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
* Add skills system with Claude Code compatibility
* consolidate skills into single module, merge loaders, add <available_skills> XML tags
* add Codex CLI skills compatibility, skip hidden/symlinks
