resolveUpdateMethod classified the install purely by directory containment,
so a standalone binary placed where `npm prefix -g` / `bun pm bin -g` also
points (e.g. ~/.local/bin) was misrouted to `npm install -g`, which then
aborted with EEXIST refusing to overwrite the existing regular file. Now a
plain executable (not a symlink) inside a package-manager bin dir is treated
as the standalone binary and self-updated in place.
- Added language-specific code formatters for JavaScript, Julia, Python, and Ruby to improve display rendering.
- Integrated display formatting into browser run and eval render tools while preserving verbatim execution.
- Added comprehensive test suites verifying formatting stability, lexical safety, and streaming behavior.
- Implemented a structured web-search query parsing module supporting directives, tokenization, date parsing, and syntax serialization.
- Updated search providers to map query directives and date bounds to native provider parameters and filters.
- Added lenient result constraint post-filtering and configuration settings for enhanced engine routing.
- Added comprehensive unit and integration tests covering query parsing, constraint filtering, and provider-specific request mapping.
The rebuild dedup dropped any preserved pendingTools component whose toolCallId
had a persisted toolResult. A background task's initial async.state=="running"
result is persisted while EventController#handleToolExecutionEnd deliberately
keeps its component in pendingTools so a later tool_execution_update/_end can
settle it. Dropping that still-live handle stranded those updates on the running
snapshot. Only terminal results are now owned by the replay; running async
handles stay preserved. Added a regression covering the running-task case.
rebuildChatFromMessages preserves the live pendingTools components across its
clear+replay so streaming keeps routing into them. That preservation assumed
every pending-tool component was still dangling (its result outside
state.messages). Once a tool's result had landed in the session entries while
its component still lingered in pendingTools (a rebuild racing the
tool-completion event, or a background/displaceable snapshot), the replay
reconstructed the completed block from the persisted toolResult AND the
preserved live component was re-appended, so the same tool block rendered twice.
Resolved tool calls are now dropped from the preserved live set and owned by the
replay; only genuinely in-flight (dangling, replay-stripped) calls are preserved.
Fixes#6516
Replaced direct assertions on internal ordering and recovery helpers with an isolated broker integration test. The test seeds recovered terminal metadata, starts an active daemon, sends the authenticated list RPC, and asserts active-first ordering, true exit-time recency, the terminal cap, and protocol serialization/parsing.
Made the ordering and recovery helpers internal again because production wiring now supplies their coverage.
Fixes#6517
Recovery unconditionally restamped every non-detached record's exitedAt with the restart timestamp, including already-exited/failed ones, so after an idle-broker restart the list history cap could keep arbitrary directory-order entries and drop the genuinely most-recently-exited process.
Reap only records that were still alive at recovery; terminal records keep their real exitedAt/exitReason. Extract reapRecoveredSnapshot() and cover it with tests.
Fixes#6517
- Added guidelines stating that concurrent edits to the same files are safe.
- Specified prerequisites for safe overlap including skipping validation and defining contracts up front.
The broker `list`/ps op sorted every daemon record by createdAt ascending and never pruned, so in a long-lived project the active (newest) daemon rendered behind all exited ones and the response grew without bound.
List non-terminal daemons first (oldest to newest) and cap exited/failed history at the 10 most recently exited; truncated records stay addressable by name via describe/logs/restart.
Fixes#6517
- Add usage history, reporting, and client summary endpoints to the auth broker.
- Implement SQLite persistence, batching, and periodic flushing for observed client usage.
- Integrate usage reporting into the coding agent session for completed assistant messages.
- Update stats aggregator and dashboard to retrieve usage history snapshots from the broker.
- Added tool schema and description compaction for oversized data payloads in `packages/coding-agent/src/debug/raw-sse-buffer.ts`.
- Implemented head-tail trimming to preserve leading and trailing event fields when events exceed character budgets.
- Added test coverage verifying SSE debug event truncation, elision markers, and JSON-safe tool compaction behavior.
- Added available shell builtins list to the bash tool prompt template.
- Added helper to check if shell builtins are disabled via settings or environment.
- Removes `model` field from task item/schema, TaskParams, and TaskItem types.
- Removes model selector validation, formatting, and approval display logic.
- Updates task tool priority docs to reflect that model is no longer per-call overridable.
- Updates eval agent() helper docs and prompt templates to remove model parameter.
- Updates tests to reflect removal of model override capability.
Required CLI model registries to expose getAvailable() and used that authenticated
set whenever callers omit availableModels. Deferred SDK and bench/dry-balance
resolution now lets configured roles beat unauthenticated catalog id collisions.
Updated resolver test registries and made the #6508 regression omit the explicit
availableModels option, covering the deferred-caller path from the review.
Fixes#6508
`resolveCliModel` ran findExactCliModel's unauthenticated catalog fallback
before configured-role resolution, so the bundled `cursor/default` model (bare
id `default`) shadowed a configured `modelRoles.default`. On machines without
Cursor credentials `--model default` failed with `No API key found for cursor`
instead of resolving the configured, authenticated default role.
Defer the catalog fallback: explicit provider/id references and authenticated
bare ids still win over roles, a configured role now beats an unauthenticated
catalog-only id, and the catalog id is still recovered via the trailing fuzzy
fallback when no role matches.
Fixes#6508
- Large-paste menu now saves pastes as local://paste-N.md instead of
local://attachment-N, giving the artifact a markdown extension and a
clearer name.
- Add `resolveFallbackTool` callback to `AgentOptions` and `AgentLoopConfig` that resolves tool calls not found in the advertised set.
- Use the callback as a third lookup step after `name` and `customWireName` match, enabling side transports like `xd://` device mounts.
- Add test coverage verifying the fallback resolves known devices and preserves "not found" errors for unknown names.
- Wire the coding agent's device registry as `resolveFallbackTool` in both `createAgentSession` and `streamAgentSession` paths.
- Prepended a model-visible PREVIEW_PENDING_NOTICE to ast_edit preview
results; the TUI-only proposed badge never reached the model, so
preview diffs read as already-applied edits.
- Rendered the resolve reminder with the source tool name via
Handlebars instead of a generic 'This is a preview'.
- Documented the xd://resolve / xd://reject two-phase flow in the
ast_edit tool prompt.
- Kept op required in the todo schema; lenientArgValidation now routes raw args to execute(), where resolveTodoParams re-validates and repairs an omitted op (list -> init, phase+items -> append, bare items on empty list -> init).
- Ambiguous op-less calls surface the schema error as a retryable tool error instead of a hard validation failure.
computeNonMessageBreakdown estimated Skills tokens from the unfiltered
session.skills registry and subtracted that from the first system-prompt
block, which only ever contained the rendered (filtered) skills. Hidden
explicit-only skills (hide/disable-model-invocation) and all skills when
the read tool was absent inflated Skills and clamped System prompt to 0.
Add a renderedSkills helper mirroring buildSystemPrompt's filter and use
it for the Skills estimate so the category split matches the provider
prompt.
Fixes#6498
Redacted assistant anthropicServerTool blocks alongside redactedThinking and providerPayload so /share never uploads raw server_tool_use input or web_search_tool_result encrypted_content.
Persisted native server-tool calls and web-search results in assistant content, replayed them only to the issuing Anthropic provider, and retained Umans gateway filtering.
Fixes#6495
Raced session_stop handlers against the active settle signal and discarded cancellation without timeout errors.
Added runner and AgentSession regressions for pre-dispatch and in-flight aborts, timeout preservation, and stale continuation suppression.
Fixes#6489
- Add `CodexAttestationProvider` hook and `getCodexAttestationHeader` resolver that gates on ChatGPT-OAuth credentials.
- Integrate attestation into WebSocket transport, SSE event stream, and OpenAI compaction requests.
- Wire `setCodexAttestationProvider(generateCodexAttestation)` in model-registry init for OAuth sessions.
- Added `LIVE_DELEGATION_MESSAGE_TYPE` constant and delegation message handling for voice sessions.
- Implemented turn-based transcript coalescing with user and assistant turn counters.
- Added transcript display row with normalized rendering in the live visualizer.
- Refactored controller to send delegation messages via `sendCustomMessage` with configurable frame styling.
- Removed microphone permission error reporting from silence detection logic.
- Switched from `miniaudio` to `maudio` Rust crate and added `AudioCapture` and `AudioPlayback` native classes.
- Removed browser-side audio infrastructure including Web Audio API, audio worklet processor, and WebRTC runtime.
- Migrated STT recorder and transcriber modules to use native `AudioCapture` with callback-based streaming.
- Replaced streaming audio player with native `AudioPlayback` that writes PCM directly without TypeScript intermediaries.
- Removed ffmpeg, wav, and platform-specific playback commands from the audio toolchain.
- Replaced puppeteer-based WebRTC with native LiveWebRtcPeer for cross-platform live audio delivery.
- Added cross-platform microphone capture via miniaudio and Opus codec integration for live encoding/decoding.
- Added Apple DeviceCheck attestation token generation via raw Objective-C FFI for macOS.
- Updated live session model to "gpt-live-1-codex" and default voice to "sol" across protocol and controller.
- Added LiveWebRtcPeer and deviceCheckGenerateToken to the public native bindings API.
- Extracted #formatToolExecution into a standalone formatDefaultToolExecution module.
- Updated xdev renderXdevCall and renderXdevResult to use the default card when no mounted renderer exists.
- Added fallback rendering that shows tool label, args, and output with appropriate theming.
- Added integration test verifying generic card renders for mounted tools without bespoke renderers.
- Catch execution errors in XdevRegistry and render them using the mounted tool's error handling.
- Preserve xdev dispatch context when device execution fails.
- Add `pinSessionOAuthAccount` storage method and active account flag to the auth storage API.
- Introduce session account selector component, controller logic, and interactive mode delegation.
- Implement the `/session pin` builtin slash command with text listing and account pinning capabilities.
- Add unit tests covering session account selection, component navigation, and command handling.
Scheduling agent.continue() inside navigateTree started a post-prompt
task before the interactive /tree handler rebuilt its transcript, so a
fast provider's agent_start/turn_start could render against the stale
pre-rebuild UI and then be clobbered by renderInitialMessages.
navigateTree now reports the commit via askReanswerCommitted instead of
resuming, and SelectorController.showTreeSelector calls the new
AgentSession.resumeAfterAskReanswer() only after renderInitialMessages +
reloadTodos, so the resumed turn always renders against the rebuilt
transcript.
Addresses chatgpt-codex-connector review on #6484.
Fixes#6483
Committing a new answer to a past `ask` via `/tree` branched a fresh
sibling toolResult and rebuilt context, but `navigateTree` never
scheduled `agent.continue()`. Unlike a live `ask` — whose continuation
is intrinsic to the streaming run loop — the /tree re-answer mutates the
tree outside any running turn, so the model never consumed the new
answer and the session sat idle until a manual prompt.
Schedule an agent continue at the end of the reanswerAskResult
completion, gated to the ask re-answer branch only so plain leaf moves
and the read-only reopenAsk probe stay idle.
Fixes#6483
requestRender(true) only queues the paint via setImmediate; calling
prewarm() synchronously afterwards put the worker spawn syscall ahead
of the render callback in the same loop turn. Schedule the prewarm
with its own setImmediate (FIFO after the render callback) so the
first startup frame paints before the subprocess spawns.
- Fixed a macOS clipboard bug where copied URL text like `https://i.can.ac/x.png` was coerced into a bogus HFS path (`/https/::i.can.ac:x.png`) and dead-ended with "Image not found" instead of falling through to text paste.
- The AppleScript now checks `clipboard info for "class furl"` before coercing so plain text/URL clipboards paste as text rather than file paths.
- Extracted the script to its own `.applescript` file and added TypeScript declarations for `.applescript` imports.
- Added the upstream keyText helper to the legacy package-root shim.
- Covered active keybinding formatting and documented the compatibility fix.
Fixes#6470
#finalizeFile marked the sink finalized then ran the capped-artifact tail
replay before closing. A write error during that replay threw before
sink.end(), and because #finalized was already set the executor finally
paths calling dispose() could not retry the close, leaking the descriptor
and masking the original tool error.
Moved sink.end() into a finally around the tail replay and swallowed both
the replay and close errors so the descriptor is always released and
dispose() never throws.
mr-r0b0t
