- isThinkingPart now only checks thought === true, not thoughtSignature
- thoughtSignature is for context replay and can appear on any part type
- Store thoughtSignature on text blocks as textSignature for proper replay
- Remove id from functionCall/functionResponse (unsupported by Vertex/Cloud Code Assist)
Refs: https://ai.google.dev/gemini-api/docs/thought-signatures
Co-authored-by: Amp <amp@ampcode.com>
Renamed from supportsStreamOptions to clarify this controls stream_options: { include_usage: true }.
Defaults to true (no behavioral change for existing providers).
Providers like gatewayz.ai that reject this parameter can set supportsUsageInStreaming: false in model config.
Based on #596 by @XesGaDeus
The zen.test.ts file was added without the standard skipIf guard,
causing CI to fail on all PRs since no OPENCODE_API_KEY is configured.
This follows the same pattern used by other API-dependent tests.
Google streaming may emit thoughtSignature without thought=true (including empty-text signature-only parts). Treat non-empty thoughtSignature as thinking to avoid leaking reasoning into normal text and retain signature across streaming deltas. Add unit test coverage.
- Add sessionId to StreamOptions for providers that support session-based caching
- OpenAI Codex provider uses sessionId for prompt_cache_key and routing headers
- Agent class now accepts and forwards sessionId to stream functions
- coding-agent passes session ID from SessionManager and updates on session changes
- Update ai package README with table of contents, OpenAI Codex OAuth docs, and env vars table
- Increase Codex instructions cache TTL from 15 minutes to 24 hours
- Add tests for sessionId forwarding in ai and agent packages
Previously the system prompt was converted to an input message in convertMessages,
then stripped out by filterPiSystemPrompts. Now the system prompt is passed directly
to transformRequestBody and appended after CODEX_PI_BRIDGE in the bridge message.
Breaking changes:
- Settings: 'hooks' and 'customTools' arrays replaced with 'extensions'
- CLI: '--hook' and '--tool' flags replaced with '--extension' / '-e'
- API: HookMessage renamed to CustomMessage, role 'hookMessage' to 'custom'
- API: FileSlashCommand renamed to PromptTemplate
- API: discoverSlashCommands() renamed to discoverPromptTemplates()
- Directories: commands/ renamed to prompts/ for prompt templates
Migration:
- Session version bumped to 3 (auto-migrates v2 sessions)
- Old 'hookMessage' role entries converted to 'custom'
Structural changes:
- src/core/hooks/ and src/core/custom-tools/ merged into src/core/extensions/
- src/core/slash-commands.ts renamed to src/core/prompt-templates.ts
- examples/hooks/ and examples/custom-tools/ merged into examples/extensions/
- docs/hooks.md and docs/custom-tools.md merged into docs/extensions.md
New test coverage:
- test/extensions-runner.test.ts (10 tests)
- test/extensions-discovery.test.ts (26 tests)
- test/prompt-templates.test.ts
- Implement google-vertex provider in packages/ai
- Support ADC (Application Default Credentials) via @google/generative-ai
- Add Gemini model catalog for Vertex AI
- Update packages/coding-agent to handle google-vertex provider
- Removed Agent API section from pi-ai README (moved to agent package)
- Rewrote agent package README for new architecture:
- No more transports (ProviderTransport, AppTransport removed)
- Uses streamFn directly with streamProxy for proxy usage
- Documents convertToLlm and transformContext
- Documents low-level agentLoop/agentLoopContinue API
- Updated custom message types documentation
- Renamed AppMessage to AgentMessage throughout
- New agent-loop.ts with AgentLoopContext, AgentLoopConfig
- Removed transport abstraction, Agent now takes streamFn directly
- Extracted streamProxy to proxy.ts utility
- Removed agent-loop from pi-ai (now in agent package)
- Updated consumers (coding-agent, mom) for AgentMessage rename
- Tests updated but some consumers still need migration
Known issues:
- AgentTool, AgentToolResult not exported from pi-ai
- Attachment not exported from pi-agent-core
- ProviderTransport removed but still referenced
- messageTransformer -> convertToLlm migration incomplete
- CustomMessages declaration merging not working properly
- Migrate glm-4.5, glm-4.5-air, glm-4.5-flash, glm-4.6, glm-4.7 from anthropic-messages to openai-completions API
- Updated baseUrl from https://api.z.ai/api/anthropic to https://api.z.ai/api/coding/paas/v4
- Added compat setting to disable developer role for zai models
- Filter empty text blocks in openai-completions to avoid zai API validation errors
- Fixed zai provider tests to use OpenAI-style options (reasoningEffort)
- Change all zai models from anthropic-messages to openai-completions API
- Update baseUrl from https://api.z.ai/api/anthropic to https://api.z.ai/api/coding/paas/v4
- Add compat setting to disable developer role for zai
- Update zai provider tests to use OpenAI-style options (reasoningEffort instead of thinkingEnabled/thinkingBudgetTokens)
- Enable previously disabled thinking and image input tests for zai models
- Remove setApiKey, resolveApiKey, and global apiKeys Map from stream.ts
- Rename getApiKey to getApiKeyFromEnv (only checks env vars)
- Remove OAuth storage layer (storage.ts deleted)
- OAuth login/refresh functions now return credentials instead of saving
- getOAuthApiKey/refreshOAuthToken now take credentials as params
- Add test/oauth.ts helper for ai package tests
- Simplify root npm run check (single biome + tsgo pass)
- Remove redundant check scripts from most packages
- Add web-ui and coding-agent examples to biome/tsgo includes
coding-agent still has compile errors - needs refactoring for new API
When a user interrupts a tool call flow (sends a message without providing
tool results), APIs like OpenAI Responses and Anthropic fail because:
- OpenAI requires tool outputs for function calls
- OpenAI requires reasoning items to have their following items
- Anthropic requires non-empty content for error tool results
Instead of filtering out orphaned tool calls (which breaks thinking signatures),
we now insert synthetic empty tool results with isError: true and content
'No result provided'. This preserves the conversation structure and satisfies
all API requirements.
- 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
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
- Allow branch selector to open with single user message (changed <= 1 to === 0 check)
- Support in-memory branching for --no-session mode (no files created)
- Add isEnabled() getter to SessionManager
- Update sessionFile getter to return null when sessions disabled
- Update SessionSwitchEvent types to allow null session files
- Add branching tests for single message and --no-session scenarios
fixes#163
- Skip empty assistant messages (no content, no tool calls) to avoid
Mistral's 'Assistant message must have either content or tool_calls'
error
- Remove synthetic assistant bridge message after tool results (Mistral
no longer requires this as of Dec 2024)
- Add test for empty assistant message handling
Follow-up to #165
- Add Mistral to KnownProvider type and model generation
- Implement Mistral-specific compat handling in openai-completions:
- requiresToolResultName: tool results need name field
- requiresAssistantAfterToolResult: synthetic assistant message between tool/user
- requiresThinkingAsText: thinking blocks as <thinking> text
- requiresMistralToolIds: tool IDs must be exactly 9 alphanumeric chars
- Add MISTRAL_API_KEY environment variable support
- Add Mistral tests across all test files
- Update documentation (README, CHANGELOG) for both ai and coding-agent packages
- Remove client IDs from gemini.md, reference upstream source instead
Closes#165
- Add agentLoopContinue() to pi-ai for resuming from existing context
- Add Agent.continue() method and transport.continue() interface
- Simplify AgentSession compaction to two cases: overflow (auto-retry) and threshold (no retry)
- Remove proactive mid-turn compaction abort
- Merge turn prefix summary into main summary
- Add isCompacting property to AgentSession and RPC state
- Block input during compaction in interactive mode
- Show compaction count on session resume
- Rename RPC.md to rpc.md for consistency
Related to #128
- Add 'xhigh' to ThinkingLevel type in ai and agent packages
- Map xhigh to reasoning_effort: 'max' for OpenAI providers
- Add thinkingXhigh color token to theme schema and built-in themes
- Show xhigh option only when using codex-max models
- Update CHANGELOG for both ai and coding-agent packages
closes#143
