events and recent data
- Returns search result information formatted as search result blocks
- Use this tool for accessing information beyond Claude's knowledge cutoff
- Searches are performed automatically within a single API call
Usage notes:
- Domain filtering is supported to include or block specific websites
- Web search is only available in the US

View File

@@ -0,0 +1,69 @@
import { z } from "zod"
import * as path from "path"
import { Tool } from "./tool"
import { FileTimes } from "./util/file-times"
import { LSP } from "../lsp"
import { Permission } from "../permission"
import DESCRIPTION from "./write.txt"
import { App } from "../app/app"
export const WriteTool = Tool.define({
id: "write",
description: DESCRIPTION,
parameters: z.object({
filePath: z
.string()
.describe(
"The absolute path to the file to write (must be absolute, not relative)",
),
content: z.string().describe("The content to write to the file"),
}),
async execute(params, ctx) {
const app = App.info()
const filepath = path.isAbsolute(params.filePath)
? params.filePath
: path.join(app.path.cwd, params.filePath)
const file = Bun.file(filepath)
const exists = await file.exists()
if (exists) await FileTimes.assert(ctx.sessionID, filepath)
await Permission.ask({
id: "write",
sessionID: ctx.sessionID,
title: exists
? "Overwrite this file: " + filepath
: "Create new file: " + filepath,
metadata: {
filePath: filepath,
content: params.content,
exists,
},
})
await Bun.write(filepath, params.content)
FileTimes.read(ctx.sessionID, filepath)
let output = ""
await LSP.touchFile(filepath, true)
const diagnostics = await LSP.diagnostics()
for (const [file, issues] of Object.entries(diagnostics)) {
if (issues.length === 0) continue
if (file === filepath) {
output += `\nThis file has errors, please fix\n<file_diagnostics>\n${issues.map(LSP.Diagnostic.pretty).join("\n")}\n</file_diagnostics>\n`
continue
}
output += `\n<project_diagnostics>\n${file}\n${issues.map(LSP.Diagnostic.pretty).join("\n")}\n</project_diagnostics>\n`
}
return {
metadata: {
diagnostics,
filepath,
exists: exists,
title: path.relative(app.path.root, filepath),
},
output,
}
},
})

View File

@@ -0,0 +1,8 @@
Writes a file to the local filesystem.
Usage:
- This tool will overwrite the existing file if there is one at the provided path.
- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.
- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.
- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.
- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.

View File

@@ -0,0 +1,64 @@
import { z, type ZodSchema } from "zod"
import { Log } from "./log"
const log = Log.create()
export abstract class NamedError extends Error {
abstract schema(): ZodSchema
abstract toObject(): { name: string; data: any }
static create<Name extends string, Data extends ZodSchema>(
name: Name,
data: Data,
) {
const schema = z
.object({
name: z.literal(name),
data,
})
.openapi({
ref: name,
})
const result = class extends NamedError {
public static readonly Schema = schema
public readonly name = name as Name
constructor(
public readonly data: z.input<Data>,
options?: ErrorOptions,
) {
super(name, options)
this.name = name
log.error(name, {
...this.data,
cause: options?.cause?.toString(),
})
}
static isInstance(input: any): input is InstanceType<typeof result> {
return "name" in input && input.name === name
}
schema() {
return schema
}
toObject() {
return {
name: name,
data: this.data,
}
}
}
Object.defineProperty(result, "name", { value: name })
return result
}
public static readonly Unknown = NamedError.create(
"UnknownError",
z.object({
message: z.string(),
}),
)
}

View File

@@ -2,17 +2,17 @@ import { exists } from "fs/promises"
import { dirname, join } from "path"
export namespace Filesystem {
export async function findUp(target: string, start: string) {
let currentDir = start
export async function findUp(target: string, start: string, stop?: string) {
let current = start
const result = []
while (true) {
const targetPath = join(currentDir, target)
if (await exists(targetPath)) return targetPath
const parentDir = dirname(currentDir)
if (parentDir === currentDir) {
return
}
currentDir = parentDir
const search = join(current, target)
if (await exists(search)) result.push(search)
if (stop === current) break
const parent = dirname(current)
if (parent === current) break
current = parent
}
return result
}
}

View File

@@ -0,0 +1,11 @@
export function lazy<T>(fn: () => T) {
let value: T | undefined
let loaded = false
return (): T => {
if (loaded) return value as T
value = fn()
return value as T
}
}

View File

@@ -1,35 +1,51 @@
import path from "path"
import fs from "fs/promises"
import { Global } from "../global"
export namespace Log {
const write = {
out: (msg: string) => {
process.stdout.write(msg)
},
err: (msg: string) => {
process.stderr.write(msg)
},
export const Default = create({ service: "default" })
export interface Options {
print: boolean
}
export async function file(directory: string) {
await fs.mkdir(directory, { recursive: true })
const outPath = path.join(directory, "opencode.out.log")
const errPath = path.join(directory, "opencode.err.log")
await fs.truncate(outPath).catch(() => {})
await fs.truncate(errPath).catch(() => {})
const out = Bun.file(outPath)
const err = Bun.file(errPath)
const outWriter = out.writer()
const errWriter = err.writer()
write["out"] = (msg) => {
outWriter.write(msg)
outWriter.flush()
}
write["err"] = (msg) => {
errWriter.write(msg)
errWriter.flush()
let logpath = ""
export function file() {
return logpath
}
export async function init(options: Options) {
const dir = path.join(Global.Path.data, "log")
await fs.mkdir(dir, { recursive: true })
cleanup(dir)
if (options.print) return
logpath = path.join(dir, new Date().toISOString().split(".")[0] + ".log")
const logfile = Bun.file(logpath)
await fs.truncate(logpath).catch(() => {})
const writer = logfile.writer()
process.stderr.write = (msg) => {
writer.write(msg)
writer.flush()
return true
}
}
async function cleanup(dir: string) {
const entries = await fs.readdir(dir, { withFileTypes: true })
const files = entries
.filter((entry) => entry.isFile() && entry.name.endsWith(".log"))
.map((entry) => path.join(dir, entry.name))
if (files.length <= 5) return
const filesToDelete = files.slice(0, -10)
await Promise.all(
filesToDelete.map((file) => fs.unlink(file).catch(() => {})),
)
}
let last = Date.now()
export function create(tags?: Record<string, any>) {
tags = tags || {}
@@ -41,20 +57,24 @@ export namespace Log {
.filter(([_, value]) => value !== undefined && value !== null)
.map(([key, value]) => `${key}=${value}`)
.join(" ")
const next = new Date()
const diff = next.getTime() - last
last = next.getTime()
return (
[new Date().toISOString(), prefix, message].filter(Boolean).join(" ") +
"\n"
[next.toISOString().split(".")[0], "+" + diff + "ms", prefix, message]
.filter(Boolean)
.join(" ") + "\n"
)
}
const result = {
info(message?: any, extra?: Record<string, any>) {
write.out(build(message, extra))
process.stderr.write(build(message, extra))
},
error(message?: any, extra?: Record<string, any>) {
write.err(build(message, extra))
process.stderr.write(build(message, extra))
},
warn(message?: any, extra?: Record<string, any>) {
write.err(build(message, extra))
process.stderr.write(build(message, extra))
},
tag(key: string, value: string) {
if (tags) tags[key] = value
@@ -63,6 +83,23 @@ export namespace Log {
clone() {
return Log.create({ ...tags })
},
time(message: string, extra?: Record<string, any>) {
const now = Date.now()
result.info(message, { status: "started", ...extra })
function stop() {
result.info(message, {
status: "completed",
duration: Date.now() - now,
...extra,
})
}
return {
stop,
[Symbol.dispose]() {
stop()
},
}
},
}
return result

Some files were not shown because too many files have changed in this diff Show More