Fixes OpenAI Responses 400 error 'reasoning without following item' by
skipping errored/aborted assistant messages entirely rather than filtering
at the provider level. This covers openai-responses, openai-codex-responses,
and future providers.
Removes strictResponsesPairing compat option (no longer needed).
Closes#838
Split OpenAICompat into OpenAICompletionsCompat and OpenAIResponsesCompat
for type-safe API-specific compat settings. Added strictResponsesPairing
option to suppress orphaned reasoning/tool calls on incomplete turns,
fixing 400 errors on Azure's Responses API which requires strict pairing.
Closes#768
Container components with embedded Input/Editor children must implement
Focusable and propagate focus state to enable correct IME candidate
window positioning.
Related to #827
Components with search inputs now implement Focusable interface and
propagate focus state to their child Input components. This allows
the hardware cursor to be positioned correctly for IME candidate
window placement.
Affected components:
- ModelSelectorComponent
- ScopedModelsSelectorComponent
- SessionSelectorComponent (and SessionList)
- ExtensionInputComponent
- LoginDialogComponent
- TreeSelectorComponent (and LabelInput)
fixes#827
- Add APPROVED_CONTRIBUTORS file with existing contributors
- Add pr-gate.yml workflow to close PRs from unapproved contributors
- Add approve-contributor.yml workflow to approve via lgtm on issues
- Add CONTRIBUTING.md with guidelines
- Update README.md to point to CONTRIBUTING.md
- Replace hardcoded pi->CC tool mappings with single CC tool name list
- Case-insensitive lookup: if tool name matches CC tool, use CC casing
- Remove broken find->Glob mapping (round-trip failed)
- Add test coverage for tool name normalization
When an assistant message has stopReason 'error', its tool calls are now
excluded from pending tool tracking. This prevents synthetic tool results
from being generated for calls that will be dropped by provider-specific
converters (e.g., Codex drops tool calls from errored messages).
Previously, this mismatch caused OpenAI to reject requests with 'No tool
call found for function call output with call_id ...' errors.
fixes#812
Instead of skipping unsigned tool calls entirely (which lobotomizes context),
convert them to text with an explicit note telling the model this is historical
context from a different model and not a format to mimic.
This preserves tool call/result context when switching from providers without
thought signatures (e.g. Claude via Antigravity) to Gemini 3.
When auto-compaction fails (e.g., quota exceeded), emit the error via
the auto_compaction_end event instead of throwing. The UI now displays
the error message, allowing users to take action (switch models, wait
for quota reset, etc.) instead of crashing.
fixes#792
Multiple agents may work on different files in the same worktree.
Added rules to prevent agents from accidentally committing or
destroying each other's work.
When 429/500 errors occur during tool execution, empty assistant messages
with stopReason='error' get persisted. These break the tool_use -> tool_result
chain for Claude/Gemini APIs.
Added centralized filtering in transformMessages to skip assistant messages
with empty content and no tool calls. Provider-level filters remain for
defense-in-depth.
When --no-extensions was used, extensionsResult.extensions was an empty
array. The condition in buildSessionOptions() checked .length > 0,
so preloadedExtensions was not set. This caused createAgentSession()
to fall through to extension discovery.
Remove the .length > 0 condition so the empty result is passed through,
signaling that extension loading was already handled.
Fixes#776
- Update ExtensionCommandContext.navigateTree type signature
- Pass new options through in print-mode and rpc-mode handlers
- Update docs/extensions.md, docs/sdk.md, docs/tree.md
- Add changelog entry
Previous commit broke Node.js/tsx by using the ESM entry point which
doesn't work with Node. This creates a wrapper module that:
- Uses require() for lazy loading (works in both Node and Bun)
- Gracefully handles load failures (returns original image)
- Works in Node.js, tsx, and Bun compiled binaries
- Import photon-node from ESM entry point (photon_rs_bg.js) instead of CJS
entry, allowing Bun to embed WASM in compiled binaries
- Add photon.d.ts for TypeScript support of ESM entry
- Add scripts/build-binaries.sh for local binary builds
- Simplify GitHub workflow to use the build script
- Add binaries/ to gitignore
Fixes cursor visibility issues in JetBrains IDE terminals (IntelliJ, PyCharm) where
the hardware cursor either blinks or becomes invisible depending on settings.
Fixes#771
Previously, OpenAI-compatible provider settings (like developer role support)
were detected only from the baseUrl. When using custom URLs (e.g., proxies),
detection failed. Now checks model.provider first, then falls back to URL.
Fixes#774
Implements support for ${@:N} and ${@:N:L} syntax to slice argument arrays
in prompt templates, following bash conventions.
Closes#769
Co-authored-by: Zeno Jiricek <airtonix@users.noreply.github.com>
- Add Focusable interface for components that need hardware cursor positioning
- Add CURSOR_MARKER (APC escape sequence) for marking cursor position in render output
- Editor and Input components implement Focusable and emit marker when focused
- TUI extracts cursor position from rendered output and positions hardware cursor
- Track hardwareCursorRow separately from cursorRow for differential rendering
- visibleWidth() and extractAnsiCode() now handle APC sequences
- Update overlay-test.ts example to demonstrate Focusable usage
- Add documentation for Focusable interface in docs/tui.md
Closes#719, closes#525
The Editor component now accepts TUI as the first constructor parameter,
enabling it to query terminal dimensions. When content exceeds available
height, the editor scrolls vertically keeping the cursor visible.
Features:
- Max editor height is 30% of terminal rows (minimum 5 lines)
- Page Up/Down keys scroll by page size
- Scroll indicators show lines above/below: ─── ↑ 5 more ───
Breaking change: Editor constructor signature changed from
new Editor(theme)
to
new Editor(tui, theme)
fixes#732
When stdin is piped (not a TTY), read the content and treat it as the
first message. Since interactive mode requires a TTY for keyboard input,
print mode is automatically enabled.
- echo foo | pi -> equivalent to pi -p foo
- echo foo | pi -p -> equivalent to pi -p foo
- RPC mode unaffected (uses stdin for JSON-RPC)
fixes#708
- Skill commands (/skill:name) now expanded in AgentSession instead of
interactive mode, enabling them in RPC and print modes
- Input event can now intercept /skill:name before expansion
- Updated extensions.md with clearer input event docs and processing order
- Updated rpc.md: hook -> extension terminology, added skill expansion mentions
- Added PR attribution to changelog entries for #761
Resolves pi-internal:// paths to the coding-agent package directory,
allowing the model to read internal documentation. Appends a hint
showing the filesystem path and instructing to use it for further reads.
- align Codex Responses provider with Pi static instructions
- simplify Codex request/stream handling and cleanup exports
- keep legacy OpenCode Codex prompt for testing until Pi prompt is allowlisted
Mario Zechner