Adds support for Amazon Bedrock with Claude models including:
- Full streaming support via Converse API
- Reasoning/thinking support for Claude models
- Cross-region inference model ID handling
- Multiple AWS credential sources (profile, IAM keys, API keys)
- Image support in messages and tool results
- Unicode surrogate sanitization
Also adds 'Adding a New Provider' documentation to AGENTS.md and README.
Co-authored-by: nickchan2 <nickchan2@users.noreply.github.com>
When running from source with tsx, the jiti aliases pointed to .js files
that don't exist (only .ts files exist). This caused jiti to fall back to
different module resolution, loading a separate instance of theme.ts where
initTheme() was never called, resulting in undefined theme.
Now checks if .js exists and falls back to .ts for dev mode compatibility.
Breaking change: pi.getAllTools() now returns Array<{ name, description }>
instead of string[]. Extensions needing just names can use .map(t => t.name).
Removes redundant getToolInfo() method added in original PR.
Fixes#647
- Add SessionInfoEntry type for session metadata
- Add /name <name> command to set session display name
- Add pi.setSessionName() and pi.getSessionName() extension API
- Session selector shows name (in warning color) instead of first message when set
- Session name included in fuzzy search
- /session command displays name when set
closes#650
- /resume and --resume now toggle between Current Folder and All sessions with Tab
- SessionManager.list() and listAll() are now async with optional progress callback
- Shows loading progress (e.g. Loading 5/42) while scanning sessions
- SessionInfo.cwd field shows session working directory in All view
- Lazy loading: All sessions only loaded when user presses Tab
closes#619
Co-authored-by: Thomas Mustier <mustierthomas@gmail.com>
Git uses atomic writes (temp file + rename) which changes the inode.
fs.watch on a file stops working after the inode changes.
Now watches the directory containing HEAD and filters for HEAD changes.
- New /models command with toggle UI for each available model
- Changes persist to enabledModels in settings.json
- Updates take effect immediately for Ctrl+P cycling
- Skills registered as /skill:name commands for quick access
- Toggle via /settings or skills.enableSkillCommands in settings.json
- Fuzzy matching for all slash command autocomplete (type /skbra for /skill:brave-search)
- Moved fuzzy module from coding-agent to tui package for reuse
Closes#630 by @Dwsy (reimplemented with fixes)
Applied streaming TextDecoder fix to executeBashWithOperations(), matching
the fix in executeBash() from PR #433. Remote execution (SSH, containers)
was still using Buffer.toString() which corrupts multi-byte UTF-8 sequences
split across chunk boundaries.
fixes#608
Expose data that extensions cannot otherwise access: git branch and
extension statuses from setStatus(). Token stats, model info, etc.
remain computable via ctx.sessionManager and ctx.model.
The --no-skills flag set options.skills = [] in main.ts, but the
interactive mode UI would rediscover skills anyway because it called
loadSkills() directly instead of using the already-loaded skills.
Changes:
- Add AgentSession.skills and AgentSession.skillWarnings properties
- discoverSkills() now returns { skills, warnings } instead of Skill[]
- Interactive mode uses session.skills instead of calling loadSkills()
- Update SDK docs and examples for new return type
Fixes#577
The --no-skills flag set options.skills = [] in main.ts, but the interactive mode UI would rediscover skills anyway because it called loadSkills() directly.
Changes:
- Add AgentSession.skills and AgentSession.skillWarnings properties
- discoverSkills() now returns { skills, warnings } instead of Skill[]
- Interactive mode uses session.skills instead of calling loadSkills()
Co-authored-by: Carlos Villela <cv@lixo.org>
Adds overlay rendering capability to the TUI, enabling floating modal
components that render on top of existing content without clearing the screen.
- Add showOverlay(), hideOverlay(), hasOverlay() methods to TUI
- Implement ANSI-aware line compositing via extractSegments()
- Support overlay stack (multiple overlays, later on top)
- Add { overlay: true } option to ctx.ui.custom()
- Add overlay-test.ts example extension
Also fixes pre-existing bug where bash tool output cached visual lines
at fixed terminal width, causing crashes on terminal resize.
Co-authored-by: Nico Bailon <nico.bailon@gmail.com>
- user_bash event for intercepting ! and !! commands (#528)
- Extensions can return { operations } or { result } to redirect/replace
- executeBashWithOperations() for custom BashOperations execution
- session.recordBashResult() for extensions handling bash themselves
- Theme API: getAllThemes(), getTheme(), setTheme() on ctx.ui
- mac-system-theme.ts example: sync with macOS dark/light mode
- Updated ssh.ts to use user_bash event
When passing a string systemPrompt to createAgentSession(), it is now
used as-is without appending context files and skills. This matches the
documented behavior: 'String replaces default, function receives default
and returns final.'
Previously, string systemPrompt would have context files and skills
appended, causing duplication if they were already in the string.
fixes#543
- Add systemPrompt to BeforeAgentStartEvent so extensions can see current prompt
- Change systemPromptAppend to systemPrompt in BeforeAgentStartEventResult for full replacement
- Extensions can now chain modifications (each sees the result of previous)
- Update ssh.ts to replace local cwd with remote cwd in system prompt
- Update pirate.ts, claude-rules.ts, preset.ts to use new API
fixes#575
- Add setActiveTools() to ExtensionAPI for dynamic tool management
- Extensions can now override, wrap, or disable built-in tools
- Add tool-override.ts example demonstrating the pattern
- Update documentation for tool override capabilities
When aborting a retry attempt, surface the retry-aware abort message
in the assistant output and tool results instead of a generic "Aborted".
- Set errorMessage for aborted streaming messages
- Render abort message without forcing a leading newline when no content
Three related fixes:
1. google-gemini-cli: Handle abort signal in stream reading loop
- Add abort event listener to cancel reader immediately when signal fires
- Fix AbortError detection in retry catch block (fetch throws AbortError,
not our custom message)
- Swallow reader.cancel() rejection to avoid unhandled promise
2. agent-session: Fix retry attempt counter showing 0 on cancel
- abortRetry() was resetting _retryAttempt before the catch block could
read it for the error message
3. interactive-mode: Restore main escape handler on agent_start
- When auto-retry starts, onEscape is replaced with retry-specific handler
- auto_retry_end (which restores it) fires on turn_end, after streaming begins
- Now restore immediately on agent_start if retry handler is still active
Amended: suppress reader.cancel() rejection on abort.
Add --no-tools flag that allows starting pi without any built-in tools,
enabling extension-only tool setups (e.g., pi-ssh-remote).
- Add --no-tools flag to CLI args parsing
- Handle --tools '' (empty string) as equivalent to no tools
- Fix system prompt to not show READ-ONLY mode when no tools (extensions may provide write capabilities)
- Add tests for new flag and system prompt behavior
fixes#555
Tools now use ExtensionRunner.createContext() instead of a separate
inline context factory. This ensures tools and event handlers share
the same context, fixing ctx.shutdown() and other context methods.
- Made ExtensionRunner.createContext() public
- Changed wrapRegisteredTools to accept ExtensionRunner instead of getContext callback
- Create ExtensionRunner when SDK custom tools are present (not just extensions)
- Removed redundant inline context factory from sdk.ts
The tool execution context was created with a no-op shutdown handler.
Now it delegates to ExtensionRunner.shutdown() which uses the handler
set by the mode via initialize().
- Replace per-extension closures with shared ExtensionRuntime
- Split context actions: ExtensionContextActions (required) + ExtensionCommandContextActions (optional)
- Rename LoadedExtension to Extension, remove setter methods
- Change runner.initialize() from options object to positional params
- Derive hasUI from uiContext presence (no separate param)
- Add warning when extensions override built-in tools
- RPC and print modes now provide full command context actions
BREAKING CHANGE: Extension system types and initialization API changed.
See CHANGELOG.md for migration details.
When enabledModels is configured without thinking level suffixes (e.g.,
'claude-opus-4-5' instead of 'claude-opus-4-5:high'), the scoped model's
default 'off' thinking level was overriding defaultThinkingLevel from
settings.
Now thinkingLevel in ScopedModel is optional (undefined means 'not
explicitly specified'). When passing to SDK, undefined values are filled
with defaultThinkingLevel from settings.
