Implement Agent Skills standard (https://agentskills.io/specification):
- Validate name (must match parent dir, lowercase, max 64 chars)
- Validate description (required, max 1024 chars)
- Warn on unknown frontmatter fields
- Warn on name collisions (keep first)
- Change prompt format to XML structure
- Remove {baseDir} placeholder (use relative paths)
- Add tests and update documentation
fixes#231
Previously, when using 'google-generative-ai' API with a custom baseUrl
in models.json, the baseUrl was ignored and requests always went to the
default Google endpoint.
Now the provider correctly passes model.baseUrl to the SDK's
httpOptions.baseUrl, enabling use of custom endpoints or API proxies.
Fixes#216
- Fix tool result format for Gemini 3 Flash Preview compatibility
- Use 'output' key for successful results (not 'result')
- Use 'error' key for error results (not 'isError')
- Per Google SDK documentation for FunctionResponse.response
- Improve type safety in google.ts provider
- Add ImageContent import and use proper type guards
- Replace 'as any' casts with proper typing
- Import and use Schema type for tool parameters
- Add proper typing for index deletion in error handler
- Add comprehensive test for Gemini 3 Flash tool calling
- Tests successful tool call and result handling
- Tests error tool result handling
- Verifies fix for issue #213Fixes#213
* use the correct Gemini 3 Flash Preview thinking levels
* fix a build error
* add changelog entry
* regenerate models
* make less assumptions about future models
Previous test used compressed 8k images (0.01MB) which was meaningless.
Now tests with actual large noise images that don't compress.
Realistic payload limits discovered:
- Anthropic: 6 x 3MB = ~18MB total (not 32MB as documented)
- OpenAI: 2 x 15MB = ~30MB total
- Gemini: 10 x 20MB = ~200MB total (very permissive)
- Mistral: 4 x 10MB = ~40MB total
- xAI: 1 x 20MB (strict request size limit)
- Groq: 5 x 5760px images (5 image + pixel limit)
- zAI: 2 x 15MB = ~30MB (50MB request limit)
- OpenRouter: 2 x 5MB = ~10MB total
Also fixed GEMINI_API_KEY env var (was GOOGLE_API_KEY).
Related to #120
Tested max 8kx8k images per provider:
- Anthropic: 100 (explicit limit, fails at 101)
- OpenAI: 100-200 (100 works, 200 times out)
- Mistral: 8 (explicit limit, fails at 9)
- xAI: 100-150 (100 works, 150 times out)
- Groq: 0 (8k exceeds 33M pixel limit)
- zAI: 400 (context window limited at 500)
- OpenRouter: 40 (context window limited at 50)
- Gemini: untested (no API key in test env)
Key finding: Anthropic's 'many images' rule does NOT cause API errors.
100 x 8kx8k images work fine. Anthropic likely auto-resizes internally.
Related to #120
Tests max image count, size, dimensions, and 8k stress test for:
- Anthropic, OpenAI, Gemini, Mistral, OpenRouter, xAI, Groq, zAI
Key finding: Anthropic's 'many images' rule (>20 images = 2000px max)
does NOT cause API errors. 100 x 8k images work fine. Anthropic likely
auto-resizes internally.
Related to #120
Tests provider-specific image limitations across all supported providers:
- Maximum number of images in context
- Maximum image size (bytes)
- Maximum image dimensions
Discovered limits (Dec 2025):
- Anthropic: 100 images, 5MB per image, 8000px max dimension
- OpenAI: 500 images, >=25MB per image
- Gemini: ~2500 images, >=40MB per image
- Mistral: 8 images, ~15MB per image
- OpenRouter: ~40 images (context limited), ~15MB per image
- Add AgentToolUpdateCallback type and optional onUpdate callback to AgentTool.execute()
- Add tool_execution_update event with toolCallId, toolName, args, partialResult
- Normalize tool_execution_end to always use AgentToolResult (no more string fallback)
- Bash tool streams truncated rolling buffer output during execution
- ToolExecutionComponent shows last N lines when collapsed (not first N)
- Interactive mode handles tool_execution_update events
- Update RPC docs and ai/agent READMEs
fixes#44
Previously, when reasoning was not specified, some providers like Gemini
with 'dynamic thinking' enabled by default would still use thinking.
Now explicitly sets thinkingEnabled: false (Anthropic) and
thinking: { enabled: false } (Google) when reasoning is undefined.
Closes#180
- Auto-enable all models after /login via POST /models/{model}/policy
- Use openai-responses API for gpt-5/o3/o4 models (not accessible via completions)
- Normalize tool call IDs when switching between github-copilot models with different APIs
(fixes#198: openai-responses generates 450+ char IDs with special chars that break other models)
- Update README with streamlined GitHub Copilot docs
- OAuth login for GitHub Copilot via /login command
- Support for github.com and GitHub Enterprise
- Models sourced from models.dev (Claude, GPT, Gemini, Grok, etc.)
- Dynamic base URL from token's proxy-ep field
- Use vscode-chat integration ID for API compatibility
- Documentation for model enablement at github.com/settings/copilot/features
Co-authored-by: cau1k <cau1k@users.noreply.github.com>
- add GitHub Copilot model discovery (env token fallback, headers,
compat) plus fallback list and quoted provider keys in generated map
- surface Copilot provider end-to-end (KnownProvider/default, env+OAuth
token refresh/save, enterprise base URL swap, available only when
creds/env exist)
- tweak interactive OAuth UI to render instruction text and prompt
placeholders
gpt-5.2-high took about 35 minutes. It had a lot of trouble with `npm
check` and went off on a "let's adjust every tsconfig" side quest.
Device code flow works, but the ai/scripts/generate-models.ts impl is
wrong as models from months ago are missing and only those deprecated
are accessible in the /models picker.
Breaking change: Pi skills must now be named SKILL.md inside a directory,
matching Codex CLI format. Previously any *.md file was treated as a skill.
Migrate by renaming ~/.pi/agent/skills/foo.md to ~/.pi/agent/skills/foo/SKILL.md
