- SessionManager: add flushed flag, _persist() flushes all entries when first assistant seen
- SessionManager: reset() now creates session header
- MomSessionManager: same pattern, remove pendingEntries/sessionInitialized/startSession/shouldInitializeSession
- Use default params instead of resolvedAgentDir pattern in loaders
- Remove unused DiscoverAndLoadHooksOptions interface
- Remove redundant github-copilot special casing in getAvailableModels
- loadAndMergeModels(agentDir) - loads models.json from agentDir
- getAvailableModels(agentDir) - uses agentDir for model discovery
- findModel(provider, id, agentDir) - uses agentDir for model lookup
- configureOAuthStorage(agentDir) - configures OAuth to use agentDir/oauth.json
- createAgentSession calls configureOAuthStorage with options.agentDir
- Export configureOAuthStorage from SDK
- Add factory methods: create(cwd), open(path), continueRecent(cwd), inMemory()
- Add static list(cwd) for session listing
- Make constructor private, pass cwd explicitly
- Update SDK to take sessionManager instead of sessionFile options
- Update main.ts to create SessionManager based on CLI flags
- Update SessionSelectorComponent to take sessions[] instead of SessionManager
- Update tests to use factory methods
- Add continueSession, restoreFromSession, additionalHookPaths,
additionalCustomToolPaths, scopedModels to CreateAgentSessionOptions
- Return CreateAgentSessionResult with session, customToolsResult,
and modelFallbackMessage
- main.ts now focuses on CLI arg parsing and mode routing
- Reduced main.ts from ~490 to ~340 lines
Adds glob pattern support for skill filtering:
- --skills <patterns> CLI flag (comma-separated glob patterns)
- includeSkills setting in settings.json
- ignoredSkills now supports glob patterns
- ignoredSkills takes precedence over includeSkills and --skills
Closes#268
- Event-based architecture: agent forwards AgentSessionEvent to adapters
- Multi-adapter support via single config.json
- Access control: admins, DM permissions per adapter
- Channel namespacing by adapter name
- Channel isolation via bubblewrap in Linux/Docker environments
- Simplified directory structure and interfaces
- Fix //tmp issue: distinguish slash commands from file paths by checking if anything precedes the /
- Fix symlinks to directories (like /tmp) not getting trailing slash
- Add setOAuthStorage() and resetOAuthStorage() to pi-ai for custom storage backends
- Configure coding-agent to use its own configurable OAuth path via getOAuthPath()
- Model selector (/model command) now only shows models from --models scope when set
- Rewrite OAuth documentation in pi-ai README with examples
Fixes#255
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.
