feat: Add support for OpenRouter (#92 )

* Add support for OpenRouter as a new model provider - Introduced `ProviderOpenRouter` in the `models` package. - Added OpenRouter-specific models, including `GPT41`, `GPT41Mini`, `GPT4o`, and others, with their configurations and costs. - Updated `generateSchema` to include OpenRouter as a provider. - Added OpenRouter-specific environment variable handling (`OPENROUTER_API_KEY`) in `config.go`. - Implemented default model settings for OpenRouter agents in `setDefaultModelForAgent`. - Updated `getProviderAPIKey` to retrieve the OpenRouter API key. - Extended `SupportedModels` to include OpenRouter models. - Added OpenRouter client initialization in the `provider` package. - Modified `processGeneration` to handle `FinishReasonUnknown` in addition to `FinishReasonToolUse`. * [feature/openrouter-provider] Add new models and provider to schema - Added "deepseek-chat-free" and "deepseek-r1-free" to the list of supported models in `opencode-schema.json`. * [feature/openrouter-provider] Add OpenRouter provider support and integrate new models - Updated README.md to include OpenRouter as a supported provider and its configuration details. - Added `OPENROUTER_API_KEY` to environment variable configuration. - Introduced OpenRouter-specific models in `internal/llm/models/openrouter.go` with mappings to existing cost and token configurations. - Updated `internal/config/config.go` to set default models for OpenRouter agents. - Extended `opencode-schema.json` to include OpenRouter models in the schema definitions. - Refactored model IDs and names to align with OpenRouter naming conventions. * [feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider - Simplified finish reason check in `agent.go` by removing redundant variable assignment. - Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present. - Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider. [feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider - Simplified finish reason check in `agent.go` by removing redundant variable assignment. - Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present. - Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider. * **[feature/openrouter-provider] Add support for custom headers in OpenAI client configuration** - Introduced a new `extraHeaders` field in the `openaiOptions` struct to allow specifying additional HTTP headers. - Added logic in `newOpenAIClient` to apply `extraHeaders` to the OpenAI client configuration. - Implemented a new option function `WithOpenAIExtraHeaders` to set custom headers in `openaiOptions`. - Updated the OpenRouter provider configuration in `NewProvider` to include default headers (`HTTP-Referer` and `X-Title`) for OpenRouter API requests. * Update OpenRouter model config and remove unsupported models * [feature/openrouter-provider] Update OpenRouter models and default configurations - Added new OpenRouter models: `claude-3.5-sonnet`, `claude-3-haiku`, `claude-3.7-sonnet`, `claude-3.5-haiku`, and `claude-3-opus` in `openrouter.go`. - Updated default agent models in `config.go`: - `agents.coder.model` now uses `claude-3.7-sonnet`. - `agents.task.model` now uses `claude-3.7-sonnet`. - `agents.title.model` now uses `claude-3.5-haiku`. - Updated `opencode-schema.json` to include the new models in the allowed list for schema validation. - Adjusted logic in `setDefaultModelForAgent` to reflect the new default models. * [feature/openrouter-provider] Remove unused ProviderEvent emission in stream function The changes remove the emission of a `ProviderEvent` with type `EventContentStop` in the `stream` function of the `openaiClient` implementation. This event was sent upon successful stream completion but is no longer used.
fix diagnostics for deleted files
2026-05-02 23:04:07 +08:00 · 2025-04-29 13:56:49 +02:00 · 2025-04-28 19:37:42 +02:00 · 2025-04-28 19:25:06 +02:00 · 2025-04-28 15:42:57 +02:00 · 2025-04-27 20:43:27 +02:00
33 changed files with 1943 additions and 670 deletions
--- a/.goreleaser.yml
+++ b/.goreleaser.yml
@@ -4,7 +4,7 @@ before:
  hooks:
 builds:
  - env:
-      - CGO_ENABLED=1
+      - CGO_ENABLED=0
    goos:
      - linux
      - darwin
@@ -17,7 +17,6 @@ builds:

 archives:
  - format: tar.gz
-    # this name template makes the OS and Arch compatible with the results of uname.
    name_template: >-
      opencode-
      {{- if eq .Os "darwin" }}mac-
@@ -27,7 +26,6 @@ archives:
      {{- else if eq .Arch "#86" }}i386
      {{- else }}{{ .Arch }}{{ end }}
      {{- if .Arm }}v{{ .Arm }}{{ end }}
-    # use zip for windows archives
    format_overrides:
      - goos: windows
        format: zip
--- a/README.md
+++ b/README.md
@@ -11,7 +11,7 @@ OpenCode is a Go-based CLI application that brings AI assistance to your termina
 ## 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, and Groq
+- **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
@@ -22,8 +22,35 @@ OpenCode is a Go-based CLI application that brings AI assistance to your termina

 ## Installation

+### Using the Install Script
+
+```bash
+# Install the latest version
+curl -fsSL https://opencode.ai/install | bash
+
+# Install a specific version
+curl -fsSL https://opencode.ai/install | VERSION=0.1.0 bash
+```
+
+### Using Homebrew (macOS and Linux)
+
+```bash
+brew install opencode-ai/tap/opencode
+```
+
+### Using AUR (Arch Linux)
+
+```bash
+# Using yay
+yay -S opencode-bin
+
+# Using paru
+paru -S opencode-bin
+```
+
+### Using Go
+
 ```bash
-# Coming soon
 go install github.com/opencode-ai/opencode@latest
 ```

@@ -39,15 +66,19 @@ OpenCode looks for configuration in the following locations:

 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 |
-| `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) |
+| Environment Variable       | Purpose                                                |
+|----------------------------|--------------------------------------------------------|
+| `ANTHROPIC_API_KEY`        | For Claude models                                      |
+| `OPENAI_API_KEY`           | For OpenAI models                                      |
+| `GEMINI_API_KEY`           | For Google Gemini models                               |
+| `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

@@ -64,6 +95,14 @@ You can configure OpenCode using environment variables:
    "anthropic": {
      "apiKey": "your-api-key",
      "disabled": false
+    },
+    "groq": {
+      "apiKey": "your-api-key",
+      "disabled": false
+    },
+    "openrouter": {
+      "apiKey": "your-api-key",
+      "disabled": false
    }
  },
  "agents": {
@@ -131,6 +170,23 @@ OpenCode supports a variety of AI models from different providers:

 - 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
+
 ## Usage

 ```bash
@@ -164,6 +220,7 @@ opencode -c /path/to/project
 | `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
@@ -193,6 +250,16 @@ opencode -c /path/to/project
 | `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                       |
--- a/cmd/schema/main.go
+++ b/cmd/schema/main.go
@@ -77,6 +77,27 @@ func generateSchema() map[string]any {
 		"default":     false,
 	}

+	schema["properties"].(map[string]any)["contextPaths"] = map[string]any{
+		"type":        "array",
+		"description": "Context paths for the application",
+		"items": map[string]any{
+			"type": "string",
+		},
+		"default": []string{
+			".github/copilot-instructions.md",
+			".cursorrules",
+			".cursor/rules/",
+			"CLAUDE.md",
+			"CLAUDE.local.md",
+			"opencode.md",
+			"opencode.local.md",
+			"OpenCode.md",
+			"OpenCode.local.md",
+			"OPENCODE.md",
+			"OPENCODE.local.md",
+		},
+	}
+
 	// Add MCP servers
 	schema["properties"].(map[string]any)["mcpServers"] = map[string]any{
 		"type":        "object",
@@ -152,7 +173,9 @@ func generateSchema() map[string]any {
 		string(models.ProviderOpenAI),
 		string(models.ProviderGemini),
 		string(models.ProviderGROQ),
+		string(models.ProviderOpenRouter),
 		string(models.ProviderBedrock),
+		string(models.ProviderAzure),
 	}

 	providerSchema["additionalProperties"].(map[string]any)["properties"].(map[string]any)["provider"] = map[string]any{
@@ -259,4 +282,3 @@ func generateSchema() map[string]any {

 	return schema
 }
-
--- a/go.mod
+++ b/go.mod
@@ -5,10 +5,12 @@ go 1.24.0
 toolchain go1.24.2

 require (
+	github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.7.0
 	github.com/JohannesKaufmann/html-to-markdown v1.6.0
 	github.com/PuerkitoBio/goquery v1.9.2
 	github.com/alecthomas/chroma/v2 v2.15.0
 	github.com/anthropics/anthropic-sdk-go v0.2.0-beta.2
+	github.com/aymanbagabas/go-udiff v0.2.0
 	github.com/bmatcuk/doublestar/v4 v4.8.1
 	github.com/catppuccin/go v0.3.0
 	github.com/charmbracelet/bubbles v0.20.0
@@ -18,19 +20,17 @@ require (
 	github.com/charmbracelet/lipgloss v1.1.0
 	github.com/charmbracelet/x/ansi v0.8.0
 	github.com/fsnotify/fsnotify v1.8.0
-	github.com/go-git/go-git/v5 v5.15.0
 	github.com/go-logfmt/logfmt v0.6.0
-	github.com/golang-migrate/migrate/v4 v4.18.2
 	github.com/google/generative-ai-go v0.19.0
 	github.com/google/uuid v1.6.0
 	github.com/lrstanley/bubblezone v0.0.0-20250315020633-c249a3fe1231
 	github.com/mark3labs/mcp-go v0.17.0
-	github.com/mattn/go-runewidth v0.0.16
-	github.com/mattn/go-sqlite3 v1.14.24
 	github.com/muesli/ansi v0.0.0-20230316100256-276c6243b2f6
 	github.com/muesli/reflow v0.3.0
 	github.com/muesli/termenv v0.16.0
+	github.com/ncruces/go-sqlite3 v0.25.0
 	github.com/openai/openai-go v0.1.0-beta.2
+	github.com/pressly/goose/v3 v3.24.2
 	github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3
 	github.com/spf13/cobra v1.9.1
 	github.com/spf13/viper v1.20.0
@@ -45,9 +45,9 @@ require (
 	cloud.google.com/go/auth/oauth2adapt v0.2.6 // indirect
 	cloud.google.com/go/compute/metadata v0.6.0 // indirect
 	cloud.google.com/go/longrunning v0.5.7 // indirect
-	dario.cat/mergo v1.0.0 // indirect
-	github.com/Microsoft/go-winio v0.6.2 // indirect
-	github.com/ProtonMail/go-crypto v1.1.6 // indirect
+	github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 // indirect
+	github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0 // indirect
+	github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2 // indirect
 	github.com/andybalholm/cascadia v1.3.2 // indirect
 	github.com/atotto/clipboard v0.1.4 // indirect
 	github.com/aws/aws-sdk-go-v2 v1.30.3 // indirect
@@ -70,62 +70,58 @@ require (
 	github.com/charmbracelet/x/cellbuf v0.0.13-0.20250311204145-2c3ea96c31dd // indirect
 	github.com/charmbracelet/x/exp/strings v0.0.0-20240722160745-212f7b056ed0 // indirect
 	github.com/charmbracelet/x/term v0.2.1 // indirect
-	github.com/cloudflare/circl v1.6.1 // indirect
-	github.com/cyphar/filepath-securejoin v0.4.1 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/dlclark/regexp2 v1.11.4 // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
-	github.com/emirpasic/gods v1.18.1 // indirect
 	github.com/erikgeiser/coninput v0.0.0-20211004153227-1c3628e74d0f // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
-	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
-	github.com/go-git/go-billy/v5 v5.6.2 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-viper/mapstructure/v2 v2.2.1 // indirect
-	github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
+	github.com/golang-jwt/jwt/v5 v5.2.2 // indirect
 	github.com/google/s2a-go v0.1.8 // indirect
 	github.com/googleapis/enterprise-certificate-proxy v0.3.4 // indirect
 	github.com/googleapis/gax-go/v2 v2.14.1 // indirect
 	github.com/gorilla/css v1.0.1 // indirect
-	github.com/hashicorp/errwrap v1.1.0 // indirect
-	github.com/hashicorp/go-multierror v1.1.1 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
-	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
-	github.com/kevinburke/ssh_config v1.2.0 // indirect
+	github.com/kylelemons/godebug v1.1.0 // indirect
 	github.com/lucasb-eyer/go-colorful v1.2.0 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/mattn/go-localereader v0.0.1 // indirect
+	github.com/mattn/go-runewidth v0.0.16 // indirect
+	github.com/mfridman/interpolate v0.0.2 // indirect
 	github.com/microcosm-cc/bluemonday v1.0.27 // indirect
 	github.com/mitchellh/hashstructure/v2 v2.0.2 // indirect
 	github.com/muesli/cancelreader v0.2.2 // indirect
+	github.com/ncruces/julianday v1.0.0 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.3 // indirect
-	github.com/pjbgf/sha1cd v0.3.2 // indirect
+	github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/rivo/uniseg v0.4.7 // indirect
+	github.com/rogpeppe/go-internal v1.14.1 // indirect
 	github.com/sagikazarmark/locafero v0.7.0 // indirect
-	github.com/skeema/knownhosts v1.3.1 // indirect
+	github.com/sethvargo/go-retry v0.3.0 // indirect
 	github.com/sourcegraph/conc v0.3.0 // indirect
 	github.com/spf13/afero v1.12.0 // indirect
 	github.com/spf13/cast v1.7.1 // indirect
 	github.com/spf13/pflag v1.0.6 // indirect
 	github.com/subosito/gotenv v1.6.0 // indirect
+	github.com/tetratelabs/wazero v1.9.0 // indirect
 	github.com/tidwall/gjson v1.18.0 // indirect
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.1 // indirect
 	github.com/tidwall/sjson v1.2.5 // indirect
-	github.com/xanzy/ssh-agent v0.3.3 // indirect
 	github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect
 	github.com/yosida95/uritemplate/v3 v3.0.2 // indirect
 	github.com/yuin/goldmark v1.7.8 // indirect
 	github.com/yuin/goldmark-emoji v1.0.5 // indirect
+	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.54.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 // indirect
-	go.opentelemetry.io/otel v1.29.0 // indirect
-	go.opentelemetry.io/otel/metric v1.29.0 // indirect
-	go.opentelemetry.io/otel/trace v1.29.0 // indirect
-	go.uber.org/atomic v1.9.0 // indirect
-	go.uber.org/multierr v1.9.0 // indirect
+	go.opentelemetry.io/otel v1.35.0 // indirect
+	go.opentelemetry.io/otel/metric v1.35.0 // indirect
+	go.opentelemetry.io/otel/trace v1.35.0 // indirect
+	go.uber.org/multierr v1.11.0 // indirect
 	golang.org/x/crypto v0.37.0 // indirect
 	golang.org/x/net v0.39.0 // indirect
 	golang.org/x/oauth2 v0.25.0 // indirect
@@ -134,10 +130,9 @@ require (
 	golang.org/x/term v0.31.0 // indirect
 	golang.org/x/text v0.24.0 // indirect
 	golang.org/x/time v0.8.0 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20241223144023-3abc09e42ca8 // indirect
-	google.golang.org/grpc v1.67.3 // indirect
-	google.golang.org/protobuf v1.36.1 // indirect
-	gopkg.in/warnings.v0 v0.1.2 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20250106144421-5f5ef82da422 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463 // indirect
+	google.golang.org/grpc v1.71.0 // indirect
+	google.golang.org/protobuf v1.36.6 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
--- a/go.sum
+++ b/go.sum
@@ -10,17 +10,18 @@ cloud.google.com/go/compute/metadata v0.6.0 h1:A6hENjEsCDtC1k8byVsgwvVcioamEHvZ4
 cloud.google.com/go/compute/metadata v0.6.0/go.mod h1:FjyFAW1MW0C203CEOMDTu3Dk1FlqW3Rga40jzHL4hfg=
 cloud.google.com/go/longrunning v0.5.7 h1:WLbHekDbjK1fVFD3ibpFFVoyizlLRl73I7YKuAKilhU=
 cloud.google.com/go/longrunning v0.5.7/go.mod h1:8GClkudohy1Fxm3owmBGid8W0pSgodEMwEAztp38Xng=
-dario.cat/mergo v1.0.0 h1:AGCNq9Evsj31mOgNPcLyXc+4PNABt905YmuqPYYpBWk=
-dario.cat/mergo v1.0.0/go.mod h1:uNxQE+84aUszobStD9th8a29P2fMDhsBdgRYvZOxGmk=
+github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0 h1:g0EZJwz7xkXQiZAI5xi9f3WWFYBlX1CPTrR+NDToRkQ=
+github.com/Azure/azure-sdk-for-go/sdk/azcore v1.17.0/go.mod h1:XCW7KnZet0Opnr7HccfUw1PLc4CjHqpcaxW8DHklNkQ=
+github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.7.0 h1:tfLQ34V6F7tVSwoTf/4lH5sE0o6eCJuNDTmH09nDpbc=
+github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.7.0/go.mod h1:9kIvujWAA58nmPmWB1m23fyWic1kYZMxD9CxaWn4Qpg=
+github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0 h1:ywEEhmNahHBihViHepv3xPBn1663uRv2t2q/ESv9seY=
+github.com/Azure/azure-sdk-for-go/sdk/internal v1.10.0/go.mod h1:iZDifYGJTIgIIkYRNWPENUnqx6bJ2xnSDFI2tjwZNuY=
+github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2 h1:XHOnouVk1mxXfQidrMEnLlPk9UMeRtyBTnEFtxkV0kU=
+github.com/AzureAD/microsoft-authentication-library-for-go v1.2.2/go.mod h1:wP83P5OoQ5p6ip3ScPr0BAq0BvuPAvacpEuSzyouqAI=
 github.com/JohannesKaufmann/html-to-markdown v1.6.0 h1:04VXMiE50YYfCfLboJCLcgqF5x+rHJnb1ssNmqpLH/k=
 github.com/JohannesKaufmann/html-to-markdown v1.6.0/go.mod h1:NUI78lGg/a7vpEJTz/0uOcYMaibytE4BUOQS8k78yPQ=
 github.com/MakeNowJust/heredoc v1.0.0 h1:cXCdzVdstXyiTqTvfqk9SDHpKNjxuom+DOlyEeQ4pzQ=
 github.com/MakeNowJust/heredoc v1.0.0/go.mod h1:mG5amYoWBHf8vpLOuehzbGGw0EHxpZZ6lCpQ4fNJ8LE=
-github.com/Microsoft/go-winio v0.5.2/go.mod h1:WpS1mjBmmwHBEWmogvA2mj8546UReBk4v8QkMxJ6pZY=
-github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
-github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
-github.com/ProtonMail/go-crypto v1.1.6 h1:ZcV+Ropw6Qn0AX9brlQLAUXfqLBc7Bl+f/DmNxpLfdw=
-github.com/ProtonMail/go-crypto v1.1.6/go.mod h1:rA3QumHc/FZ8pAHreoekgiAbzpNsfQAosU5td4SnOrE=
 github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE=
 github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=
 github.com/alecthomas/assert/v2 v2.11.0 h1:2Q9r3ki8+JYXvGsDyBXwH3LcJ+WK5D0gc5E8vS6K3D0=
@@ -31,12 +32,8 @@ github.com/alecthomas/repr v0.4.0 h1:GhI2A8MACjfegCPVq9f1FLvIBS+DrQ2KQBFZP1iFzXc
 github.com/alecthomas/repr v0.4.0/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
 github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
 github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
-github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be h1:9AeTilPcZAjCFIImctFaOjnTIavg87rW78vTPkQqLI8=
-github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4=
 github.com/anthropics/anthropic-sdk-go v0.2.0-beta.2 h1:h7qxtumNjKPWFv1QM/HJy60MteeW23iKeEtBoY7bYZk=
 github.com/anthropics/anthropic-sdk-go v0.2.0-beta.2/go.mod h1:AapDW22irxK2PSumZiQXYUFvsdQgkwIWlpESweWZI/c=
-github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPdPJAN/hZIm0C4OItdklCFmMRWYpio=
-github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5/go.mod h1:wHh0iHkYZB8zMSxRWpUBQtwG5a7fFgvEO+odwuTv2gs=
 github.com/atotto/clipboard v0.1.4 h1:EH0zSVneZPSuFR11BlR9YppQTVDbh5+16AmcJi4g1z4=
 github.com/atotto/clipboard v0.1.4/go.mod h1:ZY9tmq7sm5xIbd9bOK4onWV4S6X0u6GY7Vn0Yu86PYI=
 github.com/aws/aws-sdk-go-v2 v1.30.3 h1:jUeBtG0Ih+ZIFH0F4UkmL9w3cSpaMv9tYYDbzILP8dY=
@@ -99,11 +96,7 @@ github.com/charmbracelet/x/exp/strings v0.0.0-20240722160745-212f7b056ed0 h1:qko
 github.com/charmbracelet/x/exp/strings v0.0.0-20240722160745-212f7b056ed0/go.mod h1:pBhA0ybfXv6hDjQUZ7hk1lVxBiUbupdw5R31yPUViVQ=
 github.com/charmbracelet/x/term v0.2.1 h1:AQeHeLZ1OqSXhrAWpYUtZyX1T3zVxfpZuEQMIQaGIAQ=
 github.com/charmbracelet/x/term v0.2.1/go.mod h1:oQ4enTYFV7QN4m0i9mzHrViD7TQKvNEEkHUMCmsxdUg=
-github.com/cloudflare/circl v1.6.1 h1:zqIqSPIndyBh1bjLVVDHMPpVKqp8Su/V+6MeDzzQBQ0=
-github.com/cloudflare/circl v1.6.1/go.mod h1:uddAzsPgqdMAYatqJ0lsjX1oECcQLIlRpzZh3pJrofs=
 github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
-github.com/cyphar/filepath-securejoin v0.4.1 h1:JyxxyPEaktOD+GAnqIqTf9A8tHyAG22rowi7HkoSU1s=
-github.com/cyphar/filepath-securejoin v0.4.1/go.mod h1:Sdj7gXlvMcPZsbhwhQ33GguGLDGQL7h7bg04C/+u9jI=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -111,10 +104,6 @@ github.com/dlclark/regexp2 v1.11.4 h1:rPYF9/LECdNymJufQKmri9gV604RvvABwgOA8un7yA
 github.com/dlclark/regexp2 v1.11.4/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
-github.com/elazarl/goproxy v1.7.2 h1:Y2o6urb7Eule09PjlhQRGNsqRfPmYI3KKQLFpCAV3+o=
-github.com/elazarl/goproxy v1.7.2/go.mod h1:82vkLNir0ALaW14Rc399OTTjyNREgmdL2cVoIbS6XaE=
-github.com/emirpasic/gods v1.18.1 h1:FXtiHYKDGKCW2KzwZKx0iC0PQmdlorYgdFG9jPXJ1Bc=
-github.com/emirpasic/gods v1.18.1/go.mod h1:8tpGGwCnJ5H4r6BWwaV6OrWmMoPhUl5jm/FMNAnJvWQ=
 github.com/erikgeiser/coninput v0.0.0-20211004153227-1c3628e74d0f h1:Y/CXytFA4m6baUTXGLOoWe4PQhGxaX0KpnayAqC48p4=
 github.com/erikgeiser/coninput v0.0.0-20211004153227-1c3628e74d0f/go.mod h1:vw97MGsxSvLiUE2X8qFplwetxpGLQrlU1Q9AUEIzCaM=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
@@ -123,16 +112,6 @@ github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHk
 github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
 github.com/fsnotify/fsnotify v1.8.0 h1:dAwr6QBTBZIkG8roQaJjGof0pp0EeF+tNV7YBP3F/8M=
 github.com/fsnotify/fsnotify v1.8.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
-github.com/gliderlabs/ssh v0.3.8 h1:a4YXD1V7xMF9g5nTkdfnja3Sxy1PVDCj1Zg4Wb8vY6c=
-github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU=
-github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI=
-github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376/go.mod h1:an3vInlBmSxCcxctByoQdvwPiA7DTK7jaaFDBTtu0ic=
-github.com/go-git/go-billy/v5 v5.6.2 h1:6Q86EsPXMa7c3YZ3aLAQsMA0VlWmy43r6FHqa/UNbRM=
-github.com/go-git/go-billy/v5 v5.6.2/go.mod h1:rcFC2rAsp/erv7CMz9GczHcuD0D32fWzH+MJAU+jaUU=
-github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399 h1:eMje31YglSBqCdIqdhKBW8lokaMrL3uTkpGYlE2OOT4=
-github.com/go-git/go-git-fixtures/v4 v4.3.2-0.20231010084843-55a94097c399/go.mod h1:1OCfN199q1Jm3HZlxleg+Dw/mwps2Wbk9frAWm+4FII=
-github.com/go-git/go-git/v5 v5.15.0 h1:f5Qn0W0F7ry1iN0ZwIU5m/n7/BKB4hiZfc+zlZx7ly0=
-github.com/go-git/go-git/v5 v5.15.0/go.mod h1:4Ge4alE/5gPs30F2H1esi2gPd69R0C39lolkucHBOp8=
 github.com/go-logfmt/logfmt v0.6.0 h1:wGYYu3uicYdqXVgoYbvnkrPVXkuLM1p1ifugDMEdRi4=
 github.com/go-logfmt/logfmt v0.6.0/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=
 github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
@@ -142,10 +121,10 @@ github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
 github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 github.com/go-viper/mapstructure/v2 v2.2.1 h1:ZAaOCxANMuZx5RCeg0mBdEZk7DZasvvZIxtHqx8aGss=
 github.com/go-viper/mapstructure/v2 v2.2.1/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
-github.com/golang-migrate/migrate/v4 v4.18.2 h1:2VSCMz7x7mjyTXx3m2zPokOY82LTRgxK1yQYKo6wWQ8=
-github.com/golang-migrate/migrate/v4 v4.18.2/go.mod h1:2CM6tJvn2kqPXwnXO/d3rAQYiyoIm180VsO8PRX6Rpk=
-github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 h1:f+oWsMOmNPc8JmEHVZIycC7hBoQxHH9pNKQORJNozsQ=
-github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8/go.mod h1:wcDNUvekVysuuOpQKo3191zZyTpiI6se1N1ULghS0sw=
+github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeDy8=
+github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
+github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
+github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
 github.com/google/generative-ai-go v0.19.0 h1:R71szggh8wHMCUlEMsW2A/3T+5LdEIkiaHSYgSpUgdg=
 github.com/google/generative-ai-go v0.19.0/go.mod h1:JYolL13VG7j79kM5BtHz4qwONHkeJQzOCkKXnpqtS/E=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
@@ -160,19 +139,10 @@ github.com/googleapis/gax-go/v2 v2.14.1 h1:hb0FFeiPaQskmvakKu5EbCbpntQn48jyHuvrk
 github.com/googleapis/gax-go/v2 v2.14.1/go.mod h1:Hb/NubMaVM88SrNkvl8X/o8XWwDJEPqouaLeN2IUxoA=
 github.com/gorilla/css v1.0.1 h1:ntNaBIghp6JmvWnxbZKANoLyuXTPZ4cAMlo6RyhlbO8=
 github.com/gorilla/css v1.0.1/go.mod h1:BvnYkspnSzMmwRK+b8/xgNPLiIuNZr6vbZBTPQ2A3b0=
-github.com/hashicorp/errwrap v1.0.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
-github.com/hashicorp/errwrap v1.1.0 h1:OxrOeh75EUXMY8TBjag2fzXGZ40LB6IKw45YeGUDY2I=
-github.com/hashicorp/errwrap v1.1.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
-github.com/hashicorp/go-multierror v1.1.1 h1:H5DkEtf6CXdFp0N0Em5UCwQpXMWke8IA0+lD48awMYo=
-github.com/hashicorp/go-multierror v1.1.1/go.mod h1:iw975J/qwKPdAO1clOe2L8331t/9/fmwbPZ6JB6eMoM=
 github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUqJM=
 github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
-github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
-github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
-github.com/kevinburke/ssh_config v1.2.0 h1:x584FjTGwHzMwvHx18PXxbBVzfnxogHaAReU4gf13a4=
-github.com/kevinburke/ssh_config v1.2.0/go.mod h1:CT57kijsi8u/K/BOFA39wgDQJ9CxiF4nAY/ojJ6r6mM=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
@@ -180,8 +150,8 @@ github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
-github.com/lib/pq v1.10.9 h1:YXG7RB+JIjhP29X+OtkiDnYaXQwpS4JEWq7dtCCRUEw=
-github.com/lib/pq v1.10.9/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
+github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
+github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
 github.com/lrstanley/bubblezone v0.0.0-20250315020633-c249a3fe1231 h1:9rjt7AfnrXKNSZhp36A3/4QAZAwGGCGD/p8Bse26zms=
 github.com/lrstanley/bubblezone v0.0.0-20250315020633-c249a3fe1231/go.mod h1:S5etECMx+sZnW0Gm100Ma9J1PgVCTgNyFaqGu2b08b4=
 github.com/lucasb-eyer/go-colorful v1.2.0 h1:1nnpGOrhyZZuNyfu1QjKiUICQ74+3FNCN69Aj6K7nkY=
@@ -195,8 +165,8 @@ github.com/mattn/go-localereader v0.0.1/go.mod h1:8fBrzywKY7BI3czFoHkuzRoWE9C+Ei
 github.com/mattn/go-runewidth v0.0.12/go.mod h1:RAqKPSqVFrSLVXbA8x7dzmKdmGzieGRCM46jaSJTDAk=
 github.com/mattn/go-runewidth v0.0.16 h1:E5ScNMtiwvlvB5paMFdw9p4kSQzbXFikJ5SQO6TULQc=
 github.com/mattn/go-runewidth v0.0.16/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
-github.com/mattn/go-sqlite3 v1.14.24 h1:tpSp2G2KyMnnQu99ngJ47EIkWVmliIizyZBfPrBWDRM=
-github.com/mattn/go-sqlite3 v1.14.24/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
+github.com/mfridman/interpolate v0.0.2 h1:pnuTK7MQIxxFz1Gr+rjSIx9u7qVjf5VOoM/u6BbAxPY=
+github.com/mfridman/interpolate v0.0.2/go.mod h1:p+7uk6oE07mpE/Ik1b8EckO0O4ZXiGAfshKBWLUM9Xg=
 github.com/microcosm-cc/bluemonday v1.0.27 h1:MpEUotklkwCSLeH+Qdx1VJgNqLlpY2KXwXFM08ygZfk=
 github.com/microcosm-cc/bluemonday v1.0.27/go.mod h1:jFi9vgW+H7c3V0lb6nR74Ib/DIB5OBs92Dimizgw2cA=
 github.com/mitchellh/hashstructure/v2 v2.0.2 h1:vGKWl0YJqUNxE8d+h8f6NJLcCJrgbhC4NcD46KavDd4=
@@ -209,19 +179,25 @@ github.com/muesli/reflow v0.3.0 h1:IFsN6K9NfGtjeggFP+68I4chLZV2yIKsXJFNZ+eWh6s=
 github.com/muesli/reflow v0.3.0/go.mod h1:pbwTDkVPibjO2kyvBQRBxTWEEGDGq0FlB1BIKtnHY/8=
 github.com/muesli/termenv v0.16.0 h1:S5AlUN9dENB57rsbnkPyfdGuWIlkmzJjbFf0Tf5FWUc=
 github.com/muesli/termenv v0.16.0/go.mod h1:ZRfOIKPFDYQoDFF4Olj7/QJbW60Ol/kL1pU3VfY/Cnk=
-github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k=
-github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY=
+github.com/ncruces/go-sqlite3 v0.25.0 h1:trugKUs98Zwy9KwRr/EUxZHL92LYt7UqcKqAfpGpK+I=
+github.com/ncruces/go-sqlite3 v0.25.0/go.mod h1:n6Z7036yFilJx04yV0mi5JWaF66rUmXn1It9Ux8dx68=
+github.com/ncruces/go-strftime v0.1.9 h1:bY0MQC28UADQmHmaF5dgpLmImcShSi2kHU9XLdhx/f4=
+github.com/ncruces/go-strftime v0.1.9/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
+github.com/ncruces/julianday v1.0.0 h1:fH0OKwa7NWvniGQtxdJRxAgkBMolni2BjDHaWTxqt7M=
+github.com/ncruces/julianday v1.0.0/go.mod h1:Dusn2KvZrrovOMJuOt0TNXL6tB7U2E8kvza5fFc9G7g=
 github.com/openai/openai-go v0.1.0-beta.2 h1:Ra5nCFkbEl9w+UJwAciC4kqnIBUCcJazhmMA0/YN894=
 github.com/openai/openai-go v0.1.0-beta.2/go.mod h1:g461MYGXEXBVdV5SaR/5tNzNbSfwTBBefwc+LlDCK0Y=
 github.com/pelletier/go-toml/v2 v2.2.3 h1:YmeHyLY8mFWbdkNWwpr+qIL2bEqT0o95WSdkNHvL12M=
 github.com/pelletier/go-toml/v2 v2.2.3/go.mod h1:MfCQTFTvCcUyyvvwm1+G6H/jORL20Xlb6rzQu9GuUkc=
-github.com/pjbgf/sha1cd v0.3.2 h1:a9wb0bp1oC2TGwStyn0Umc/IGKQnEgF0vVaZ8QF8eo4=
-github.com/pjbgf/sha1cd v0.3.2/go.mod h1:zQWigSxVmsHEZow5qaLtPYxpcKMMQpa09ixqBxuCS6A=
+github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=
+github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
-github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/pressly/goose/v3 v3.24.2 h1:c/ie0Gm8rnIVKvnDQ/scHErv46jrDv9b4I0WRcFJzYU=
+github.com/pressly/goose/v3 v3.24.2/go.mod h1:kjefwFB0eR4w30Td2Gj2Mznyw94vSP+2jJYkOVNbD1k=
+github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
+github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/rivo/uniseg v0.1.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
@@ -237,9 +213,8 @@ github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAm
 github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I=
 github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8=
 github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3/go.mod h1:A0bzQcvG0E7Rwjx0REVgAGH58e96+X0MeOfepqsbeW4=
-github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
-github.com/skeema/knownhosts v1.3.1 h1:X2osQ+RAjK76shCbvhHHHVl3ZlgDm8apHEHFqRjnBY8=
-github.com/skeema/knownhosts v1.3.1/go.mod h1:r7KTdC8l4uxWRyK2TpQZ/1o5HaSzh06ePQNxPwTcfiY=
+github.com/sethvargo/go-retry v0.3.0 h1:EEt31A35QhrcRZtrYFDTBg91cqZVnFL2navjDrah2SE=
+github.com/sethvargo/go-retry v0.3.0/go.mod h1:mNX17F0C/HguQMyMyJxcnU471gOZGxCLyYaFyAZraas=
 github.com/sourcegraph/conc v0.3.0 h1:OQTbbt6P72L20UqAkXXuLOj79LfEanQ+YQFNpLA9ySo=
 github.com/sourcegraph/conc v0.3.0/go.mod h1:Sdozi7LEKbFPqYX2/J+iBAM6HpqSLTASQIKqDmF7Mt0=
 github.com/spf13/afero v1.12.0 h1:UcOPyRBYczmFn6yvphxkn9ZEOY65cpwGKb5mL36mrqs=
@@ -253,13 +228,14 @@ github.com/spf13/pflag v1.0.6/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An
 github.com/spf13/viper v1.20.0 h1:zrxIyR3RQIOsarIrgL8+sAvALXul9jeEPa06Y0Ph6vY=
 github.com/spf13/viper v1.20.0/go.mod h1:P9Mdzt1zoHIG8m2eZQinpiBjo6kCmZSKBClNNqjJvu4=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
-github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
 github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/subosito/gotenv v1.6.0 h1:9NlTDc1FTs4qu0DDq7AEtTPNw6SVm7uBMsUCUjABIf8=
 github.com/subosito/gotenv v1.6.0/go.mod h1:Dk4QP5c2W3ibzajGcXpNraDfq2IrhjMIvMSWPKKo0FU=
+github.com/tetratelabs/wazero v1.9.0 h1:IcZ56OuxrtaEz8UYNRHBrUa9bYeX9oVY93KspZZBf/I=
+github.com/tetratelabs/wazero v1.9.0/go.mod h1:TSbcXCfFP0L2FGkRPxHphadXPjo1T6W+CseNNY7EkjM=
 github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
 github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY=
 github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
@@ -270,8 +246,6 @@ github.com/tidwall/pretty v1.2.1 h1:qjsOFOWWQl+N3RsoF5/ssm1pHmJJwhjlSbZ51I6wMl4=
 github.com/tidwall/pretty v1.2.1/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
 github.com/tidwall/sjson v1.2.5 h1:kLy8mja+1c9jlljvWTlSazM7cKDRfJuR/bOJhcY5NcY=
 github.com/tidwall/sjson v1.2.5/go.mod h1:Fvgq9kS/6ociJEDnK0Fk1cpYF4FIW6ZF7LAe+6jwd28=
-github.com/xanzy/ssh-agent v0.3.3 h1:+/15pJfg/RsTxqYcX6fHqOXZwwMP+2VyYWJeWM2qQFM=
-github.com/xanzy/ssh-agent v0.3.3/go.mod h1:6dzNDKs0J9rVPHPhaGCukekBHKqfl+L3KghI1Bc68Uw=
 github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavMF/ppJZNG9ZpyihvCd0w101no=
 github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e/go.mod h1:RbqR21r5mrJuqunuUZ/Dhy/avygyECGrLceyNeo4LiM=
 github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
@@ -282,35 +256,37 @@ github.com/yuin/goldmark v1.7.8 h1:iERMLn0/QJeHFhxSt3p6PeN9mGnvIKSpG9YYorDMnic=
 github.com/yuin/goldmark v1.7.8/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E=
 github.com/yuin/goldmark-emoji v1.0.5 h1:EMVWyCGPlXJfUXBXpuMu+ii3TIaxbVBnEX9uaDC4cIk=
 github.com/yuin/goldmark-emoji v1.0.5/go.mod h1:tTkZEbwu5wkPmgTcitqddVxY9osFZiavD+r4AzQrh1U=
+go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
+go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
 go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.54.0 h1:r6I7RJCN86bpD/FQwedZ0vSixDpwuWREjW9oRMsmqDc=
 go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.54.0/go.mod h1:B9yO6b04uB80CzjedvewuqDhxJxi11s7/GtiGa8bAjI=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 h1:TT4fX+nBOA/+LUkobKGW1ydGcn+G3vRw9+g5HwCphpk=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0/go.mod h1:L7UH0GbB0p47T4Rri3uHjbpCFYrVrwc1I25QhNPiGK8=
-go.opentelemetry.io/otel v1.29.0 h1:PdomN/Al4q/lN6iBJEN3AwPvUiHPMlt93c8bqTG5Llw=
-go.opentelemetry.io/otel v1.29.0/go.mod h1:N/WtXPs1CNCUEx+Agz5uouwCba+i+bJGFicT8SR4NP8=
-go.opentelemetry.io/otel/metric v1.29.0 h1:vPf/HFWTNkPu1aYeIsc98l4ktOQaL6LeSoeV2g+8YLc=
-go.opentelemetry.io/otel/metric v1.29.0/go.mod h1:auu/QWieFVWx+DmQOUMgj0F8LHWdgalxXqvp7BII/W8=
-go.opentelemetry.io/otel/trace v1.29.0 h1:J/8ZNK4XgR7a21DZUAsbF8pZ5Jcw1VhACmnYt39JTi4=
-go.opentelemetry.io/otel/trace v1.29.0/go.mod h1:eHl3w0sp3paPkYstJOmAimxhiFXPg+MMTlEh3nsQgWQ=
-go.uber.org/atomic v1.9.0 h1:ECmE8Bn/WFTYwEW/bpKD3M8VtR/zQVbavAoalC1PYyE=
-go.uber.org/atomic v1.9.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
-go.uber.org/multierr v1.9.0 h1:7fIwc/ZtS0q++VgcfqFDxSBZVv/Xo49/SYnDFupUwlI=
-go.uber.org/multierr v1.9.0/go.mod h1:X2jQV1h+kxSjClGpnseKVIxpmcjrj7MNnI0bnlfKTVQ=
+go.opentelemetry.io/otel v1.35.0 h1:xKWKPxrxB6OtMCbmMY021CqC45J+3Onta9MqjhnusiQ=
+go.opentelemetry.io/otel v1.35.0/go.mod h1:UEqy8Zp11hpkUrL73gSlELM0DupHoiq72dR+Zqel/+Y=
+go.opentelemetry.io/otel/metric v1.35.0 h1:0znxYu2SNyuMSQT4Y9WDWej0VpcsxkuklLa4/siN90M=
+go.opentelemetry.io/otel/metric v1.35.0/go.mod h1:nKVFgxBZ2fReX6IlyW28MgZojkoAkJGaE8CpgeAU3oE=
+go.opentelemetry.io/otel/sdk v1.34.0 h1:95zS4k/2GOy069d321O8jWgYsW3MzVV+KuSPKp7Wr1A=
+go.opentelemetry.io/otel/sdk v1.34.0/go.mod h1:0e/pNiaMAqaykJGKbi+tSjWfNNHMTxoC9qANsCzbyxU=
+go.opentelemetry.io/otel/sdk/metric v1.34.0 h1:5CeK9ujjbFVL5c1PhLuStg1wxA7vQv7ce1EK0Gyvahk=
+go.opentelemetry.io/otel/sdk/metric v1.34.0/go.mod h1:jQ/r8Ze28zRKoNRdkjCZxfs6YvBTG1+YIqyFVFYec5w=
+go.opentelemetry.io/otel/trace v1.35.0 h1:dPpEfJu1sDIqruz7BHFG3c7528f6ddfSWfFDVt/xgMs=
+go.opentelemetry.io/otel/trace v1.35.0/go.mod h1:WUk7DtFp1Aw2MkvqGdwiXYDZZNvA/1J8o6xRXLrIkyc=
+go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
+go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
 golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M=
 golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
 golang.org/x/crypto v0.37.0 h1:kJNSjF/Xp7kU0iB2Z+9viTPMW4EqqsrywMXLJOOsXSE=
 golang.org/x/crypto v0.37.0/go.mod h1:vg+k43peMZ0pUMhYmVAWysMK35e6ioLh3wB8ZCAfbVc=
-golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 h1:2dVuKD2vS7b0QIHQbpyTISPd0LeHDbnYEryqj5Q1ug8=
-golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56/go.mod h1:M4RDyNAINzryxdtnbRXRL/OHtkFuWGRjvuhBJpk2IlY=
+golang.org/x/exp v0.0.0-20250305212735-054e65f0b394 h1:nDVHiLt8aIbd/VzvPWN6kSOPE7+F/fNFDSXLVYkE/Iw=
+golang.org/x/exp v0.0.0-20250305212735-054e65f0b394/go.mod h1:sIifuuw/Yco/y6yb6+bDNfyeQ/MdPUy/hKEMYQV17cM=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
@@ -328,15 +304,12 @@ golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.13.0 h1:AauUjRAJ9OSnvULf/ARrrVywoJDy0YS2AwQ98I37610=
 golang.org/x/sync v0.13.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210809222454-d867a43fc93e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -358,7 +331,6 @@ golang.org/x/term v0.31.0 h1:erwDkOK1Msy6offm1mOgvspSkslFnIGsFnxOKoufg3o=
 golang.org/x/term v0.31.0/go.mod h1:R4BeIy7D95HzImkxGkTW1UQTtP54tio2RyHz7PwK0aw=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
@@ -375,22 +347,28 @@ golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/api v0.215.0 h1:jdYF4qnyczlEz2ReWIsosNLDuzXyvFHJtI5gcr0J7t0=
 google.golang.org/api v0.215.0/go.mod h1:fta3CVtuJYOEdugLNWm6WodzOS8KdFckABwN4I40hzY=
-google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576 h1:CkkIfIt50+lT6NHAVoRYEyAvQGFM7xEwXUUywFvEb3Q=
-google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576/go.mod h1:1R3kvZ1dtP3+4p4d3G8uJ8rFk/fWlScl38vanWACI08=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20241223144023-3abc09e42ca8 h1:TqExAhdPaB60Ux47Cn0oLV07rGnxZzIsaRhQaqS666A=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20241223144023-3abc09e42ca8/go.mod h1:lcTa1sDdWEIHMWlITnIczmw5w60CF9ffkb8Z+DVmmjA=
-google.golang.org/grpc v1.67.3 h1:OgPcDAFKHnH8X3O4WcO4XUc8GRDeKsKReqbQtiCj7N8=
-google.golang.org/grpc v1.67.3/go.mod h1:YGaHCc6Oap+FzBJTZLBzkGSYt/cvGPFTPxkn7QfSU8s=
-google.golang.org/protobuf v1.36.1 h1:yBPeRvTftaleIgM3PZ/WBIZ7XM/eEYAaEyCwvyjq/gk=
-google.golang.org/protobuf v1.36.1/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
+google.golang.org/genproto/googleapis/api v0.0.0-20250106144421-5f5ef82da422 h1:GVIKPyP/kLIyVOgOnTwFOrvQaQUzOzGMCxgFUOEmm24=
+google.golang.org/genproto/googleapis/api v0.0.0-20250106144421-5f5ef82da422/go.mod h1:b6h1vNKhxaSoEI+5jc3PJUCustfli/mRab7295pY7rw=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463 h1:e0AIkUUhxyBKh6ssZNrAMeqhA7RKUj42346d1y02i2g=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
+google.golang.org/grpc v1.71.0 h1:kF77BGdPTQ4/JZWMlb9VpJ5pa25aqvVqogsxNHHdeBg=
+google.golang.org/grpc v1.71.0/go.mod h1:H0GRtasmQOh9LkFoCPDu3ZrwUtD1YGE+b2vYBYd/8Ec=
+google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
+google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
-gopkg.in/warnings.v0 v0.1.2 h1:wFXVbFY8DY5/xOe1ECiWdKCzZlxgshcYVNkBHstARME=
-gopkg.in/warnings.v0 v0.1.2/go.mod h1:jksf8JmL6Qr/oQM2OXTHunEvvTAsrWBLb6OOjuVWRNI=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+modernc.org/libc v1.61.13 h1:3LRd6ZO1ezsFiX1y+bHd1ipyEHIJKvuprv0sLTBwLW8=
+modernc.org/libc v1.61.13/go.mod h1:8F/uJWL/3nNil0Lgt1Dpz+GgkApWh04N3el3hxJcA6E=
+modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=
+modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=
+modernc.org/memory v1.9.1 h1:V/Z1solwAVmMW1yttq3nDdZPJqV1rM05Ccq6KMSZ34g=
+modernc.org/memory v1.9.1/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw=
+modernc.org/sqlite v1.36.2 h1:vjcSazuoFve9Wm0IVNHgmJECoOXLZM1KfMXbcX2axHA=
+modernc.org/sqlite v1.36.2/go.mod h1:ADySlx7K4FdY5MaJcEv86hTJ0PjedAloTUuif0YS3ws=
--- a/internal/app/app.go
+++ b/internal/app/app.go
@@ -73,6 +73,7 @@ func New(ctx context.Context, conn *sql.DB) (*App, error) {
 	return app, nil
 }

+
 // Shutdown performs a clean shutdown of the application
 func (app *App) Shutdown() {
 	// Cancel all watcher goroutines
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -67,14 +67,15 @@ type LSPConfig struct {

 // Config is the main configuration structure for the application.
 type Config struct {
-	Data       Data                              `json:"data"`
-	WorkingDir string                            `json:"wd,omitempty"`
-	MCPServers map[string]MCPServer              `json:"mcpServers,omitempty"`
-	Providers  map[models.ModelProvider]Provider `json:"providers,omitempty"`
-	LSP        map[string]LSPConfig              `json:"lsp,omitempty"`
-	Agents     map[AgentName]Agent               `json:"agents"`
-	Debug      bool                              `json:"debug,omitempty"`
-	DebugLSP   bool                              `json:"debugLSP,omitempty"`
+	Data         Data                              `json:"data"`
+	WorkingDir   string                            `json:"wd,omitempty"`
+	MCPServers   map[string]MCPServer              `json:"mcpServers,omitempty"`
+	Providers    map[models.ModelProvider]Provider `json:"providers,omitempty"`
+	LSP          map[string]LSPConfig              `json:"lsp,omitempty"`
+	Agents       map[AgentName]Agent               `json:"agents"`
+	Debug        bool                              `json:"debug,omitempty"`
+	DebugLSP     bool                              `json:"debugLSP,omitempty"`
+	ContextPaths []string                          `json:"contextPaths,omitempty"`
 }

 // Application constants
@@ -82,8 +83,24 @@ const (
 	defaultDataDirectory = ".opencode"
 	defaultLogLevel      = "info"
 	appName              = "opencode"
+
+	MaxTokensFallbackDefault = 4096
 )

+var defaultContextPaths = []string{
+	".github/copilot-instructions.md",
+	".cursorrules",
+	".cursor/rules/",
+	"CLAUDE.md",
+	"CLAUDE.local.md",
+	"opencode.md",
+	"opencode.local.md",
+	"OpenCode.md",
+	"OpenCode.local.md",
+	"OPENCODE.md",
+	"OPENCODE.local.md",
+}
+
 // Global configuration instance
 var cfg *Config

@@ -185,6 +202,7 @@ func configureViper() {
 // setDefaults configures default values for configuration options.
 func setDefaults(debug bool) {
 	viper.SetDefault("data.directory", defaultDataDirectory)
+	viper.SetDefault("contextPaths", defaultContextPaths)

 	if debug {
 		viper.SetDefault("debug", true)
@@ -196,16 +214,29 @@ func setDefaults(debug bool) {
 }

 // setProviderDefaults configures LLM provider defaults based on environment variables.
-// the default model priority is:
-// 1. Anthropic
-// 2. OpenAI
-// 3. Google Gemini
-// 4. Groq
-// 5. AWS Bedrock
 func setProviderDefaults() {
-	// Anthropic configuration
+	// Set all API keys we can find in the environment
 	if apiKey := os.Getenv("ANTHROPIC_API_KEY"); apiKey != "" {
 		viper.SetDefault("providers.anthropic.apiKey", apiKey)
+	}
+	if apiKey := os.Getenv("OPENAI_API_KEY"); apiKey != "" {
+		viper.SetDefault("providers.openai.apiKey", apiKey)
+	}
+	if apiKey := os.Getenv("GEMINI_API_KEY"); apiKey != "" {
+		viper.SetDefault("providers.gemini.apiKey", apiKey)
+	}
+	if apiKey := os.Getenv("GROQ_API_KEY"); apiKey != "" {
+		viper.SetDefault("providers.groq.apiKey", apiKey)
+	}
+
+	// Use this order to set the default models
+	// 1. Anthropic
+	// 2. OpenAI
+	// 3. Google Gemini
+	// 4. Groq
+	// 5. AWS Bedrock
+	// Anthropic configuration
+	if apiKey := os.Getenv("ANTHROPIC_API_KEY"); apiKey != "" {
 		viper.SetDefault("agents.coder.model", models.Claude37Sonnet)
 		viper.SetDefault("agents.task.model", models.Claude37Sonnet)
 		viper.SetDefault("agents.title.model", models.Claude37Sonnet)
@@ -214,7 +245,6 @@ func setProviderDefaults() {

 	// OpenAI configuration
 	if apiKey := os.Getenv("OPENAI_API_KEY"); apiKey != "" {
-		viper.SetDefault("providers.openai.apiKey", apiKey)
 		viper.SetDefault("agents.coder.model", models.GPT41)
 		viper.SetDefault("agents.task.model", models.GPT41Mini)
 		viper.SetDefault("agents.title.model", models.GPT41Mini)
@@ -223,7 +253,6 @@ func setProviderDefaults() {

 	// Google Gemini configuration
 	if apiKey := os.Getenv("GEMINI_API_KEY"); apiKey != "" {
-		viper.SetDefault("providers.gemini.apiKey", apiKey)
 		viper.SetDefault("agents.coder.model", models.Gemini25)
 		viper.SetDefault("agents.task.model", models.Gemini25Flash)
 		viper.SetDefault("agents.title.model", models.Gemini25Flash)
@@ -232,13 +261,21 @@ func setProviderDefaults() {

 	// Groq configuration
 	if apiKey := os.Getenv("GROQ_API_KEY"); apiKey != "" {
-		viper.SetDefault("providers.groq.apiKey", apiKey)
 		viper.SetDefault("agents.coder.model", models.QWENQwq)
 		viper.SetDefault("agents.task.model", models.QWENQwq)
 		viper.SetDefault("agents.title.model", models.QWENQwq)
 		return
 	}

+	// OpenRouter configuration
+	if apiKey := os.Getenv("OPENROUTER_API_KEY"); apiKey != "" {
+		viper.SetDefault("providers.openrouter.apiKey", apiKey)
+		viper.SetDefault("agents.coder.model", models.OpenRouterClaude37Sonnet)
+		viper.SetDefault("agents.task.model", models.OpenRouterClaude37Sonnet)
+		viper.SetDefault("agents.title.model", models.OpenRouterClaude35Haiku)
+		return
+	}
+
 	// AWS Bedrock configuration
 	if hasAWSCredentials() {
 		viper.SetDefault("agents.coder.model", models.BedrockClaude37Sonnet)
@@ -246,6 +283,15 @@ func setProviderDefaults() {
 		viper.SetDefault("agents.title.model", models.BedrockClaude37Sonnet)
 		return
 	}
+
+	if os.Getenv("AZURE_OPENAI_ENDPOINT") != "" {
+		// api-key may be empty when using Entra ID credentials – that's okay
+		viper.SetDefault("providers.azure.apiKey", os.Getenv("AZURE_OPENAI_API_KEY"))
+		viper.SetDefault("agents.coder.model", models.AzureGPT41)
+		viper.SetDefault("agents.task.model", models.AzureGPT41Mini)
+		viper.SetDefault("agents.title.model", models.AzureGPT41Mini)
+		return
+	}
 }

 // hasAWSCredentials checks if AWS credentials are available in the environment.
@@ -312,60 +358,33 @@ func applyDefaultValues() {
 	}
 }

-// Validate checks if the configuration is valid and applies defaults where needed.
 // It validates model IDs and providers, ensuring they are supported.
-func Validate() error {
-	if cfg == nil {
-		return fmt.Errorf("config not loaded")
+func validateAgent(cfg *Config, name AgentName, agent Agent) error {
+	// Check if model exists
+	model, modelExists := models.SupportedModels[agent.Model]
+	if !modelExists {
+		logging.Warn("unsupported model configured, reverting to default",
+			"agent", name,
+			"configured_model", agent.Model)
+
+		// Set default model based on available providers
+		if setDefaultModelForAgent(name) {
+			logging.Info("set default model for agent", "agent", name, "model", cfg.Agents[name].Model)
+		} else {
+			return fmt.Errorf("no valid provider available for agent %s", name)
+		}
+		return nil
 	}

-	// Validate agent models
-	for name, agent := range cfg.Agents {
-		// Check if model exists
-		model, modelExists := models.SupportedModels[agent.Model]
-		if !modelExists {
-			logging.Warn("unsupported model configured, reverting to default",
-				"agent", name,
-				"configured_model", agent.Model)
+	// Check if provider for the model is configured
+	provider := model.Provider
+	providerCfg, providerExists := cfg.Providers[provider]

-			// Set default model based on available providers
-			if setDefaultModelForAgent(name) {
-				logging.Info("set default model for agent", "agent", name, "model", cfg.Agents[name].Model)
-			} else {
-				return fmt.Errorf("no valid provider available for agent %s", name)
-			}
-			continue
-		}
-
-		// Check if provider for the model is configured
-		provider := model.Provider
-		providerCfg, providerExists := cfg.Providers[provider]
-
-		if !providerExists {
-			// Provider not configured, check if we have environment variables
-			apiKey := getProviderAPIKey(provider)
-			if apiKey == "" {
-				logging.Warn("provider not configured for model, reverting to default",
-					"agent", name,
-					"model", agent.Model,
-					"provider", provider)
-
-				// Set default model based on available providers
-				if setDefaultModelForAgent(name) {
-					logging.Info("set default model for agent", "agent", name, "model", cfg.Agents[name].Model)
-				} else {
-					return fmt.Errorf("no valid provider available for agent %s", name)
-				}
-			} else {
-				// Add provider with API key from environment
-				cfg.Providers[provider] = Provider{
-					APIKey: apiKey,
-				}
-				logging.Info("added provider from environment", "provider", provider)
-			}
-		} else if providerCfg.Disabled || providerCfg.APIKey == "" {
-			// Provider is disabled or has no API key
-			logging.Warn("provider is disabled or has no API key, reverting to default",
+	if !providerExists {
+		// Provider not configured, check if we have environment variables
+		apiKey := getProviderAPIKey(provider)
+		if apiKey == "" {
+			logging.Warn("provider not configured for model, reverting to default",
 				"agent", name,
 				"model", agent.Model,
 				"provider", provider)
@@ -376,75 +395,110 @@ func Validate() error {
 			} else {
 				return fmt.Errorf("no valid provider available for agent %s", name)
 			}
-		}
-
-		// Validate max tokens
-		if agent.MaxTokens <= 0 {
-			logging.Warn("invalid max tokens, setting to default",
-				"agent", name,
-				"model", agent.Model,
-				"max_tokens", agent.MaxTokens)
-
-			// Update the agent with default max tokens
-			updatedAgent := cfg.Agents[name]
-			if model.DefaultMaxTokens > 0 {
-				updatedAgent.MaxTokens = model.DefaultMaxTokens
-			} else {
-				updatedAgent.MaxTokens = 4096 // Fallback default
+		} else {
+			// Add provider with API key from environment
+			cfg.Providers[provider] = Provider{
+				APIKey: apiKey,
 			}
-			cfg.Agents[name] = updatedAgent
-		} else if model.ContextWindow > 0 && agent.MaxTokens > model.ContextWindow/2 {
-			// Ensure max tokens doesn't exceed half the context window (reasonable limit)
-			logging.Warn("max tokens exceeds half the context window, adjusting",
-				"agent", name,
-				"model", agent.Model,
-				"max_tokens", agent.MaxTokens,
-				"context_window", model.ContextWindow)
-
-			// Update the agent with adjusted max tokens
-			updatedAgent := cfg.Agents[name]
-			updatedAgent.MaxTokens = model.ContextWindow / 2
-			cfg.Agents[name] = updatedAgent
+			logging.Info("added provider from environment", "provider", provider)
 		}
+	} else if providerCfg.Disabled || providerCfg.APIKey == "" {
+		// Provider is disabled or has no API key
+		logging.Warn("provider is disabled or has no API key, reverting to default",
+			"agent", name,
+			"model", agent.Model,
+			"provider", provider)

-		// Validate reasoning effort for models that support reasoning
-		if model.CanReason && provider == models.ProviderOpenAI {
-			if agent.ReasoningEffort == "" {
-				// Set default reasoning effort for models that support it
-				logging.Info("setting default reasoning effort for model that supports reasoning",
+		// Set default model based on available providers
+		if setDefaultModelForAgent(name) {
+			logging.Info("set default model for agent", "agent", name, "model", cfg.Agents[name].Model)
+		} else {
+			return fmt.Errorf("no valid provider available for agent %s", name)
+		}
+	}
+
+	// Validate max tokens
+	if agent.MaxTokens <= 0 {
+		logging.Warn("invalid max tokens, setting to default",
+			"agent", name,
+			"model", agent.Model,
+			"max_tokens", agent.MaxTokens)
+
+		// Update the agent with default max tokens
+		updatedAgent := cfg.Agents[name]
+		if model.DefaultMaxTokens > 0 {
+			updatedAgent.MaxTokens = model.DefaultMaxTokens
+		} else {
+			updatedAgent.MaxTokens = MaxTokensFallbackDefault
+		}
+		cfg.Agents[name] = updatedAgent
+	} else if model.ContextWindow > 0 && agent.MaxTokens > model.ContextWindow/2 {
+		// Ensure max tokens doesn't exceed half the context window (reasonable limit)
+		logging.Warn("max tokens exceeds half the context window, adjusting",
+			"agent", name,
+			"model", agent.Model,
+			"max_tokens", agent.MaxTokens,
+			"context_window", model.ContextWindow)
+
+		// Update the agent with adjusted max tokens
+		updatedAgent := cfg.Agents[name]
+		updatedAgent.MaxTokens = model.ContextWindow / 2
+		cfg.Agents[name] = updatedAgent
+	}
+
+	// Validate reasoning effort for models that support reasoning
+	if model.CanReason && provider == models.ProviderOpenAI {
+		if agent.ReasoningEffort == "" {
+			// Set default reasoning effort for models that support it
+			logging.Info("setting default reasoning effort for model that supports reasoning",
+				"agent", name,
+				"model", agent.Model)
+
+			// Update the agent with default reasoning effort
+			updatedAgent := cfg.Agents[name]
+			updatedAgent.ReasoningEffort = "medium"
+			cfg.Agents[name] = updatedAgent
+		} else {
+			// Check if reasoning effort is valid (low, medium, high)
+			effort := strings.ToLower(agent.ReasoningEffort)
+			if effort != "low" && effort != "medium" && effort != "high" {
+				logging.Warn("invalid reasoning effort, setting to medium",
 					"agent", name,
-					"model", agent.Model)
+					"model", agent.Model,
+					"reasoning_effort", agent.ReasoningEffort)

-				// Update the agent with default reasoning effort
+				// Update the agent with valid reasoning effort
 				updatedAgent := cfg.Agents[name]
 				updatedAgent.ReasoningEffort = "medium"
 				cfg.Agents[name] = updatedAgent
-			} else {
-				// Check if reasoning effort is valid (low, medium, high)
-				effort := strings.ToLower(agent.ReasoningEffort)
-				if effort != "low" && effort != "medium" && effort != "high" {
-					logging.Warn("invalid reasoning effort, setting to medium",
-						"agent", name,
-						"model", agent.Model,
-						"reasoning_effort", agent.ReasoningEffort)
-
-					// Update the agent with valid reasoning effort
-					updatedAgent := cfg.Agents[name]
-					updatedAgent.ReasoningEffort = "medium"
-					cfg.Agents[name] = updatedAgent
-				}
 			}
-		} else if !model.CanReason && agent.ReasoningEffort != "" {
-			// Model doesn't support reasoning but reasoning effort is set
-			logging.Warn("model doesn't support reasoning but reasoning effort is set, ignoring",
-				"agent", name,
-				"model", agent.Model,
-				"reasoning_effort", agent.ReasoningEffort)
+		}
+	} else if !model.CanReason && agent.ReasoningEffort != "" {
+		// Model doesn't support reasoning but reasoning effort is set
+		logging.Warn("model doesn't support reasoning but reasoning effort is set, ignoring",
+			"agent", name,
+			"model", agent.Model,
+			"reasoning_effort", agent.ReasoningEffort)

-			// Update the agent to remove reasoning effort
-			updatedAgent := cfg.Agents[name]
-			updatedAgent.ReasoningEffort = ""
-			cfg.Agents[name] = updatedAgent
+		// Update the agent to remove reasoning effort
+		updatedAgent := cfg.Agents[name]
+		updatedAgent.ReasoningEffort = ""
+		cfg.Agents[name] = updatedAgent
+	}
+
+	return nil
+}
+
+// Validate checks if the configuration is valid and applies defaults where needed.
+func Validate() error {
+	if cfg == nil {
+		return fmt.Errorf("config not loaded")
+	}
+
+	// Validate agent models
+	for name, agent := range cfg.Agents {
+		if err := validateAgent(cfg, name, agent); err != nil {
+			return err
 		}
 	}

@@ -480,6 +534,10 @@ func getProviderAPIKey(provider models.ModelProvider) string {
 		return os.Getenv("GEMINI_API_KEY")
 	case models.ProviderGROQ:
 		return os.Getenv("GROQ_API_KEY")
+	case models.ProviderAzure:
+		return os.Getenv("AZURE_OPENAI_API_KEY")
+	case models.ProviderOpenRouter:
+		return os.Getenv("OPENROUTER_API_KEY")
 	case models.ProviderBedrock:
 		if hasAWSCredentials() {
 			return "aws-credentials-available"
@@ -531,6 +589,34 @@ func setDefaultModelForAgent(agent AgentName) bool {
 		return true
 	}

+	if apiKey := os.Getenv("OPENROUTER_API_KEY"); apiKey != "" {
+		var model models.ModelID
+		maxTokens := int64(5000)
+		reasoningEffort := ""
+
+		switch agent {
+		case AgentTitle:
+			model = models.OpenRouterClaude35Haiku
+			maxTokens = 80
+		case AgentTask:
+			model = models.OpenRouterClaude37Sonnet
+		default:
+			model = models.OpenRouterClaude37Sonnet
+		}
+
+		// Check if model supports reasoning
+		if modelInfo, ok := models.SupportedModels[model]; ok && modelInfo.CanReason {
+			reasoningEffort = "medium"
+		}
+
+		cfg.Agents[agent] = Agent{
+			Model:           model,
+			MaxTokens:       maxTokens,
+			ReasoningEffort: reasoningEffort,
+		}
+		return true
+	}
+
 	if apiKey := os.Getenv("GEMINI_API_KEY"); apiKey != "" {
 		var model models.ModelID
 		maxTokens := int64(5000)
@@ -592,3 +678,36 @@ func WorkingDirectory() string {
 	}
 	return cfg.WorkingDir
 }
+
+func UpdateAgentModel(agentName AgentName, modelID models.ModelID) error {
+	if cfg == nil {
+		panic("config not loaded")
+	}
+
+	existingAgentCfg := cfg.Agents[agentName]
+
+	model, ok := models.SupportedModels[modelID]
+	if !ok {
+		return fmt.Errorf("model %s not supported", modelID)
+	}
+
+	maxTokens := existingAgentCfg.MaxTokens
+	if model.DefaultMaxTokens > 0 {
+		maxTokens = model.DefaultMaxTokens
+	}
+
+	newAgentCfg := Agent{
+		Model:           modelID,
+		MaxTokens:       maxTokens,
+		ReasoningEffort: existingAgentCfg.ReasoningEffort,
+	}
+	cfg.Agents[agentName] = newAgentCfg
+
+	if err := validateAgent(cfg, agentName, newAgentCfg); err != nil {
+		// revert config update on failure
+		cfg.Agents[agentName] = existingAgentCfg
+		return fmt.Errorf("failed to update agent model: %w", err)
+	}
+
+	return nil
+}
--- a/internal/db/connect.go
+++ b/internal/db/connect.go
@@ -6,14 +6,13 @@ import (
 	"os"
 	"path/filepath"

-	"github.com/golang-migrate/migrate/v4"
-	"github.com/golang-migrate/migrate/v4/source/iofs"
-
-	"github.com/golang-migrate/migrate/v4/database/sqlite3"
-	_ "github.com/mattn/go-sqlite3"
+	_ "github.com/ncruces/go-sqlite3/driver"
+	_ "github.com/ncruces/go-sqlite3/embed"

 	"github.com/opencode-ai/opencode/internal/config"
 	"github.com/opencode-ai/opencode/internal/logging"
+
+	"github.com/pressly/goose/v3"
 )

 func Connect() (*sql.DB, error) {
@@ -54,38 +53,16 @@ func Connect() (*sql.DB, error) {
 		}
 	}

-	// Initialize schema from embedded file
-	d, err := iofs.New(FS, "migrations")
-	if err != nil {
-		logging.Error("Failed to open embedded migrations", "error", err)
-		db.Close()
-		return nil, fmt.Errorf("failed to open embedded migrations: %w", err)
+	goose.SetBaseFS(FS)
+
+	if err := goose.SetDialect("sqlite3"); err != nil {
+		logging.Error("Failed to set dialect", "error", err)
+		return nil, fmt.Errorf("failed to set dialect: %w", err)
 	}

-	driver, err := sqlite3.WithInstance(db, &sqlite3.Config{})
-	if err != nil {
-		logging.Error("Failed to create SQLite driver", "error", err)
-		db.Close()
-		return nil, fmt.Errorf("failed to create SQLite driver: %w", err)
+	if err := goose.Up(db, "migrations"); err != nil {
+		logging.Error("Failed to apply migrations", "error", err)
+		return nil, fmt.Errorf("failed to apply migrations: %w", err)
 	}
-
-	m, err := migrate.NewWithInstance("iofs", d, "ql", driver)
-	if err != nil {
-		logging.Error("Failed to create migration instance", "error", err)
-		db.Close()
-		return nil, fmt.Errorf("failed to create migration instance: %w", err)
-	}
-
-	err = m.Up()
-	if err != nil && err != migrate.ErrNoChange {
-		logging.Error("Migration failed", "error", err)
-		db.Close()
-		return nil, fmt.Errorf("failed to apply schema: %w", err)
-	} else if err == migrate.ErrNoChange {
-		logging.Info("No schema changes to apply")
-	} else {
-		logging.Info("Schema migration applied successfully")
-	}
-
 	return db, nil
 }
--- a/internal/db/migrations/000001_initial.down.sql
+++ b/internal/db/migrations/000001_initial.down.sql
@@ -1,10 +0,0 @@
-DROP TRIGGER IF EXISTS update_sessions_updated_at;
-DROP TRIGGER IF EXISTS update_messages_updated_at;
-DROP TRIGGER IF EXISTS update_files_updated_at;
-
-DROP TRIGGER IF EXISTS update_session_message_count_on_delete;
-DROP TRIGGER IF EXISTS update_session_message_count_on_insert;
-
-DROP TABLE IF EXISTS sessions;
-DROP TABLE IF EXISTS messages;
-DROP TABLE IF EXISTS files;
--- a/internal/db/migrations/20250424200609_initial.sql
+++ b/internal/db/migrations/20250424200609_initial.sql
@@ -1,3 +1,5 @@
+-- +goose Up
+-- +goose StatementBegin
 -- Sessions
 CREATE TABLE IF NOT EXISTS sessions (
    id TEXT PRIMARY KEY,
@@ -78,3 +80,19 @@ UPDATE sessions SET
    message_count = message_count - 1
 WHERE id = old.session_id;
 END;
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+DROP TRIGGER IF EXISTS update_sessions_updated_at;
+DROP TRIGGER IF EXISTS update_messages_updated_at;
+DROP TRIGGER IF EXISTS update_files_updated_at;
+
+DROP TRIGGER IF EXISTS update_session_message_count_on_delete;
+DROP TRIGGER IF EXISTS update_session_message_count_on_insert;
+
+DROP TABLE IF EXISTS sessions;
+DROP TABLE IF EXISTS messages;
+DROP TABLE IF EXISTS files;
+-- +goose StatementEnd
--- a/internal/diff/diff.go
+++ b/internal/diff/diff.go
@@ -4,23 +4,18 @@ import (
 	"bytes"
 	"fmt"
 	"io"
-	"os"
-	"path/filepath"
 	"regexp"
 	"strconv"
 	"strings"
-	"time"

 	"github.com/alecthomas/chroma/v2"
 	"github.com/alecthomas/chroma/v2/formatters"
 	"github.com/alecthomas/chroma/v2/lexers"
 	"github.com/alecthomas/chroma/v2/styles"
+	"github.com/aymanbagabas/go-udiff"
 	"github.com/charmbracelet/lipgloss"
 	"github.com/charmbracelet/x/ansi"
-	"github.com/go-git/go-git/v5"
-	"github.com/go-git/go-git/v5/plumbing/object"
 	"github.com/opencode-ai/opencode/internal/config"
-	"github.com/opencode-ai/opencode/internal/logging"
 	"github.com/sergi/go-diff/diffmatchpatch"
 )

@@ -942,106 +937,21 @@ func GenerateDiff(beforeContent, afterContent, fileName string) (string, int, in
 	cwd := config.WorkingDirectory()
 	fileName = strings.TrimPrefix(fileName, cwd)
 	fileName = strings.TrimPrefix(fileName, "/")
-	// Create temporary directory for git operations
-	tempDir, err := os.MkdirTemp("", fmt.Sprintf("git-diff-%d", time.Now().UnixNano()))
-	if err != nil {
-		logging.Error("Failed to create temp directory for git diff", "error", err)
-		return "", 0, 0
-	}
-	defer os.RemoveAll(tempDir)

-	// Initialize git repo
-	repo, err := git.PlainInit(tempDir, false)
-	if err != nil {
-		logging.Error("Failed to initialize git repository", "error", err)
-		return "", 0, 0
+	var (
+		unified   = udiff.Unified("a/"+fileName, "b/"+fileName, beforeContent, afterContent)
+		additions = 0
+		removals  = 0
+	)
+
+	lines := strings.Split(unified, "\n")
+	for _, line := range lines {
+		if strings.HasPrefix(line, "+") && !strings.HasPrefix(line, "+++") {
+			additions++
+		} else if strings.HasPrefix(line, "-") && !strings.HasPrefix(line, "---") {
+			removals++
+		}
 	}

-	wt, err := repo.Worktree()
-	if err != nil {
-		logging.Error("Failed to get git worktree", "error", err)
-		return "", 0, 0
-	}
-
-	// Write the "before" content and commit it
-	fullPath := filepath.Join(tempDir, fileName)
-	if err = os.MkdirAll(filepath.Dir(fullPath), 0o755); err != nil {
-		logging.Error("Failed to create directory for file", "error", err)
-		return "", 0, 0
-	}
-	if err = os.WriteFile(fullPath, []byte(beforeContent), 0o644); err != nil {
-		logging.Error("Failed to write before content to file", "error", err)
-		return "", 0, 0
-	}
-
-	_, err = wt.Add(fileName)
-	if err != nil {
-		logging.Error("Failed to add file to git", "error", err)
-		return "", 0, 0
-	}
-
-	beforeCommit, err := wt.Commit("Before", &git.CommitOptions{
-		Author: &object.Signature{
-			Name:  "OpenCode",
-			Email: "coder@opencode.ai",
-			When:  time.Now(),
-		},
-	})
-	if err != nil {
-		logging.Error("Failed to commit before content", "error", err)
-		return "", 0, 0
-	}
-
-	// Write the "after" content and commit it
-	if err = os.WriteFile(fullPath, []byte(afterContent), 0o644); err != nil {
-		logging.Error("Failed to write after content to file", "error", err)
-		return "", 0, 0
-	}
-
-	_, err = wt.Add(fileName)
-	if err != nil {
-		logging.Error("Failed to add file to git", "error", err)
-		return "", 0, 0
-	}
-
-	afterCommit, err := wt.Commit("After", &git.CommitOptions{
-		Author: &object.Signature{
-			Name:  "OpenCode",
-			Email: "coder@opencode.ai",
-			When:  time.Now(),
-		},
-	})
-	if err != nil {
-		logging.Error("Failed to commit after content", "error", err)
-		return "", 0, 0
-	}
-
-	// Get the diff between the two commits
-	beforeCommitObj, err := repo.CommitObject(beforeCommit)
-	if err != nil {
-		logging.Error("Failed to get before commit object", "error", err)
-		return "", 0, 0
-	}
-
-	afterCommitObj, err := repo.CommitObject(afterCommit)
-	if err != nil {
-		logging.Error("Failed to get after commit object", "error", err)
-		return "", 0, 0
-	}
-
-	patch, err := beforeCommitObj.Patch(afterCommitObj)
-	if err != nil {
-		logging.Error("Failed to create git diff patch", "error", err)
-		return "", 0, 0
-	}
-
-	// Count additions and removals
-	additions := 0
-	removals := 0
-	for _, fileStat := range patch.Stats() {
-		additions += fileStat.Addition
-		removals += fileStat.Deletion
-	}
-
-	return patch.String(), additions, removals
+	return unified, additions, removals
 }
--- a/internal/llm/agent/agent.go
+++ b/internal/llm/agent/agent.go
@@ -42,6 +42,7 @@ type Service interface {
 	Cancel(sessionID string)
 	IsSessionBusy(sessionID string) bool
 	IsBusy() bool
+	Update(agentName config.AgentName, modelID models.ModelID) (models.Model, error)
 }

 type agent struct {
@@ -436,6 +437,25 @@ func (a *agent) TrackUsage(ctx context.Context, sessionID string, model models.M
 	return nil
 }

+func (a *agent) Update(agentName config.AgentName, modelID models.ModelID) (models.Model, error) {
+	if a.IsBusy() {
+		return models.Model{}, fmt.Errorf("cannot change model while processing requests")
+	}
+
+	if err := config.UpdateAgentModel(agentName, modelID); err != nil {
+		return models.Model{}, fmt.Errorf("failed to update config: %w", err)
+	}
+
+	provider, err := createAgentProvider(agentName)
+	if err != nil {
+		return models.Model{}, fmt.Errorf("failed to create provider for model %s: %w", modelID, err)
+	}
+
+	a.provider = provider
+
+	return a.provider.Model(), nil
+}
+
 func createAgentProvider(agentName config.AgentName) (provider.Provider, error) {
 	cfg := config.Get()
 	agentConfig, ok := cfg.Agents[agentName]
--- a/internal/llm/agent/mcp-tools.go
+++ b/internal/llm/agent/mcp-tools.go
@@ -58,7 +58,7 @@ func runTool(ctx context.Context, c MCPClient, toolName string, input string) (t
 	toolRequest := mcp.CallToolRequest{}
 	toolRequest.Params.Name = toolName
 	var args map[string]any
-	if err = json.Unmarshal([]byte(input), &input); err != nil {
+	if err = json.Unmarshal([]byte(input), &args); err != nil {
 		return tools.NewTextErrorResponse(fmt.Sprintf("error parsing parameters: %s", err)), nil
 	}
 	toolRequest.Params.Arguments = args
--- a/internal/llm/models/anthropic.go
+++ b/internal/llm/models/anthropic.go
@@ -11,8 +11,8 @@ const (
 	Claude3Opus    ModelID = "claude-3-opus"
 )

+// https://docs.anthropic.com/en/docs/about-claude/models/all-models
 var AnthropicModels = map[ModelID]Model{
-	// Anthropic
 	Claude35Sonnet: {
 		ID:                 Claude35Sonnet,
 		Name:               "Claude 3.5 Sonnet",
@@ -29,13 +29,13 @@ var AnthropicModels = map[ModelID]Model{
 		ID:                 Claude3Haiku,
 		Name:               "Claude 3 Haiku",
 		Provider:           ProviderAnthropic,
-		APIModel:           "claude-3-haiku-latest",
+		APIModel:           "claude-3-haiku-20240307", // doesn't support "-latest"
 		CostPer1MIn:        0.25,
 		CostPer1MInCached:  0.30,
 		CostPer1MOutCached: 0.03,
 		CostPer1MOut:       1.25,
 		ContextWindow:      200000,
-		DefaultMaxTokens:   5000,
+		DefaultMaxTokens:   4096,
 	},
 	Claude37Sonnet: {
 		ID:                 Claude37Sonnet,
--- a/internal/llm/models/azure.go
+++ b/internal/llm/models/azure.go
@@ -0,0 +1,157 @@
+package models
+
+const ProviderAzure ModelProvider = "azure"
+
+const (
+	AzureGPT41        ModelID = "azure.gpt-4.1"
+	AzureGPT41Mini    ModelID = "azure.gpt-4.1-mini"
+	AzureGPT41Nano    ModelID = "azure.gpt-4.1-nano"
+	AzureGPT45Preview ModelID = "azure.gpt-4.5-preview"
+	AzureGPT4o        ModelID = "azure.gpt-4o"
+	AzureGPT4oMini    ModelID = "azure.gpt-4o-mini"
+	AzureO1           ModelID = "azure.o1"
+	AzureO1Mini       ModelID = "azure.o1-mini"
+	AzureO3           ModelID = "azure.o3"
+	AzureO3Mini       ModelID = "azure.o3-mini"
+	AzureO4Mini       ModelID = "azure.o4-mini"
+)
+
+var AzureModels = map[ModelID]Model{
+	AzureGPT41: {
+		ID:                 AzureGPT41,
+		Name:               "Azure OpenAI – GPT 4.1",
+		Provider:           ProviderAzure,
+		APIModel:           "gpt-4.1",
+		CostPer1MIn:        OpenAIModels[GPT41].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41].DefaultMaxTokens,
+	},
+	AzureGPT41Mini: {
+		ID:                 AzureGPT41Mini,
+		Name:               "Azure OpenAI – GPT 4.1 mini",
+		Provider:           ProviderAzure,
+		APIModel:           "gpt-4.1-mini",
+		CostPer1MIn:        OpenAIModels[GPT41Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41Mini].DefaultMaxTokens,
+	},
+	AzureGPT41Nano: {
+		ID:                 AzureGPT41Nano,
+		Name:               "Azure OpenAI – GPT 4.1 nano",
+		Provider:           ProviderAzure,
+		APIModel:           "gpt-4.1-nano",
+		CostPer1MIn:        OpenAIModels[GPT41Nano].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41Nano].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41Nano].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41Nano].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41Nano].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41Nano].DefaultMaxTokens,
+	},
+	AzureGPT45Preview: {
+		ID:                 AzureGPT45Preview,
+		Name:               "Azure OpenAI – GPT 4.5 preview",
+		Provider:           ProviderAzure,
+		APIModel:           "gpt-4.5-preview",
+		CostPer1MIn:        OpenAIModels[GPT45Preview].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT45Preview].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT45Preview].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT45Preview].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT45Preview].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT45Preview].DefaultMaxTokens,
+	},
+	AzureGPT4o: {
+		ID:                 AzureGPT4o,
+		Name:               "Azure OpenAI – GPT-4o",
+		Provider:           ProviderAzure,
+		APIModel:           "gpt-4o",
+		CostPer1MIn:        OpenAIModels[GPT4o].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT4o].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT4o].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT4o].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT4o].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT4o].DefaultMaxTokens,
+	},
+	AzureGPT4oMini: {
+		ID:                 AzureGPT4oMini,
+		Name:               "Azure OpenAI – GPT-4o mini",
+		Provider:           ProviderAzure,
+		APIModel:           "gpt-4o-mini",
+		CostPer1MIn:        OpenAIModels[GPT4oMini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT4oMini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT4oMini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT4oMini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT4oMini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT4oMini].DefaultMaxTokens,
+	},
+	AzureO1: {
+		ID:                 AzureO1,
+		Name:               "Azure OpenAI – O1",
+		Provider:           ProviderAzure,
+		APIModel:           "o1",
+		CostPer1MIn:        OpenAIModels[O1].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1].CanReason,
+	},
+	AzureO1Mini: {
+		ID:                 AzureO1Mini,
+		Name:               "Azure OpenAI – O1 mini",
+		Provider:           ProviderAzure,
+		APIModel:           "o1-mini",
+		CostPer1MIn:        OpenAIModels[O1Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1Mini].CanReason,
+	},
+	AzureO3: {
+		ID:                 AzureO3,
+		Name:               "Azure OpenAI – O3",
+		Provider:           ProviderAzure,
+		APIModel:           "o3",
+		CostPer1MIn:        OpenAIModels[O3].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O3].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O3].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O3].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O3].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O3].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O3].CanReason,
+	},
+	AzureO3Mini: {
+		ID:                 AzureO3Mini,
+		Name:               "Azure OpenAI – O3 mini",
+		Provider:           ProviderAzure,
+		APIModel:           "o3-mini",
+		CostPer1MIn:        OpenAIModels[O3Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O3Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O3Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O3Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O3Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O3Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O3Mini].CanReason,
+	},
+	AzureO4Mini: {
+		ID:                 AzureO4Mini,
+		Name:               "Azure OpenAI – O4 mini",
+		Provider:           ProviderAzure,
+		APIModel:           "o4-mini",
+		CostPer1MIn:        OpenAIModels[O4Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O4Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O4Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O4Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O4Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O4Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O4Mini].CanReason,
+	},
+}
--- a/internal/llm/models/groq.go
+++ b/internal/llm/models/groq.go
@@ -0,0 +1,82 @@
+package models
+
+const (
+	ProviderGROQ ModelProvider = "groq"
+
+	// GROQ
+	QWENQwq ModelID = "qwen-qwq"
+
+	// GROQ preview models
+	Llama4Scout               ModelID = "meta-llama/llama-4-scout-17b-16e-instruct"
+	Llama4Maverick            ModelID = "meta-llama/llama-4-maverick-17b-128e-instruct"
+	Llama3_3_70BVersatile     ModelID = "llama-3.3-70b-versatile"
+	DeepseekR1DistillLlama70b ModelID = "deepseek-r1-distill-llama-70b"
+)
+
+var GroqModels = map[ModelID]Model{
+	//
+	// GROQ
+	QWENQwq: {
+		ID:                 QWENQwq,
+		Name:               "Qwen Qwq",
+		Provider:           ProviderGROQ,
+		APIModel:           "qwen-qwq-32b",
+		CostPer1MIn:        0.29,
+		CostPer1MInCached:  0.275,
+		CostPer1MOutCached: 0.0,
+		CostPer1MOut:       0.39,
+		ContextWindow:      128_000,
+		DefaultMaxTokens:   50000,
+		// for some reason, the groq api doesn't like the reasoningEffort parameter
+		CanReason: false,
+	},
+
+	Llama4Scout: {
+		ID:                 Llama4Scout,
+		Name:               "Llama4Scout",
+		Provider:           ProviderGROQ,
+		APIModel:           "meta-llama/llama-4-scout-17b-16e-instruct",
+		CostPer1MIn:        0.11,
+		CostPer1MInCached:  0,
+		CostPer1MOutCached: 0,
+		CostPer1MOut:       0.34,
+		ContextWindow:      128_000, // 10M when?
+	},
+
+	Llama4Maverick: {
+		ID:                 Llama4Maverick,
+		Name:               "Llama4Maverick",
+		Provider:           ProviderGROQ,
+		APIModel:           "meta-llama/llama-4-maverick-17b-128e-instruct",
+		CostPer1MIn:        0.20,
+		CostPer1MInCached:  0,
+		CostPer1MOutCached: 0,
+		CostPer1MOut:       0.20,
+		ContextWindow:      128_000,
+	},
+
+	Llama3_3_70BVersatile: {
+		ID:                 Llama3_3_70BVersatile,
+		Name:               "Llama3_3_70BVersatile",
+		Provider:           ProviderGROQ,
+		APIModel:           "llama-3.3-70b-versatile",
+		CostPer1MIn:        0.59,
+		CostPer1MInCached:  0,
+		CostPer1MOutCached: 0,
+		CostPer1MOut:       0.79,
+		ContextWindow:      128_000,
+	},
+
+	DeepseekR1DistillLlama70b: {
+		ID:                 DeepseekR1DistillLlama70b,
+		Name:               "DeepseekR1DistillLlama70b",
+		Provider:           ProviderGROQ,
+		APIModel:           "deepseek-r1-distill-llama-70b",
+		CostPer1MIn:        0.75,
+		CostPer1MInCached:  0,
+		CostPer1MOutCached: 0,
+		CostPer1MOut:       0.99,
+		ContextWindow:      128_000,
+		CanReason:          true,
+	},
+}
--- a/internal/llm/models/models.go
+++ b/internal/llm/models/models.go
@@ -23,21 +23,25 @@ type Model struct {

 // Model IDs
 const ( // GEMINI
-	// GROQ
-	QWENQwq ModelID = "qwen-qwq"
-
 	// Bedrock
 	BedrockClaude37Sonnet ModelID = "bedrock.claude-3.7-sonnet"
 )

 const (
 	ProviderBedrock ModelProvider = "bedrock"
-	ProviderGROQ    ModelProvider = "groq"
-
 	// ForTests
 	ProviderMock ModelProvider = "__mock"
 )

+// Providers in order of popularity
+var ProviderPopularity = map[ModelProvider]int{
+	ProviderAnthropic: 1,
+	ProviderOpenAI:    2,
+	ProviderGemini:    3,
+	ProviderGROQ:      4,
+	ProviderBedrock:   5,
+}
+
 var SupportedModels = map[ModelID]Model{
 	//
 	// // GEMINI
@@ -63,18 +67,6 @@ var SupportedModels = map[ModelID]Model{
 	// 	CostPer1MOut:       0.4,
 	// },
 	//
-	// // GROQ
-	// QWENQwq: {
-	// 	ID:                 QWENQwq,
-	// 	Name:               "Qwen Qwq",
-	// 	Provider:           ProviderGROQ,
-	// 	APIModel:           "qwen-qwq-32b",
-	// 	CostPer1MIn:        0,
-	// 	CostPer1MInCached:  0,
-	// 	CostPer1MOutCached: 0,
-	// 	CostPer1MOut:       0,
-	// },
-	//
 	// // Bedrock
 	BedrockClaude37Sonnet: {
 		ID:                 BedrockClaude37Sonnet,
@@ -92,4 +84,7 @@ func init() {
 	maps.Copy(SupportedModels, AnthropicModels)
 	maps.Copy(SupportedModels, OpenAIModels)
 	maps.Copy(SupportedModels, GeminiModels)
+	maps.Copy(SupportedModels, GroqModels)
+	maps.Copy(SupportedModels, AzureModels)
+	maps.Copy(SupportedModels, OpenRouterModels)
 }
--- a/internal/llm/models/openrouter.go
+++ b/internal/llm/models/openrouter.go
@@ -0,0 +1,262 @@
+package models
+
+const (
+	ProviderOpenRouter ModelProvider = "openrouter"
+
+	OpenRouterGPT41          ModelID = "openrouter.gpt-4.1"
+	OpenRouterGPT41Mini      ModelID = "openrouter.gpt-4.1-mini"
+	OpenRouterGPT41Nano      ModelID = "openrouter.gpt-4.1-nano"
+	OpenRouterGPT45Preview   ModelID = "openrouter.gpt-4.5-preview"
+	OpenRouterGPT4o          ModelID = "openrouter.gpt-4o"
+	OpenRouterGPT4oMini      ModelID = "openrouter.gpt-4o-mini"
+	OpenRouterO1             ModelID = "openrouter.o1"
+	OpenRouterO1Pro          ModelID = "openrouter.o1-pro"
+	OpenRouterO1Mini         ModelID = "openrouter.o1-mini"
+	OpenRouterO3             ModelID = "openrouter.o3"
+	OpenRouterO3Mini         ModelID = "openrouter.o3-mini"
+	OpenRouterO4Mini         ModelID = "openrouter.o4-mini"
+	OpenRouterGemini25Flash  ModelID = "openrouter.gemini-2.5-flash"
+	OpenRouterGemini25       ModelID = "openrouter.gemini-2.5"
+	OpenRouterClaude35Sonnet ModelID = "openrouter.claude-3.5-sonnet"
+	OpenRouterClaude3Haiku   ModelID = "openrouter.claude-3-haiku"
+	OpenRouterClaude37Sonnet ModelID = "openrouter.claude-3.7-sonnet"
+	OpenRouterClaude35Haiku  ModelID = "openrouter.claude-3.5-haiku"
+	OpenRouterClaude3Opus    ModelID = "openrouter.claude-3-opus"
+)
+
+var OpenRouterModels = map[ModelID]Model{
+	OpenRouterGPT41: {
+		ID:                 OpenRouterGPT41,
+		Name:               "OpenRouter – GPT 4.1",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.1",
+		CostPer1MIn:        OpenAIModels[GPT41].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41].DefaultMaxTokens,
+	},
+	OpenRouterGPT41Mini: {
+		ID:                 OpenRouterGPT41Mini,
+		Name:               "OpenRouter – GPT 4.1 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.1-mini",
+		CostPer1MIn:        OpenAIModels[GPT41Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41Mini].DefaultMaxTokens,
+	},
+	OpenRouterGPT41Nano: {
+		ID:                 OpenRouterGPT41Nano,
+		Name:               "OpenRouter – GPT 4.1 nano",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.1-nano",
+		CostPer1MIn:        OpenAIModels[GPT41Nano].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT41Nano].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT41Nano].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT41Nano].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT41Nano].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT41Nano].DefaultMaxTokens,
+	},
+	OpenRouterGPT45Preview: {
+		ID:                 OpenRouterGPT45Preview,
+		Name:               "OpenRouter – GPT 4.5 preview",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4.5-preview",
+		CostPer1MIn:        OpenAIModels[GPT45Preview].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT45Preview].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT45Preview].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT45Preview].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT45Preview].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT45Preview].DefaultMaxTokens,
+	},
+	OpenRouterGPT4o: {
+		ID:                 OpenRouterGPT4o,
+		Name:               "OpenRouter – GPT 4o",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4o",
+		CostPer1MIn:        OpenAIModels[GPT4o].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT4o].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT4o].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT4o].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT4o].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[GPT4o].DefaultMaxTokens,
+	},
+	OpenRouterGPT4oMini: {
+		ID:                 OpenRouterGPT4oMini,
+		Name:               "OpenRouter – GPT 4o mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/gpt-4o-mini",
+		CostPer1MIn:        OpenAIModels[GPT4oMini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[GPT4oMini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[GPT4oMini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[GPT4oMini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[GPT4oMini].ContextWindow,
+	},
+	OpenRouterO1: {
+		ID:                 OpenRouterO1,
+		Name:               "OpenRouter – O1",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o1",
+		CostPer1MIn:        OpenAIModels[O1].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1].CanReason,
+	},
+	OpenRouterO1Pro: {
+		ID:                 OpenRouterO1Pro,
+		Name:               "OpenRouter – o1 pro",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o1-pro",
+		CostPer1MIn:        OpenAIModels[O1Pro].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1Pro].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1Pro].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1Pro].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1Pro].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1Pro].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1Pro].CanReason,
+	},
+	OpenRouterO1Mini: {
+		ID:                 OpenRouterO1Mini,
+		Name:               "OpenRouter – o1 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o1-mini",
+		CostPer1MIn:        OpenAIModels[O1Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O1Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O1Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O1Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O1Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O1Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O1Mini].CanReason,
+	},
+	OpenRouterO3: {
+		ID:                 OpenRouterO3,
+		Name:               "OpenRouter – o3",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o3",
+		CostPer1MIn:        OpenAIModels[O3].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O3].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O3].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O3].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O3].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O3].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O3].CanReason,
+	},
+	OpenRouterO3Mini: {
+		ID:                 OpenRouterO3Mini,
+		Name:               "OpenRouter – o3 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o3-mini-high",
+		CostPer1MIn:        OpenAIModels[O3Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O3Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O3Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O3Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O3Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O3Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O3Mini].CanReason,
+	},
+	OpenRouterO4Mini: {
+		ID:                 OpenRouterO4Mini,
+		Name:               "OpenRouter – o4 mini",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "openai/o4-mini-high",
+		CostPer1MIn:        OpenAIModels[O4Mini].CostPer1MIn,
+		CostPer1MInCached:  OpenAIModels[O4Mini].CostPer1MInCached,
+		CostPer1MOut:       OpenAIModels[O4Mini].CostPer1MOut,
+		CostPer1MOutCached: OpenAIModels[O4Mini].CostPer1MOutCached,
+		ContextWindow:      OpenAIModels[O4Mini].ContextWindow,
+		DefaultMaxTokens:   OpenAIModels[O4Mini].DefaultMaxTokens,
+		CanReason:          OpenAIModels[O4Mini].CanReason,
+	},
+	OpenRouterGemini25Flash: {
+		ID:                 OpenRouterGemini25Flash,
+		Name:               "OpenRouter – Gemini 2.5 Flash",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "google/gemini-2.5-flash-preview:thinking",
+		CostPer1MIn:        GeminiModels[Gemini25Flash].CostPer1MIn,
+		CostPer1MInCached:  GeminiModels[Gemini25Flash].CostPer1MInCached,
+		CostPer1MOut:       GeminiModels[Gemini25Flash].CostPer1MOut,
+		CostPer1MOutCached: GeminiModels[Gemini25Flash].CostPer1MOutCached,
+		ContextWindow:      GeminiModels[Gemini25Flash].ContextWindow,
+		DefaultMaxTokens:   GeminiModels[Gemini25Flash].DefaultMaxTokens,
+	},
+	OpenRouterGemini25: {
+		ID:                 OpenRouterGemini25,
+		Name:               "OpenRouter – Gemini 2.5 Pro",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "google/gemini-2.5-pro-preview-03-25",
+		CostPer1MIn:        GeminiModels[Gemini25].CostPer1MIn,
+		CostPer1MInCached:  GeminiModels[Gemini25].CostPer1MInCached,
+		CostPer1MOut:       GeminiModels[Gemini25].CostPer1MOut,
+		CostPer1MOutCached: GeminiModels[Gemini25].CostPer1MOutCached,
+		ContextWindow:      GeminiModels[Gemini25].ContextWindow,
+		DefaultMaxTokens:   GeminiModels[Gemini25].DefaultMaxTokens,
+	},
+	OpenRouterClaude35Sonnet: {
+		ID:                 OpenRouterClaude35Sonnet,
+		Name:               "OpenRouter – Claude 3.5 Sonnet",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3.5-sonnet",
+		CostPer1MIn:        AnthropicModels[Claude35Sonnet].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude35Sonnet].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude35Sonnet].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude35Sonnet].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude35Sonnet].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude35Sonnet].DefaultMaxTokens,
+	},
+	OpenRouterClaude3Haiku: {
+		ID:                 OpenRouterClaude3Haiku,
+		Name:               "OpenRouter – Claude 3 Haiku",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3-haiku",
+		CostPer1MIn:        AnthropicModels[Claude3Haiku].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude3Haiku].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude3Haiku].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude3Haiku].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude3Haiku].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude3Haiku].DefaultMaxTokens,
+	},
+	OpenRouterClaude37Sonnet: {
+		ID:                 OpenRouterClaude37Sonnet,
+		Name:               "OpenRouter – Claude 3.7 Sonnet",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3.7-sonnet",
+		CostPer1MIn:        AnthropicModels[Claude37Sonnet].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude37Sonnet].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude37Sonnet].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude37Sonnet].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude37Sonnet].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude37Sonnet].DefaultMaxTokens,
+		CanReason:          AnthropicModels[Claude37Sonnet].CanReason,
+	},
+	OpenRouterClaude35Haiku: {
+		ID:                 OpenRouterClaude35Haiku,
+		Name:               "OpenRouter – Claude 3.5 Haiku",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3.5-haiku",
+		CostPer1MIn:        AnthropicModels[Claude35Haiku].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude35Haiku].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude35Haiku].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude35Haiku].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude35Haiku].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude35Haiku].DefaultMaxTokens,
+	},
+	OpenRouterClaude3Opus: {
+		ID:                 OpenRouterClaude3Opus,
+		Name:               "OpenRouter – Claude 3 Opus",
+		Provider:           ProviderOpenRouter,
+		APIModel:           "anthropic/claude-3-opus",
+		CostPer1MIn:        AnthropicModels[Claude3Opus].CostPer1MIn,
+		CostPer1MInCached:  AnthropicModels[Claude3Opus].CostPer1MInCached,
+		CostPer1MOut:       AnthropicModels[Claude3Opus].CostPer1MOut,
+		CostPer1MOutCached: AnthropicModels[Claude3Opus].CostPer1MOutCached,
+		ContextWindow:      AnthropicModels[Claude3Opus].ContextWindow,
+		DefaultMaxTokens:   AnthropicModels[Claude3Opus].DefaultMaxTokens,
+	},
+}
--- a/internal/llm/prompt/prompt.go
+++ b/internal/llm/prompt/prompt.go
@@ -4,25 +4,14 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"strings"
+	"sync"

 	"github.com/opencode-ai/opencode/internal/config"
 	"github.com/opencode-ai/opencode/internal/llm/models"
+	"github.com/opencode-ai/opencode/internal/logging"
 )

-// contextFiles is a list of potential context files to check for
-var contextFiles = []string{
-	".github/copilot-instructions.md",
-	".cursorrules",
-	"CLAUDE.md",
-	"CLAUDE.local.md",
-	"opencode.md",
-	"opencode.local.md",
-	"OpenCode.md",
-	"OpenCode.local.md",
-	"OPENCODE.md",
-	"OPENCODE.local.md",
-}
-
 func GetAgentPrompt(agentName config.AgentName, provider models.ModelProvider) string {
 	basePrompt := ""
 	switch agentName {
@@ -38,26 +27,109 @@ func GetAgentPrompt(agentName config.AgentName, provider models.ModelProvider) s

 	if agentName == config.AgentCoder || agentName == config.AgentTask {
 		// Add context from project-specific instruction files if they exist
-		contextContent := getContextFromFiles()
+		contextContent := getContextFromPaths()
+		logging.Debug("Context content", "Context", contextContent)
 		if contextContent != "" {
-			return fmt.Sprintf("%s\n\n# Project-Specific Context\n%s", basePrompt, contextContent)
+			return fmt.Sprintf("%s\n\n# Project-Specific Context\n Make sure to follow the instructions in the context below\n%s", basePrompt, contextContent)
 		}
 	}
 	return basePrompt
 }

-// getContextFromFiles checks for the existence of context files and returns their content
-func getContextFromFiles() string {
-	workDir := config.WorkingDirectory()
-	var contextContent string
+var (
+	onceContext    sync.Once
+	contextContent string
+)

-	for _, file := range contextFiles {
-		filePath := filepath.Join(workDir, file)
-		content, err := os.ReadFile(filePath)
-		if err == nil {
-			contextContent += fmt.Sprintf("\n%s\n", string(content))
-		}
-	}
+func getContextFromPaths() string {
+	onceContext.Do(func() {
+		var (
+			cfg          = config.Get()
+			workDir      = cfg.WorkingDir
+			contextPaths = cfg.ContextPaths
+		)
+
+		contextContent = processContextPaths(workDir, contextPaths)
+	})

 	return contextContent
 }
+
+func processContextPaths(workDir string, paths []string) string {
+	var (
+		wg       sync.WaitGroup
+		resultCh = make(chan string)
+	)
+
+	// Track processed files to avoid duplicates
+	processedFiles := make(map[string]bool)
+	var processedMutex sync.Mutex
+
+	for _, path := range paths {
+		wg.Add(1)
+		go func(p string) {
+			defer wg.Done()
+
+			if strings.HasSuffix(p, "/") {
+				filepath.WalkDir(filepath.Join(workDir, p), func(path string, d os.DirEntry, err error) error {
+					if err != nil {
+						return err
+					}
+					if !d.IsDir() {
+						// Check if we've already processed this file (case-insensitive)
+						processedMutex.Lock()
+						lowerPath := strings.ToLower(path)
+						if !processedFiles[lowerPath] {
+							processedFiles[lowerPath] = true
+							processedMutex.Unlock()
+
+							if result := processFile(path); result != "" {
+								resultCh <- result
+							}
+						} else {
+							processedMutex.Unlock()
+						}
+					}
+					return nil
+				})
+			} else {
+				fullPath := filepath.Join(workDir, p)
+
+				// Check if we've already processed this file (case-insensitive)
+				processedMutex.Lock()
+				lowerPath := strings.ToLower(fullPath)
+				if !processedFiles[lowerPath] {
+					processedFiles[lowerPath] = true
+					processedMutex.Unlock()
+
+					result := processFile(fullPath)
+					if result != "" {
+						resultCh <- result
+					}
+				} else {
+					processedMutex.Unlock()
+				}
+			}
+		}(path)
+	}
+
+	go func() {
+		wg.Wait()
+		close(resultCh)
+	}()
+
+	results := make([]string, 0)
+	for result := range resultCh {
+		results = append(results, result)
+	}
+
+	return strings.Join(results, "\n")
+}
+
+func processFile(filePath string) string {
+	content, err := os.ReadFile(filePath)
+	if err != nil {
+		return ""
+	}
+	return "# From:" + filePath + "\n" + string(content)
+}
--- a/internal/llm/provider/anthropic.go
+++ b/internal/llm/provider/anthropic.go
@@ -213,7 +213,7 @@ func (a *anthropicClient) send(ctx context.Context, messages []message.Message,
 				return nil, retryErr
 			}
 			if retry {
-				logging.WarnPersist("Retrying due to rate limit... attempt %d of %d", logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
+				logging.WarnPersist(fmt.Sprintf("Retrying due to rate limit... attempt %d of %d", attempts, maxRetries), logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
 				select {
 				case <-ctx.Done():
 					return nil, ctx.Err()
@@ -262,7 +262,7 @@ func (a *anthropicClient) stream(ctx context.Context, messages []message.Message
 				event := anthropicStream.Current()
 				err := accumulatedMessage.Accumulate(event)
 				if err != nil {
-					eventChan <- ProviderEvent{Type: EventError, Error: err}
+					logging.Warn("Error accumulating message", "error", err)
 					continue
 				}

@@ -351,7 +351,7 @@ func (a *anthropicClient) stream(ctx context.Context, messages []message.Message
 				return
 			}
 			if retry {
-				logging.WarnPersist("Retrying due to rate limit... attempt %d of %d", logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
+				logging.WarnPersist(fmt.Sprintf("Retrying due to rate limit... attempt %d of %d", attempts, maxRetries), logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
 				select {
 				case <-ctx.Done():
 					// context cancelled
--- a/internal/llm/provider/azure.go
+++ b/internal/llm/provider/azure.go
@@ -0,0 +1,47 @@
+package provider
+
+import (
+	"os"
+
+	"github.com/Azure/azure-sdk-for-go/sdk/azidentity"
+	"github.com/openai/openai-go"
+	"github.com/openai/openai-go/azure"
+	"github.com/openai/openai-go/option"
+)
+
+type azureClient struct {
+	*openaiClient
+}
+
+type AzureClient ProviderClient
+
+func newAzureClient(opts providerClientOptions) AzureClient {
+
+	endpoint := os.Getenv("AZURE_OPENAI_ENDPOINT")      // ex: https://foo.openai.azure.com
+	apiVersion := os.Getenv("AZURE_OPENAI_API_VERSION") // ex: 2025-04-01-preview
+
+	if endpoint == "" || apiVersion == "" {
+		return &azureClient{openaiClient: newOpenAIClient(opts).(*openaiClient)}
+	}
+
+	reqOpts := []option.RequestOption{
+		azure.WithEndpoint(endpoint, apiVersion),
+	}
+
+	if opts.apiKey != "" || os.Getenv("AZURE_OPENAI_API_KEY") != "" {
+		key := opts.apiKey
+		if key == "" {
+			key = os.Getenv("AZURE_OPENAI_API_KEY")
+		}
+		reqOpts = append(reqOpts, azure.WithAPIKey(key))
+	} else if cred, err := azidentity.NewDefaultAzureCredential(nil); err == nil {
+		reqOpts = append(reqOpts, azure.WithTokenCredential(cred))
+	}
+
+	base := &openaiClient{
+		providerOptions: opts,
+		client:          openai.NewClient(reqOpts...),
+	}
+
+	return &azureClient{openaiClient: base}
+}
--- a/internal/llm/provider/gemini.go
+++ b/internal/llm/provider/gemini.go
@@ -54,19 +54,6 @@ func newGeminiClient(opts providerClientOptions) GeminiClient {

 func (g *geminiClient) convertMessages(messages []message.Message) []*genai.Content {
 	var history []*genai.Content
-
-	// Add system message first
-	history = append(history, &genai.Content{
-		Parts: []genai.Part{genai.Text(g.providerOptions.systemMessage)},
-		Role:  "user",
-	})
-
-	// Add a system response to acknowledge the system message
-	history = append(history, &genai.Content{
-		Parts: []genai.Part{genai.Text("I'll help you with that.")},
-		Role:  "model",
-	})
-
 	for _, msg := range messages {
 		switch msg.Role {
 		case message.User:
@@ -132,7 +119,8 @@ func (g *geminiClient) convertMessages(messages []message.Message) []*genai.Cont
 }

 func (g *geminiClient) convertTools(tools []tools.BaseTool) []*genai.Tool {
-	geminiTools := make([]*genai.Tool, 0, len(tools))
+	geminiTool := &genai.Tool{}
+	geminiTool.FunctionDeclarations = make([]*genai.FunctionDeclaration, 0, len(tools))

 	for _, tool := range tools {
 		info := tool.Info()
@@ -146,23 +134,18 @@ func (g *geminiClient) convertTools(tools []tools.BaseTool) []*genai.Tool {
 			},
 		}

-		geminiTools = append(geminiTools, &genai.Tool{
-			FunctionDeclarations: []*genai.FunctionDeclaration{declaration},
-		})
+		geminiTool.FunctionDeclarations = append(geminiTool.FunctionDeclarations, declaration)
 	}

-	return geminiTools
+	return []*genai.Tool{geminiTool}
 }

 func (g *geminiClient) finishReason(reason genai.FinishReason) message.FinishReason {
-	reasonStr := reason.String()
 	switch {
-	case reasonStr == "STOP":
+	case reason == genai.FinishReasonStop:
 		return message.FinishReasonEndTurn
-	case reasonStr == "MAX_TOKENS":
+	case reason == genai.FinishReasonMaxTokens:
 		return message.FinishReasonMaxTokens
-	case strings.Contains(reasonStr, "FUNCTION") || strings.Contains(reasonStr, "TOOL"):
-		return message.FinishReasonToolUse
 	default:
 		return message.FinishReasonUnknown
 	}
@@ -171,7 +154,11 @@ func (g *geminiClient) finishReason(reason genai.FinishReason) message.FinishRea
 func (g *geminiClient) send(ctx context.Context, messages []message.Message, tools []tools.BaseTool) (*ProviderResponse, error) {
 	model := g.client.GenerativeModel(g.providerOptions.model.APIModel)
 	model.SetMaxOutputTokens(int32(g.providerOptions.maxTokens))
-
+	model.SystemInstruction = &genai.Content{
+		Parts: []genai.Part{
+			genai.Text(g.providerOptions.systemMessage),
+		},
+	}
 	// Convert tools
 	if len(tools) > 0 {
 		model.Tools = g.convertTools(tools)
@@ -189,19 +176,13 @@ func (g *geminiClient) send(ctx context.Context, messages []message.Message, too
 	attempts := 0
 	for {
 		attempts++
+		var toolCalls []message.ToolCall
 		chat := model.StartChat()
 		chat.History = geminiMessages[:len(geminiMessages)-1] // All but last message

 		lastMsg := geminiMessages[len(geminiMessages)-1]
-		var lastText string
-		for _, part := range lastMsg.Parts {
-			if text, ok := part.(genai.Text); ok {
-				lastText = string(text)
-				break
-			}
-		}

-		resp, err := chat.SendMessage(ctx, genai.Text(lastText))
+		resp, err := chat.SendMessage(ctx, lastMsg.Parts...)
 		// If there is an error we are going to see if we can retry the call
 		if err != nil {
 			retry, after, retryErr := g.shouldRetry(attempts, err)
@@ -209,7 +190,7 @@ func (g *geminiClient) send(ctx context.Context, messages []message.Message, too
 				return nil, retryErr
 			}
 			if retry {
-				logging.WarnPersist("Retrying due to rate limit... attempt %d of %d", logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
+				logging.WarnPersist(fmt.Sprintf("Retrying due to rate limit... attempt %d of %d", attempts, maxRetries), logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
 				select {
 				case <-ctx.Done():
 					return nil, ctx.Err()
@@ -221,7 +202,6 @@ func (g *geminiClient) send(ctx context.Context, messages []message.Message, too
 		}

 		content := ""
-		var toolCalls []message.ToolCall

 		if len(resp.Candidates) > 0 && resp.Candidates[0].Content != nil {
 			for _, part := range resp.Candidates[0].Content.Parts {
@@ -232,20 +212,28 @@ func (g *geminiClient) send(ctx context.Context, messages []message.Message, too
 					id := "call_" + uuid.New().String()
 					args, _ := json.Marshal(p.Args)
 					toolCalls = append(toolCalls, message.ToolCall{
-						ID:    id,
-						Name:  p.Name,
-						Input: string(args),
-						Type:  "function",
+						ID:       id,
+						Name:     p.Name,
+						Input:    string(args),
+						Type:     "function",
+						Finished: true,
 					})
 				}
 			}
 		}
+		finishReason := message.FinishReasonEndTurn
+		if len(resp.Candidates) > 0 {
+			finishReason = g.finishReason(resp.Candidates[0].FinishReason)
+		}
+		if len(toolCalls) > 0 {
+			finishReason = message.FinishReasonToolUse
+		}

 		return &ProviderResponse{
 			Content:      content,
 			ToolCalls:    toolCalls,
 			Usage:        g.usage(resp),
-			FinishReason: g.finishReason(resp.Candidates[0].FinishReason),
+			FinishReason: finishReason,
 		}, nil
 	}
 }
@@ -253,7 +241,11 @@ func (g *geminiClient) send(ctx context.Context, messages []message.Message, too
 func (g *geminiClient) stream(ctx context.Context, messages []message.Message, tools []tools.BaseTool) <-chan ProviderEvent {
 	model := g.client.GenerativeModel(g.providerOptions.model.APIModel)
 	model.SetMaxOutputTokens(int32(g.providerOptions.maxTokens))
-
+	model.SystemInstruction = &genai.Content{
+		Parts: []genai.Part{
+			genai.Text(g.providerOptions.systemMessage),
+		},
+	}
 	// Convert tools
 	if len(tools) > 0 {
 		model.Tools = g.convertTools(tools)
@@ -277,18 +269,10 @@ func (g *geminiClient) stream(ctx context.Context, messages []message.Message, t
 		for {
 			attempts++
 			chat := model.StartChat()
-			chat.History = geminiMessages[:len(geminiMessages)-1] // All but last message
-
+			chat.History = geminiMessages[:len(geminiMessages)-1]
 			lastMsg := geminiMessages[len(geminiMessages)-1]
-			var lastText string
-			for _, part := range lastMsg.Parts {
-				if text, ok := part.(genai.Text); ok {
-					lastText = string(text)
-					break
-				}
-			}

-			iter := chat.SendMessageStream(ctx, genai.Text(lastText))
+			iter := chat.SendMessageStream(ctx, lastMsg.Parts...)

 			currentContent := ""
 			toolCalls := []message.ToolCall{}
@@ -308,7 +292,7 @@ func (g *geminiClient) stream(ctx context.Context, messages []message.Message, t
 						return
 					}
 					if retry {
-						logging.WarnPersist("Retrying due to rate limit... attempt %d of %d", logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
+						logging.WarnPersist(fmt.Sprintf("Retrying due to rate limit... attempt %d of %d", attempts, maxRetries), logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
 						select {
 						case <-ctx.Done():
 							if ctx.Err() != nil {
@@ -331,23 +315,23 @@ func (g *geminiClient) stream(ctx context.Context, messages []message.Message, t
 					for _, part := range resp.Candidates[0].Content.Parts {
 						switch p := part.(type) {
 						case genai.Text:
-							newText := string(p)
-							delta := newText[len(currentContent):]
+							delta := string(p)
 							if delta != "" {
 								eventChan <- ProviderEvent{
 									Type:    EventContentDelta,
 									Content: delta,
 								}
-								currentContent = newText
+								currentContent += delta
 							}
 						case genai.FunctionCall:
 							id := "call_" + uuid.New().String()
 							args, _ := json.Marshal(p.Args)
 							newCall := message.ToolCall{
-								ID:    id,
-								Name:  p.Name,
-								Input: string(args),
-								Type:  "function",
+								ID:       id,
+								Name:     p.Name,
+								Input:    string(args),
+								Type:     "function",
+								Finished: true,
 							}

 							isNew := true
@@ -369,37 +353,26 @@ func (g *geminiClient) stream(ctx context.Context, messages []message.Message, t
 			eventChan <- ProviderEvent{Type: EventContentStop}

 			if finalResp != nil {
+
+				finishReason := message.FinishReasonEndTurn
+				if len(finalResp.Candidates) > 0 {
+					finishReason = g.finishReason(finalResp.Candidates[0].FinishReason)
+				}
+				if len(toolCalls) > 0 {
+					finishReason = message.FinishReasonToolUse
+				}
 				eventChan <- ProviderEvent{
 					Type: EventComplete,
 					Response: &ProviderResponse{
 						Content:      currentContent,
 						ToolCalls:    toolCalls,
 						Usage:        g.usage(finalResp),
-						FinishReason: g.finishReason(finalResp.Candidates[0].FinishReason),
+						FinishReason: finishReason,
 					},
 				}
 				return
 			}

-			// If we get here, we need to retry
-			if attempts > maxRetries {
-				eventChan <- ProviderEvent{
-					Type:  EventError,
-					Error: fmt.Errorf("maximum retry attempts reached: %d retries", maxRetries),
-				}
-				return
-			}
-
-			// Wait before retrying
-			select {
-			case <-ctx.Done():
-				if ctx.Err() != nil {
-					eventChan <- ProviderEvent{Type: EventError, Error: ctx.Err()}
-				}
-				return
-			case <-time.After(time.Duration(2000*(1<<(attempts-1))) * time.Millisecond):
-				continue
-			}
 		}
 	}()

--- a/internal/llm/provider/openai.go
+++ b/internal/llm/provider/openai.go
@@ -8,19 +8,20 @@ import (
 	"io"
 	"time"

+	"github.com/openai/openai-go"
+	"github.com/openai/openai-go/option"
+	"github.com/openai/openai-go/shared"
 	"github.com/opencode-ai/opencode/internal/config"
 	"github.com/opencode-ai/opencode/internal/llm/tools"
 	"github.com/opencode-ai/opencode/internal/logging"
 	"github.com/opencode-ai/opencode/internal/message"
-	"github.com/openai/openai-go"
-	"github.com/openai/openai-go/option"
-	"github.com/openai/openai-go/shared"
 )

 type openaiOptions struct {
 	baseURL         string
 	disableCache    bool
 	reasoningEffort string
+	extraHeaders    map[string]string
 }

 type OpenAIOption func(*openaiOptions)
@@ -49,6 +50,12 @@ func newOpenAIClient(opts providerClientOptions) OpenAIClient {
 		openaiClientOptions = append(openaiClientOptions, option.WithBaseURL(openaiOpts.baseURL))
 	}

+	if openaiOpts.extraHeaders != nil {
+		for key, value := range openaiOpts.extraHeaders {
+			openaiClientOptions = append(openaiClientOptions, option.WithHeader(key, value))
+		}
+	}
+
 	client := openai.NewClient(openaiClientOptions...)
 	return &openaiClient{
 		providerOptions: opts,
@@ -188,7 +195,7 @@ func (o *openaiClient) send(ctx context.Context, messages []message.Message, too
 				return nil, retryErr
 			}
 			if retry {
-				logging.WarnPersist("Retrying due to rate limit... attempt %d of %d", logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
+				logging.WarnPersist(fmt.Sprintf("Retrying due to rate limit... attempt %d of %d", attempts, maxRetries), logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
 				select {
 				case <-ctx.Done():
 					return nil, ctx.Err()
@@ -204,11 +211,18 @@ func (o *openaiClient) send(ctx context.Context, messages []message.Message, too
 			content = openaiResponse.Choices[0].Message.Content
 		}

+		toolCalls := o.toolCalls(*openaiResponse)
+		finishReason := o.finishReason(string(openaiResponse.Choices[0].FinishReason))
+
+		if len(toolCalls) > 0 {
+			finishReason = message.FinishReasonToolUse
+		}
+
 		return &ProviderResponse{
 			Content:      content,
-			ToolCalls:    o.toolCalls(*openaiResponse),
+			ToolCalls:    toolCalls,
 			Usage:        o.usage(*openaiResponse),
-			FinishReason: o.finishReason(string(openaiResponse.Choices[0].FinishReason)),
+			FinishReason: finishReason,
 		}, nil
 	}
 }
@@ -267,13 +281,19 @@ func (o *openaiClient) stream(ctx context.Context, messages []message.Message, t
 			err := openaiStream.Err()
 			if err == nil || errors.Is(err, io.EOF) {
 				// Stream completed successfully
+				finishReason := o.finishReason(string(acc.ChatCompletion.Choices[0].FinishReason))
+
+				if len(toolCalls) > 0 {
+					finishReason = message.FinishReasonToolUse
+				}
+
 				eventChan <- ProviderEvent{
 					Type: EventComplete,
 					Response: &ProviderResponse{
 						Content:      currentContent,
 						ToolCalls:    toolCalls,
 						Usage:        o.usage(acc.ChatCompletion),
-						FinishReason: o.finishReason(string(acc.ChatCompletion.Choices[0].FinishReason)),
+						FinishReason: finishReason,
 					},
 				}
 				close(eventChan)
@@ -288,7 +308,7 @@ func (o *openaiClient) stream(ctx context.Context, messages []message.Message, t
 				return
 			}
 			if retry {
-				logging.WarnPersist("Retrying due to rate limit... attempt %d of %d", logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
+				logging.WarnPersist(fmt.Sprintf("Retrying due to rate limit... attempt %d of %d", attempts, maxRetries), logging.PersistTimeArg, time.Millisecond*time.Duration(after+100))
 				select {
 				case <-ctx.Done():
 					// context cancelled
@@ -375,6 +395,12 @@ func WithOpenAIBaseURL(baseURL string) OpenAIOption {
 	}
 }

+func WithOpenAIExtraHeaders(headers map[string]string) OpenAIOption {
+	return func(options *openaiOptions) {
+		options.extraHeaders = headers
+	}
+}
+
 func WithOpenAIDisableCache() OpenAIOption {
 	return func(options *openaiOptions) {
 		options.disableCache = true
--- a/internal/llm/provider/provider.go
+++ b/internal/llm/provider/provider.go
@@ -107,6 +107,31 @@ func NewProvider(providerName models.ModelProvider, opts ...ProviderClientOption
 			options: clientOptions,
 			client:  newBedrockClient(clientOptions),
 		}, nil
+	case models.ProviderGROQ:
+		clientOptions.openaiOptions = append(clientOptions.openaiOptions,
+			WithOpenAIBaseURL("https://api.groq.com/openai/v1"),
+		)
+		return &baseProvider[OpenAIClient]{
+			options: clientOptions,
+			client:  newOpenAIClient(clientOptions),
+		}, nil
+	case models.ProviderAzure:
+		return &baseProvider[AzureClient]{
+			options: clientOptions,
+			client:  newAzureClient(clientOptions),
+		}, nil
+	case models.ProviderOpenRouter:
+		clientOptions.openaiOptions = append(clientOptions.openaiOptions,
+			WithOpenAIBaseURL("https://openrouter.ai/api/v1"),
+			WithOpenAIExtraHeaders(map[string]string{
+				"HTTP-Referer": "opencode.ai",
+				"X-Title":      "OpenCode",
+			}),
+		)
+		return &baseProvider[OpenAIClient]{
+			options: clientOptions,
+			client:  newOpenAIClient(clientOptions),
+		}, nil
 	case models.ProviderMock:
 		// TODO: implement mock client for test
 		panic("not implemented")
--- a/internal/llm/tools/glob.go
+++ b/internal/llm/tools/glob.go
@@ -1,11 +1,13 @@
 package tools

 import (
+	"bytes"
 	"context"
 	"encoding/json"
 	"fmt"
 	"io/fs"
 	"os"
+	"os/exec"
 	"path/filepath"
 	"sort"
 	"strings"
@@ -132,14 +134,73 @@ func (g *globTool) Run(ctx context.Context, call ToolCall) (ToolResponse, error)
 }

 func globFiles(pattern, searchPath string, limit int) ([]string, bool, error) {
-	if !strings.HasPrefix(pattern, "/") && !strings.HasPrefix(pattern, searchPath) {
-		if !strings.HasSuffix(searchPath, "/") {
-			searchPath += "/"
-		}
-		pattern = searchPath + pattern
+	matches, err := globWithRipgrep(pattern, searchPath, limit)
+	if err == nil {
+		return matches, len(matches) >= limit, nil
 	}

-	fsys := os.DirFS("/")
+	return globWithDoublestar(pattern, searchPath, limit)
+}
+
+func globWithRipgrep(
+	pattern, searchRoot string,
+	limit int,
+) ([]string, error) {
+	if searchRoot == "" {
+		searchRoot = "."
+	}
+
+	rgBin, err := exec.LookPath("rg")
+	if err != nil {
+		return nil, fmt.Errorf("ripgrep not found in $PATH: %w", err)
+	}
+
+	if !filepath.IsAbs(pattern) && !strings.HasPrefix(pattern, "/") {
+		pattern = "/" + pattern
+	}
+
+	args := []string{
+		"--files",
+		"--null",
+		"--glob", pattern,
+		"-L",
+	}
+
+	cmd := exec.Command(rgBin, args...)
+	cmd.Dir = searchRoot
+
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		if ee, ok := err.(*exec.ExitError); ok && ee.ExitCode() == 1 {
+			return nil, nil
+		}
+		return nil, fmt.Errorf("ripgrep: %w\n%s", err, out)
+	}
+
+	var matches []string
+	for _, p := range bytes.Split(out, []byte{0}) {
+		if len(p) == 0 {
+			continue
+		}
+		abs := filepath.Join(searchRoot, string(p))
+		if skipHidden(abs) {
+			continue
+		}
+		matches = append(matches, abs)
+	}
+
+	sort.SliceStable(matches, func(i, j int) bool {
+		return len(matches[i]) < len(matches[j])
+	})
+
+	if len(matches) > limit {
+		matches = matches[:limit]
+	}
+	return matches, nil
+}
+
+func globWithDoublestar(pattern, searchPath string, limit int) ([]string, bool, error) {
+	fsys := os.DirFS(searchPath)

 	relPattern := strings.TrimPrefix(pattern, "/")

@@ -158,7 +219,11 @@ func globFiles(pattern, searchPath string, limit int) ([]string, bool, error) {
 			return nil // Skip files we can't access
 		}

-		absPath := "/" + path // Restore absolute path
+		absPath := path // Restore absolute path
+		if !strings.HasPrefix(absPath, searchPath) {
+			absPath = filepath.Join(searchPath, absPath)
+		}
+
 		matches = append(matches, fileInfo{
 			path:    absPath,
 			modTime: info.ModTime(),
--- a/internal/llm/tools/shell/shell.go
+++ b/internal/llm/tools/shell/shell.go
@@ -47,7 +47,9 @@ func GetPersistentShell(workingDir string) *PersistentShell {
 		shellInstance = newPersistentShell(workingDir)
 	})

-	if !shellInstance.isAlive {
+	if shellInstance == nil {
+		shellInstance = newPersistentShell(workingDir)
+	} else if !shellInstance.isAlive {
 		shellInstance = newPersistentShell(shellInstance.cwd)
 	}

--- a/internal/lsp/client.go
+++ b/internal/lsp/client.go
@@ -389,7 +389,7 @@ func (c *Client) openKeyConfigFiles(ctx context.Context) {
 			filepath.Join(workDir, "package.json"),
 			filepath.Join(workDir, "jsconfig.json"),
 		}
-		
+
 		// Also find and open a few TypeScript files to help the server initialize
 		c.openTypeScriptFiles(ctx, workDir)
 	case ServerTypeGo:
@@ -547,12 +547,12 @@ func (c *Client) openTypeScriptFiles(ctx context.Context, workDir string) {
 // shouldSkipDir returns true if the directory should be skipped during file search
 func shouldSkipDir(path string) bool {
 	dirName := filepath.Base(path)
-	
+
 	// Skip hidden directories
 	if strings.HasPrefix(dirName, ".") {
 		return true
 	}
-	
+
 	// Skip common directories that won't contain relevant source files
 	skipDirs := map[string]bool{
 		"node_modules": true,
@@ -562,7 +562,7 @@ func shouldSkipDir(path string) bool {
 		"vendor":       true,
 		"target":       true,
 	}
-	
+
 	return skipDirs[dirName]
 }

@@ -776,3 +776,10 @@ func (c *Client) GetDiagnosticsForFile(ctx context.Context, filepath string) ([]

 	return diagnostics, nil
 }
+
+// ClearDiagnosticsForURI removes diagnostics for a specific URI from the cache
+func (c *Client) ClearDiagnosticsForURI(uri protocol.DocumentUri) {
+	c.diagnosticsMu.Lock()
+	defer c.diagnosticsMu.Unlock()
+	delete(c.diagnostics, uri)
+}
--- a/internal/lsp/watcher/watcher.go
+++ b/internal/lsp/watcher/watcher.go
@@ -643,7 +643,9 @@ func (w *WorkspaceWatcher) debounceHandleFileEvent(ctx context.Context, uri stri
 func (w *WorkspaceWatcher) handleFileEvent(ctx context.Context, uri string, changeType protocol.FileChangeType) {
 	// If the file is open and it's a change event, use didChange notification
 	filePath := uri[7:] // Remove "file://" prefix
-	if changeType == protocol.FileChangeType(protocol.Changed) && w.client.IsFileOpen(filePath) {
+	if changeType == protocol.FileChangeType(protocol.Deleted) {
+		w.client.ClearDiagnosticsForURI(protocol.DocumentUri(uri))
+	} else if changeType == protocol.FileChangeType(protocol.Changed) && w.client.IsFileOpen(filePath) {
 		err := w.client.NotifyChange(ctx, filePath)
 		if err != nil {
 			logging.Error("Error notifying change", "error", err)
--- a/internal/permission/permission.go
+++ b/internal/permission/permission.go
@@ -5,7 +5,6 @@ import (
 	"path/filepath"
 	"slices"
 	"sync"
-	"time"

 	"github.com/google/uuid"
 	"github.com/opencode-ai/opencode/internal/config"
@@ -104,12 +103,8 @@ func (s *permissionService) Request(opts CreatePermissionRequest) bool {
 	s.Publish(pubsub.CreatedEvent, permission)

 	// Wait for the response with a timeout
-	select {
-	case resp := <-respCh:
-		return resp
-	case <-time.After(10 * time.Minute):
-		return false
-	}
+	resp := <-respCh
+	return resp
 }

 func (s *permissionService) AutoApproveSession(sessionID string) {
--- a/internal/tui/components/dialog/models.go
+++ b/internal/tui/components/dialog/models.go
@@ -0,0 +1,363 @@
+package dialog
+
+import (
+	"fmt"
+	"slices"
+	"strings"
+
+	"github.com/charmbracelet/bubbles/key"
+	tea "github.com/charmbracelet/bubbletea"
+	"github.com/charmbracelet/lipgloss"
+	"github.com/opencode-ai/opencode/internal/config"
+	"github.com/opencode-ai/opencode/internal/llm/models"
+	"github.com/opencode-ai/opencode/internal/tui/layout"
+	"github.com/opencode-ai/opencode/internal/tui/styles"
+	"github.com/opencode-ai/opencode/internal/tui/util"
+)
+
+const (
+	numVisibleModels = 10
+	maxDialogWidth   = 40
+)
+
+// ModelSelectedMsg is sent when a model is selected
+type ModelSelectedMsg struct {
+	Model models.Model
+}
+
+// CloseModelDialogMsg is sent when a model is selected
+type CloseModelDialogMsg struct{}
+
+// ModelDialog interface for the model selection dialog
+type ModelDialog interface {
+	tea.Model
+	layout.Bindings
+}
+
+type modelDialogCmp struct {
+	models             []models.Model
+	provider           models.ModelProvider
+	availableProviders []models.ModelProvider
+
+	selectedIdx     int
+	width           int
+	height          int
+	scrollOffset    int
+	hScrollOffset   int
+	hScrollPossible bool
+}
+
+type modelKeyMap struct {
+	Up     key.Binding
+	Down   key.Binding
+	Left   key.Binding
+	Right  key.Binding
+	Enter  key.Binding
+	Escape key.Binding
+	J      key.Binding
+	K      key.Binding
+	H      key.Binding
+	L      key.Binding
+}
+
+var modelKeys = modelKeyMap{
+	Up: key.NewBinding(
+		key.WithKeys("up"),
+		key.WithHelp("↑", "previous model"),
+	),
+	Down: key.NewBinding(
+		key.WithKeys("down"),
+		key.WithHelp("↓", "next model"),
+	),
+	Left: key.NewBinding(
+		key.WithKeys("left"),
+		key.WithHelp("←", "scroll left"),
+	),
+	Right: key.NewBinding(
+		key.WithKeys("right"),
+		key.WithHelp("→", "scroll right"),
+	),
+	Enter: key.NewBinding(
+		key.WithKeys("enter"),
+		key.WithHelp("enter", "select model"),
+	),
+	Escape: key.NewBinding(
+		key.WithKeys("esc"),
+		key.WithHelp("esc", "close"),
+	),
+	J: key.NewBinding(
+		key.WithKeys("j"),
+		key.WithHelp("j", "next model"),
+	),
+	K: key.NewBinding(
+		key.WithKeys("k"),
+		key.WithHelp("k", "previous model"),
+	),
+	H: key.NewBinding(
+		key.WithKeys("h"),
+		key.WithHelp("h", "scroll left"),
+	),
+	L: key.NewBinding(
+		key.WithKeys("l"),
+		key.WithHelp("l", "scroll right"),
+	),
+}
+
+func (m *modelDialogCmp) Init() tea.Cmd {
+	m.setupModels()
+	return nil
+}
+
+func (m *modelDialogCmp) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
+	switch msg := msg.(type) {
+	case tea.KeyMsg:
+		switch {
+		case key.Matches(msg, modelKeys.Up) || key.Matches(msg, modelKeys.K):
+			m.moveSelectionUp()
+		case key.Matches(msg, modelKeys.Down) || key.Matches(msg, modelKeys.J):
+			m.moveSelectionDown()
+		case key.Matches(msg, modelKeys.Left) || key.Matches(msg, modelKeys.H):
+			if m.hScrollPossible {
+				m.switchProvider(-1)
+			}
+		case key.Matches(msg, modelKeys.Right) || key.Matches(msg, modelKeys.L):
+			if m.hScrollPossible {
+				m.switchProvider(1)
+			}
+		case key.Matches(msg, modelKeys.Enter):
+			util.ReportInfo(fmt.Sprintf("selected model: %s", m.models[m.selectedIdx].Name))
+			return m, util.CmdHandler(ModelSelectedMsg{Model: m.models[m.selectedIdx]})
+		case key.Matches(msg, modelKeys.Escape):
+			return m, util.CmdHandler(CloseModelDialogMsg{})
+		}
+	case tea.WindowSizeMsg:
+		m.width = msg.Width
+		m.height = msg.Height
+	}
+
+	return m, nil
+}
+
+// moveSelectionUp moves the selection up or wraps to bottom
+func (m *modelDialogCmp) moveSelectionUp() {
+	if m.selectedIdx > 0 {
+		m.selectedIdx--
+	} else {
+		m.selectedIdx = len(m.models) - 1
+		m.scrollOffset = max(0, len(m.models)-numVisibleModels)
+	}
+
+	// Keep selection visible
+	if m.selectedIdx < m.scrollOffset {
+		m.scrollOffset = m.selectedIdx
+	}
+}
+
+// moveSelectionDown moves the selection down or wraps to top
+func (m *modelDialogCmp) moveSelectionDown() {
+	if m.selectedIdx < len(m.models)-1 {
+		m.selectedIdx++
+	} else {
+		m.selectedIdx = 0
+		m.scrollOffset = 0
+	}
+
+	// Keep selection visible
+	if m.selectedIdx >= m.scrollOffset+numVisibleModels {
+		m.scrollOffset = m.selectedIdx - (numVisibleModels - 1)
+	}
+}
+
+func (m *modelDialogCmp) switchProvider(offset int) {
+	newOffset := m.hScrollOffset + offset
+
+	// Ensure we stay within bounds
+	if newOffset < 0 {
+		newOffset = len(m.availableProviders) - 1
+	}
+	if newOffset >= len(m.availableProviders) {
+		newOffset = 0
+	}
+
+	m.hScrollOffset = newOffset
+	m.provider = m.availableProviders[m.hScrollOffset]
+	m.setupModelsForProvider(m.provider)
+}
+
+func (m *modelDialogCmp) View() string {
+	// Capitalize first letter of provider name
+	providerName := strings.ToUpper(string(m.provider)[:1]) + string(m.provider[1:])
+	title := styles.BaseStyle.
+		Foreground(styles.PrimaryColor).
+		Bold(true).
+		Width(maxDialogWidth).
+		Padding(0, 0, 1).
+		Render(fmt.Sprintf("Select %s Model", providerName))
+
+	// Render visible models
+	endIdx := min(m.scrollOffset+numVisibleModels, len(m.models))
+	modelItems := make([]string, 0, endIdx-m.scrollOffset)
+
+	for i := m.scrollOffset; i < endIdx; i++ {
+		itemStyle := styles.BaseStyle.Width(maxDialogWidth)
+		if i == m.selectedIdx {
+			itemStyle = itemStyle.Background(styles.PrimaryColor).
+				Foreground(styles.Background).Bold(true)
+		}
+		modelItems = append(modelItems, itemStyle.Render(m.models[i].Name))
+	}
+
+	scrollIndicator := m.getScrollIndicators(maxDialogWidth)
+
+	content := lipgloss.JoinVertical(
+		lipgloss.Left,
+		title,
+		styles.BaseStyle.Width(maxDialogWidth).Render(lipgloss.JoinVertical(lipgloss.Left, modelItems...)),
+		scrollIndicator,
+	)
+
+	return styles.BaseStyle.Padding(1, 2).
+		Border(lipgloss.RoundedBorder()).
+		BorderBackground(styles.Background).
+		BorderForeground(styles.ForgroundDim).
+		Width(lipgloss.Width(content) + 4).
+		Render(content)
+}
+
+func (m *modelDialogCmp) getScrollIndicators(maxWidth int) string {
+	var indicator string
+
+	if len(m.models) > numVisibleModels {
+		if m.scrollOffset > 0 {
+			indicator += "↑ "
+		}
+		if m.scrollOffset+numVisibleModels < len(m.models) {
+			indicator += "↓ "
+		}
+	}
+
+	if m.hScrollPossible {
+		if m.hScrollOffset > 0 {
+			indicator = "← " + indicator
+		}
+		if m.hScrollOffset < len(m.availableProviders)-1 {
+			indicator += "→"
+		}
+	}
+
+	if indicator == "" {
+		return ""
+	}
+
+	return styles.BaseStyle.
+		Foreground(styles.PrimaryColor).
+		Width(maxWidth).
+		Align(lipgloss.Right).
+		Bold(true).
+		Render(indicator)
+}
+
+func (m *modelDialogCmp) BindingKeys() []key.Binding {
+	return layout.KeyMapToSlice(modelKeys)
+}
+
+func (m *modelDialogCmp) setupModels() {
+	cfg := config.Get()
+
+	m.availableProviders = getEnabledProviders(cfg)
+	m.hScrollPossible = len(m.availableProviders) > 1
+
+	agentCfg := cfg.Agents[config.AgentCoder]
+	selectedModelId := agentCfg.Model
+	modelInfo := models.SupportedModels[selectedModelId]
+
+	m.provider = modelInfo.Provider
+	m.hScrollOffset = findProviderIndex(m.availableProviders, m.provider)
+
+	m.setupModelsForProvider(m.provider)
+}
+
+func getEnabledProviders(cfg *config.Config) []models.ModelProvider {
+	var providers []models.ModelProvider
+	for providerId, provider := range cfg.Providers {
+		if !provider.Disabled {
+			providers = append(providers, providerId)
+		}
+	}
+
+	// Sort by provider popularity
+	slices.SortFunc(providers, func(a, b models.ModelProvider) int {
+		rA := models.ProviderPopularity[a]
+		rB := models.ProviderPopularity[b]
+
+		// models not included in popularity ranking default to last
+		if rA == 0 {
+			rA = 999
+		}
+		if rB == 0 {
+			rB = 999
+		}
+		return rA - rB
+	})
+	return providers
+}
+
+// findProviderIndex returns the index of the provider in the list, or -1 if not found
+func findProviderIndex(providers []models.ModelProvider, provider models.ModelProvider) int {
+	for i, p := range providers {
+		if p == provider {
+			return i
+		}
+	}
+	return -1
+}
+
+func (m *modelDialogCmp) setupModelsForProvider(provider models.ModelProvider) {
+	cfg := config.Get()
+	agentCfg := cfg.Agents[config.AgentCoder]
+	selectedModelId := agentCfg.Model
+
+	m.provider = provider
+	m.models = getModelsForProvider(provider)
+	m.selectedIdx = 0
+	m.scrollOffset = 0
+
+	// Try to select the current model if it belongs to this provider
+	if provider == models.SupportedModels[selectedModelId].Provider {
+		for i, model := range m.models {
+			if model.ID == selectedModelId {
+				m.selectedIdx = i
+				// Adjust scroll position to keep selected model visible
+				if m.selectedIdx >= numVisibleModels {
+					m.scrollOffset = m.selectedIdx - (numVisibleModels - 1)
+				}
+				break
+			}
+		}
+	}
+}
+
+func getModelsForProvider(provider models.ModelProvider) []models.Model {
+	var providerModels []models.Model
+	for _, model := range models.SupportedModels {
+		if model.Provider == provider {
+			providerModels = append(providerModels, model)
+		}
+	}
+
+	// reverse alphabetical order (if llm naming was consistent latest would appear first)
+	slices.SortFunc(providerModels, func(a, b models.Model) int {
+		if a.Name > b.Name {
+			return -1
+		} else if a.Name < b.Name {
+			return 1
+		}
+		return 0
+	})
+
+	return providerModels
+}
+
+func NewModelDialogCmp() ModelDialog {
+	return &modelDialogCmp{}
+}
--- a/internal/tui/layout/overlay.go
+++ b/internal/tui/layout/overlay.go
@@ -1,16 +1,15 @@
 package layout

 import (
-	"bytes"
 	"strings"

 	"github.com/charmbracelet/lipgloss"
-	"github.com/opencode-ai/opencode/internal/tui/styles"
-	"github.com/opencode-ai/opencode/internal/tui/util"
-	"github.com/mattn/go-runewidth"
+	chAnsi "github.com/charmbracelet/x/ansi"
 	"github.com/muesli/ansi"
 	"github.com/muesli/reflow/truncate"
 	"github.com/muesli/termenv"
+	"github.com/opencode-ai/opencode/internal/tui/styles"
+	"github.com/opencode-ai/opencode/internal/tui/util"
 )

 // Most of this code is borrowed from
@@ -117,42 +116,7 @@ func PlaceOverlay(
 // cutLeft cuts printable characters from the left.
 // This function is heavily based on muesli's ansi and truncate packages.
 func cutLeft(s string, cutWidth int) string {
-	var (
-		pos    int
-		isAnsi bool
-		ab     bytes.Buffer
-		b      bytes.Buffer
-	)
-	for _, c := range s {
-		var w int
-		if c == ansi.Marker || isAnsi {
-			isAnsi = true
-			ab.WriteRune(c)
-			if ansi.IsTerminator(c) {
-				isAnsi = false
-				if bytes.HasSuffix(ab.Bytes(), []byte("[0m")) {
-					ab.Reset()
-				}
-			}
-		} else {
-			w = runewidth.RuneWidth(c)
-		}
-
-		if pos >= cutWidth {
-			if b.Len() == 0 {
-				if ab.Len() > 0 {
-					b.Write(ab.Bytes())
-				}
-				if pos-cutWidth > 1 {
-					b.WriteByte(' ')
-					continue
-				}
-			}
-			b.WriteRune(c)
-		}
-		pos += w
-	}
-	return b.String()
+	return chAnsi.Cut(s, cutWidth, lipgloss.Width(s))
 }

 func max(a, b int) int {
--- a/internal/tui/tui.go
+++ b/internal/tui/tui.go
@@ -2,6 +2,7 @@ package tui

 import (
 	"context"
+	"fmt"

 	"github.com/charmbracelet/bubbles/key"
 	tea "github.com/charmbracelet/bubbletea"
@@ -25,6 +26,7 @@ type keyMap struct {
 	Help          key.Binding
 	SwitchSession key.Binding
 	Commands      key.Binding
+	Models        key.Binding
 }

 var keys = keyMap{
@@ -51,6 +53,11 @@ var keys = keyMap{
 		key.WithKeys("ctrl+k"),
 		key.WithHelp("ctrl+k", "commands"),
 	),
+
+	Models: key.NewBinding(
+		key.WithKeys("ctrl+o"),
+		key.WithHelp("ctrl+o", "model selection"),
+	),
 }

 var helpEsc = key.NewBinding(
@@ -93,6 +100,9 @@ type appModel struct {
 	commandDialog     dialog.CommandDialog
 	commands          []dialog.Command

+	showModelDialog bool
+	modelDialog     dialog.ModelDialog
+
 	showInitDialog bool
 	initDialog     dialog.InitDialogCmp
 }
@@ -112,6 +122,8 @@ func (a appModel) Init() tea.Cmd {
 	cmds = append(cmds, cmd)
 	cmd = a.commandDialog.Init()
 	cmds = append(cmds, cmd)
+	cmd = a.modelDialog.Init()
+	cmds = append(cmds, cmd)
 	cmd = a.initDialog.Init()
 	cmds = append(cmds, cmd)

@@ -243,6 +255,20 @@ func (a appModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 		a.showCommandDialog = false
 		return a, nil

+	case dialog.CloseModelDialogMsg:
+		a.showModelDialog = false
+		return a, nil
+
+	case dialog.ModelSelectedMsg:
+		a.showModelDialog = false
+
+		model, err := a.app.CoderAgent.Update(config.AgentCoder, msg.Model.ID)
+		if err != nil {
+			return a, util.ReportError(err)
+		}
+
+		return a, util.ReportInfo(fmt.Sprintf("Model changed to %s", model.Name))
+
 	case dialog.ShowInitDialogMsg:
 		a.showInitDialog = msg.Show
 		return a, nil
@@ -298,6 +324,9 @@ func (a appModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 			if a.showCommandDialog {
 				a.showCommandDialog = false
 			}
+			if a.showModelDialog {
+				a.showModelDialog = false
+			}
 			return a, nil
 		case key.Matches(msg, keys.SwitchSession):
 			if a.currentPage == page.ChatPage && !a.showQuit && !a.showPermissions && !a.showCommandDialog {
@@ -325,6 +354,17 @@ func (a appModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 				return a, nil
 			}
 			return a, nil
+		case key.Matches(msg, keys.Models):
+			if a.showModelDialog {
+				a.showModelDialog = false
+				return a, nil
+			}
+
+			if a.currentPage == page.ChatPage && !a.showQuit && !a.showPermissions && !a.showSessionDialog && !a.showCommandDialog {
+				a.showModelDialog = true
+				return a, nil
+			}
+			return a, nil
 		case key.Matches(msg, logsKeyReturnKey):
 			if a.currentPage == page.LogsPage {
 				return a, a.moveToPage(page.ChatPage)
@@ -405,6 +445,16 @@ func (a appModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 		}
 	}

+	if a.showModelDialog {
+		d, modelCmd := a.modelDialog.Update(msg)
+		a.modelDialog = d.(dialog.ModelDialog)
+		cmds = append(cmds, modelCmd)
+		// Only block key messages send all other messages down
+		if _, ok := msg.(tea.KeyMsg); ok {
+			return a, tea.Batch(cmds...)
+		}
+	}
+
 	if a.showInitDialog {
 		d, initCmd := a.initDialog.Update(msg)
 		a.initDialog = d.(dialog.InitDialogCmp)
@@ -538,6 +588,21 @@ func (a appModel) View() string {
 		)
 	}

+	if a.showModelDialog {
+		overlay := a.modelDialog.View()
+		row := lipgloss.Height(appView) / 2
+		row -= lipgloss.Height(overlay) / 2
+		col := lipgloss.Width(appView) / 2
+		col -= lipgloss.Width(overlay) / 2
+		appView = layout.PlaceOverlay(
+			col,
+			row,
+			overlay,
+			appView,
+			true,
+		)
+	}
+
 	if a.showCommandDialog {
 		overlay := a.commandDialog.View()
 		row := lipgloss.Height(appView) / 2
@@ -577,6 +642,7 @@ func New(app *app.App) tea.Model {
 		quit:          dialog.NewQuitCmp(),
 		sessionDialog: dialog.NewSessionDialogCmp(),
 		commandDialog: dialog.NewCommandDialogCmp(),
+		modelDialog:   dialog.NewModelDialogCmp(),
 		permissions:   dialog.NewPermissionDialogCmp(),
 		initDialog:    dialog.NewInitDialogCmp(),
 		app:           app,
--- a/opencode-schema.json
+++ b/opencode-schema.json
@@ -12,44 +12,75 @@
        "model": {
          "description": "Model ID for the agent",
          "enum": [
-            "gemini-2.0-flash",
            "bedrock.claude-3.7-sonnet",
-            "claude-3-opus",
-            "claude-3.5-sonnet",
-            "gpt-4o-mini",
-            "o1",
-            "o3-mini",
+            "claude-3-haiku",
+            "claude-3.7-sonnet",
+            "claude-3.5-haiku",
+            "o3",
+            "azure.o3",
+            "gpt-4.5-preview",
+            "azure.gpt-4.5-preview",
            "o1-pro",
            "o4-mini",
-            "claude-3-haiku",
-            "gpt-4o",
-            "o3",
-            "gpt-4.1-mini",
-            "gpt-4.5-preview",
-            "gemini-2.5-flash",
-            "claude-3.5-haiku",
+            "azure.o4-mini",
            "gpt-4.1",
-            "gemini-2.0-flash-lite",
-            "claude-3.7-sonnet",
-            "o1-mini",
+            "azure.gpt-4.1",
+            "o3-mini",
+            "azure.o3-mini",
            "gpt-4.1-nano",
-            "gemini-2.5"
+            "azure.gpt-4.1-nano",
+            "gpt-4o-mini",
+            "azure.gpt-4o-mini",
+            "o1",
+            "azure.o1",
+            "gemini-2.5-flash",
+            "qwen-qwq",
+            "meta-llama/llama-4-maverick-17b-128e-instruct",
+            "claude-3-opus",
+            "gpt-4o",
+            "azure.gpt-4o",
+            "gemini-2.0-flash-lite",
+            "gemini-2.0-flash",
+            "deepseek-r1-distill-llama-70b",
+            "llama-3.3-70b-versatile",
+            "claude-3.5-sonnet",
+            "o1-mini",
+            "azure.o1-mini",
+            "gpt-4.1-mini",
+            "azure.gpt-4.1-mini",
+            "gemini-2.5",
+            "meta-llama/llama-4-scout-17b-16e-instruct",
+            "openrouter.deepseek-chat-free",
+            "openrouter.deepseek-r1-free",
+            "openrouter.gpt-4.1",
+            "openrouter.gpt-4.1-mini",
+            "openrouter.gpt-4.1-nano",
+            "openrouter.gpt-4.5-preview",
+            "openrouter.gpt-4o",
+            "openrouter.gpt-4o-mini",
+            "openrouter.o1",
+            "openrouter.o1-pro",
+            "openrouter.o1-mini",
+            "openrouter.o3",
+            "openrouter.o3-mini",
+            "openrouter.o4-mini",
+            "openrouter.gemini-2.5-flash",
+            "openrouter.gemini-2.5",
+            "openrouter.claude-3.5-sonnet",
+            "openrouter.claude-3-haiku",
+            "openrouter.claude-3.7-sonnet",
+            "openrouter.claude-3.5-haiku",
+            "openrouter.claude-3-opus"
          ],
          "type": "string"
        },
        "reasoningEffort": {
          "description": "Reasoning effort for models that support it (OpenAI, Anthropic)",
-          "enum": [
-            "low",
-            "medium",
-            "high"
-          ],
+          "enum": ["low", "medium", "high"],
          "type": "string"
        }
      },
-      "required": [
-        "model"
-      ],
+      "required": ["model"],
      "type": "object"
    }
  },
@@ -67,44 +98,75 @@
          "model": {
            "description": "Model ID for the agent",
            "enum": [
-              "gemini-2.0-flash",
              "bedrock.claude-3.7-sonnet",
-              "claude-3-opus",
-              "claude-3.5-sonnet",
-              "gpt-4o-mini",
-              "o1",
-              "o3-mini",
+              "claude-3-haiku",
+              "claude-3.7-sonnet",
+              "claude-3.5-haiku",
+              "o3",
+              "azure.o3",
+              "gpt-4.5-preview",
+              "azure.gpt-4.5-preview",
              "o1-pro",
              "o4-mini",
-              "claude-3-haiku",
-              "gpt-4o",
-              "o3",
-              "gpt-4.1-mini",
-              "gpt-4.5-preview",
-              "gemini-2.5-flash",
-              "claude-3.5-haiku",
+              "azure.o4-mini",
              "gpt-4.1",
-              "gemini-2.0-flash-lite",
-              "claude-3.7-sonnet",
-              "o1-mini",
+              "azure.gpt-4.1",
+              "o3-mini",
+              "azure.o3-mini",
              "gpt-4.1-nano",
-              "gemini-2.5"
+              "azure.gpt-4.1-nano",
+              "gpt-4o-mini",
+              "azure.gpt-4o-mini",
+              "o1",
+              "azure.o1",
+              "gemini-2.5-flash",
+              "qwen-qwq",
+              "meta-llama/llama-4-maverick-17b-128e-instruct",
+              "claude-3-opus",
+              "gpt-4o",
+              "azure.gpt-4o",
+              "gemini-2.0-flash-lite",
+              "gemini-2.0-flash",
+              "deepseek-r1-distill-llama-70b",
+              "llama-3.3-70b-versatile",
+              "claude-3.5-sonnet",
+              "o1-mini",
+              "azure.o1-mini",
+              "gpt-4.1-mini",
+              "azure.gpt-4.1-mini",
+              "gemini-2.5",
+              "meta-llama/llama-4-scout-17b-16e-instruct",
+              "openrouter.deepseek-chat-free",
+              "openrouter.deepseek-r1-free",
+              "openrouter.gpt-4.1",
+              "openrouter.gpt-4.1-mini",
+              "openrouter.gpt-4.1-nano",
+              "openrouter.gpt-4.5-preview",
+              "openrouter.gpt-4o",
+              "openrouter.gpt-4o-mini",
+              "openrouter.o1",
+              "openrouter.o1-pro",
+              "openrouter.o1-mini",
+              "openrouter.o3",
+              "openrouter.o3-mini",
+              "openrouter.o4-mini",
+              "openrouter.gemini-2.5-flash",
+              "openrouter.gemini-2.5",
+              "openrouter.claude-3.5-sonnet",
+              "openrouter.claude-3-haiku",
+              "openrouter.claude-3.7-sonnet",
+              "openrouter.claude-3.5-haiku",
+              "openrouter.claude-3-opus"
            ],
            "type": "string"
          },
          "reasoningEffort": {
            "description": "Reasoning effort for models that support it (OpenAI, Anthropic)",
-            "enum": [
-              "low",
-              "medium",
-              "high"
-            ],
+            "enum": ["low", "medium", "high"],
            "type": "string"
          }
        },
-        "required": [
-          "model"
-        ],
+        "required": ["model"],
        "type": "object"
      },
      "description": "Agent configurations",
@@ -121,6 +183,26 @@
      },
      "type": "object"
    },
+    "contextPaths": {
+      "default": [
+        ".github/copilot-instructions.md",
+        ".cursorrules",
+        ".cursor/rules/",
+        "CLAUDE.md",
+        "CLAUDE.local.md",
+        "opencode.md",
+        "opencode.local.md",
+        "OpenCode.md",
+        "OpenCode.local.md",
+        "OPENCODE.md",
+        "OPENCODE.local.md"
+      ],
+      "description": "Context paths for the application",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
    "data": {
      "description": "Storage configuration",
      "properties": {
@@ -130,9 +212,7 @@
          "type": "string"
        }
      },
-      "required": [
-        "directory"
-      ],
+      "required": ["directory"],
      "type": "object"
    },
    "debug": {
@@ -170,9 +250,7 @@
            "type": "object"
          }
        },
-        "required": [
-          "command"
-        ],
+        "required": ["command"],
        "type": "object"
      },
      "description": "Language Server Protocol configurations",
@@ -210,10 +288,7 @@
          "type": {
            "default": "stdio",
            "description": "Type of MCP server",
-            "enum": [
-              "stdio",
-              "sse"
-            ],
+            "enum": ["stdio", "sse"],
            "type": "string"
          },
          "url": {
@@ -221,9 +296,7 @@
            "type": "string"
          }
        },
-        "required": [
-          "command"
-        ],
+        "required": ["command"],
        "type": "object"
      },
      "description": "Model Control Protocol server configurations",
@@ -249,7 +322,9 @@
              "openai",
              "gemini",
              "groq",
-              "bedrock"
+              "bedrock",
+              "azure",
+              "openrouter"
            ],
            "type": "string"
          }
Author	SHA1	Message	Date
Isaac Scarrott	98e2910e82	feat: Add support for OpenRouter (#92 ) * Add support for OpenRouter as a new model provider - Introduced `ProviderOpenRouter` in the `models` package. - Added OpenRouter-specific models, including `GPT41`, `GPT41Mini`, `GPT4o`, and others, with their configurations and costs. - Updated `generateSchema` to include OpenRouter as a provider. - Added OpenRouter-specific environment variable handling (`OPENROUTER_API_KEY`) in `config.go`. - Implemented default model settings for OpenRouter agents in `setDefaultModelForAgent`. - Updated `getProviderAPIKey` to retrieve the OpenRouter API key. - Extended `SupportedModels` to include OpenRouter models. - Added OpenRouter client initialization in the `provider` package. - Modified `processGeneration` to handle `FinishReasonUnknown` in addition to `FinishReasonToolUse`. * [feature/openrouter-provider] Add new models and provider to schema - Added "deepseek-chat-free" and "deepseek-r1-free" to the list of supported models in `opencode-schema.json`. * [feature/openrouter-provider] Add OpenRouter provider support and integrate new models - Updated README.md to include OpenRouter as a supported provider and its configuration details. - Added `OPENROUTER_API_KEY` to environment variable configuration. - Introduced OpenRouter-specific models in `internal/llm/models/openrouter.go` with mappings to existing cost and token configurations. - Updated `internal/config/config.go` to set default models for OpenRouter agents. - Extended `opencode-schema.json` to include OpenRouter models in the schema definitions. - Refactored model IDs and names to align with OpenRouter naming conventions. * [feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider - Simplified finish reason check in `agent.go` by removing redundant variable assignment. - Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present. - Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider. [feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider - Simplified finish reason check in `agent.go` by removing redundant variable assignment. - Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present. - Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider. * [feature/openrouter-provider] Add support for custom headers in OpenAI client configuration - Introduced a new `extraHeaders` field in the `openaiOptions` struct to allow specifying additional HTTP headers. - Added logic in `newOpenAIClient` to apply `extraHeaders` to the OpenAI client configuration. - Implemented a new option function `WithOpenAIExtraHeaders` to set custom headers in `openaiOptions`. - Updated the OpenRouter provider configuration in `NewProvider` to include default headers (`HTTP-Referer` and `X-Title`) for OpenRouter API requests. * Update OpenRouter model config and remove unsupported models * [feature/openrouter-provider] Update OpenRouter models and default configurations - Added new OpenRouter models: `claude-3.5-sonnet`, `claude-3-haiku`, `claude-3.7-sonnet`, `claude-3.5-haiku`, and `claude-3-opus` in `openrouter.go`. - Updated default agent models in `config.go`: - `agents.coder.model` now uses `claude-3.7-sonnet`. - `agents.task.model` now uses `claude-3.7-sonnet`. - `agents.title.model` now uses `claude-3.5-haiku`. - Updated `opencode-schema.json` to include the new models in the allowed list for schema validation. - Adjusted logic in `setDefaultModelForAgent` to reflect the new default models. * [feature/openrouter-provider] Remove unused ProviderEvent emission in stream function The changes remove the emission of a `ProviderEvent` with type `EventContentStop` in the `stream` function of the `openaiClient` implementation. This event was sent upon successful stream completion but is no longer used.	2025-04-29 13:56:49 +02:00
Kujtim Hoxha	2941137416	fix diagnostics for deleted files	2025-04-28 19:37:42 +02:00
Aiden Cline	b3c0285db3	feat: model selection for given provider (#57 ) * feat: model selection for given provider * tweak: adjust cfg validation func, remove duplicated logic, consolidate agent updating into agent.go * tweak: make the model dialog scrollable, adjust padding slightly for modal" * feat: add provider selection, add hints, simplify some logic, add horizontal scrolling support, additional scroll indicators" * remove nav help * update docs * increase number of visible models, make horizontal scroll "wrap" * add provider popularity rankings	2025-04-28 19:25:06 +02:00
YJG	805aeff83c	feat: add azure openai models (#74 )	2025-04-28 15:42:57 +02:00
Kujtim Hoxha	bce2ec5c10	fix duplicate context	2025-04-27 20:43:27 +02:00
Kujtim Hoxha	292e9d90ca	remove unnecessary var	2025-04-27 20:34:20 +02:00
Kujtim Hoxha	2b4441a0d1	fix context	2025-04-27 20:31:53 +02:00
Garrett Ladley	8f3a94df92	feat: configure context paths (#86 )	2025-04-27 20:11:09 +02:00
Kujtim Hoxha	4415220555	fix minor issue	2025-04-27 19:24:46 +02:00
Kujtim Hoxha	a3a04d8a54	fix gemini provider	2025-04-27 19:12:02 +02:00
Lukáš Loukota	792e2b164b	fix: gemini tool calling	2025-04-27 19:12:02 +02:00
Kujtim Hoxha	5859dcdc00	small glob fixes	2025-04-27 18:01:31 +02:00
isaac-scarrott	3c2b0f4dd0	[feature/ripgrep-glob] Add ripgrep-based file globbing to improve performance - Introduced `globWithRipgrep` function to perform file globbing using the `rg` (ripgrep) command. - Updated `globFiles` to prioritize ripgrep-based globbing and fall back to doublestar-based globbing if ripgrep fails. - Added logic to handle ripgrep command execution, output parsing, and filtering of hidden files. - Ensured results are sorted by path length and limited to the specified maximum number of matches. - Modified imports to include `os/exec` and `bytes` for ripgrep integration.	2025-04-27 18:01:31 +02:00
Kujtim Hoxha	9738886620	fix provider config	2025-04-27 14:44:40 +02:00
Sam Ottenhoff	f3dccad54b	Handle new Cursor rules format 1. Check if a path ends with a slash (/) 2. If it does, treat it as a directory and read all files within it 3. For directories like .cursor/rules/, it will scan all files and include their content in the prompt 4. Each file from a directory will be prefixed with "# From filename" for clarity	2025-04-27 14:17:06 +02:00
Kujtim Hoxha	b3a8dbd0d9	fix retry warning	2025-04-27 14:08:09 +02:00
Garrett Mitchell Ladley	d93694a979	feat: simpler diff implementation	2025-04-27 13:56:57 +02:00
Fuad	8a4d4152ce	use workingDir if shellInstance is nil otherwise use cwd if shellInstance is not nil	2025-04-27 13:46:59 +02:00
Fuad	f12386e558	use provided workingg dir	2025-04-27 13:46:59 +02:00
Fuad	94aeb7b7fe	Fix nil pointer dereference in GetPersistentShell Added nil check in GetPersistentShell before accessing shellInstance.isAlive to prevent panic when newPersistentShell returns nil due to shell startup errors. This resolves the "invalid memory address or nil pointer dereference" error that was occurring in the shell tool.	2025-04-27 13:46:59 +02:00
Kujtim Hoxha	a35466cdb3	fix acc error	2025-04-25 21:58:14 +02:00
Kujtim Hoxha	170c7ad67a	small fixes	2025-04-25 14:42:47 +02:00
Hunter Casten	7a62ab7675	feat(groq): add support for Groq using the OpenAI provider	2025-04-25 11:11:52 +02:00
Kujtim Hoxha	1586d757dc	remove tool timeout	2025-04-24 22:35:17 +02:00
Dax Raad	d043526200	add more installation options	2025-04-24 16:34:57 -04:00
Kujtim Hoxha	aaf0bc14ba	try fix	2025-04-24 22:27:51 +02:00
Kujtim Hoxha	f2d9bb7ee3	try fix	2025-04-24 22:27:51 +02:00
Kujtim Hoxha	de41703e20	change db driver	2025-04-24 22:27:51 +02:00
Kujtim Hoxha	2c24bfb7b3	fix kitty issues	2025-04-24 19:57:04 +02:00
Dax Raad	47a37b7dd6	back to disablign cgo	2025-04-24 12:46:11 -04:00