- Refactored test assertions to use loadEntriesFromFile for session file parsing.
- Verified forked session content using entry type discrimination instead of line-based parsing.
- Introduced `resolveToolEventInput` to enable mode-specific transformation of editor tool inputs before normalization.
- Updated `ExtensionToolWrapper` and `HookToolWrapper` to utilize the new resolver during tool execution.
- Added support for tracking `reasoningTokens` in `SessionStats` and `AdvisorStats` within the agent session.
- Introduced V2 streaming remote compaction for OpenAI-compatible models, enabling full conversation history forwarding and reducing data loss from local trimming.
- Added comprehensive support for sessionId, promptCacheKey, and automatic retry mechanisms to improve compaction reliability and accuracy.
- Updated agent, catalog, and configuration schemas to manage V2 streaming settings, model metadata, and model-specific context window constraints.
- Extended freeform tool patch support for Azure OpenAI and Codex models and refined assistant-side history preservation across providers.
- Extracted taskToolRenderer to a dedicated renderer file to resolve circular dependencies.
- Updated all references to the renderer to point to the new location.
Concurrent graph-root loads in the JS eval kernel segfaulted Bun
(SIGSEGV at 0xFFFFFFFFFFFFFFF8, getImportedModule on a null record in
JSC::AbstractModuleRecord::innerModuleLinking). Two roots loaded at once
over an overlapping local-import graph — e.g.
Promise.all([import("./a.ts"), import("./b.ts")]) sharing a dependency —
each launched its own module.link() over the same shared
vm.SourceTextModule instances. The async link resolver yields
mid-instantiation, letting the two link passes interleave and re-enter
Bun's node:vm linker, which crashes instead of throwing.
The earlier single-pass fix (15.7.2) only serialized linking within one
graph root; it did not guard two concurrent roots over shared modules.
LocalModuleLoader now routes every module.link() through a promise-chain
mutex (#serializeLink), so the linker is never re-entered
mid-instantiation. The lock is held only across link(), not evaluate(),
so a dynamic import during evaluation re-acquires it without deadlock,
and the chain swallows rejections so a failed link cannot wedge later
imports. Reproduced and verified against the user crash trace: the
concurrent-diamond repro went from 5/6 crashes to 0/N with correct
namespaces.
- Extended `tools/yield.ts` with typed incremental sections, raw last-turn terminal results, and updated yield guidance in the subagent system prompts.
- Reworked `task/executor.ts`, `task/render.ts`, and `task/types.ts` to assemble typed yield sections, render reviewer results from incremental yield data, and preserve the typed result shape.
- Switched `prompts/agents/reviewer.md`, `review-request.md`, and `review-custom-request.md` from `report_finding` calls to incremental `yield` sections.
- Added incremental-yield coverage in `test/task/executor-warnings.test.ts`, `test/task/render-yield-shape.test.ts`, `test/tools/yield-extraction.test.ts`, and `test/tools/yield.test.ts`.
- Added `INTERRUPTED_THINKING_MESSAGE_TYPE` and `demoteInterruptedThinking` in `session/messages.ts` for stripping unfinished thinking into durable context.
- Persisted hidden interrupted-thinking context from `session/agent-session.ts` immediately after user-interrupted assistant turns.
- Added the `prompts/system/interrupted-thinking.md` envelope used for replaying interrupted reasoning.
- Added focused interrupted-thinking coverage in `test/agent-session-interrupted-thinking.test.ts` and `test/session/interrupted-thinking-demote.test.ts`.
- Added idle recap functionality to EventController to display goals and next actions when the agent is inactive.
- Updated session parsing in gc-cli and memories to correctly support optional title entries in session files.
- Introduced `TitleChangeEntry` type and `TITLE_CHANGE_ENTRY_TYPE` to record title modifications in session logs.
- Added `titleUpdatedAt` and `hasTitleSlot` to `SessionManager` state for persistent tracking of metadata.
- Updated `setSessionName` to serialize title changes into the session file via dedicated title slots.
- Modified session file output to include a title slot header for improved auditability.
- Implemented mutable session titles with audit tracking, including storage persistence for SQL and Redis backends.
- Added comprehensive session management features such as idle recap triggers, incremental subagent yield submissions, and automated title refreshing.
- Enhanced task tracking in the TodoTool with progress prioritization and improved session cleanup logic.
- Introduced citation tag handling for OpenAI-compatible source markers and improved edit parsing.
- Added a fixed-width title slot system to serialize and persist session titles across physical files and backend storage.
- Integrated automated session title updates triggered by todo replan operations using conversation history context.
- Extended storage interfaces across memory, file-system, Redis, and SQL backends to support independent title metadata updates.
- Implemented title metadata parsing within session loaders and list utilities to ensure accurate retrieval and display.
- Added configuration schema for idle recap feature including enabled state and idle duration settings.
- Added configuration schema to refresh session titles automatically upon replanning tasks.
- Updated settings interfaces to include RecapSettings and TitleSettings types.
- Recap.enabled.
- Recap.idleSeconds.
- Title.refreshOnReplan.
Split image-bearing custom messages into developer text plus user image content before provider conversion so queued skill images stay out of developer slots.
Mapped user-attributed skill prompt custom messages to user-role model messages while preserving developer framing for auto-applied skills and other custom messages.
Fixes#3698
Address PR review: switchSession (/resume, /move, ACP fork/load,
RPC switch_session, extension switchSession) mutates the loaded
session file in place under the same AgentSession ref, so a WeakMap
keyed only on the AgentSession ref carried the previous
conversation's meter into the resumed one — the footer kept showing
the previous total after resuming a different idle session.
Snapshot the loaded sessionFile path in the per-session meter and
detect a real-to-real transition inside #meter(): on a swap, drop
the old meter and start a fresh one. The undefined → real first-save
transition only refreshes the snapshot (same conversation, same
identity, accumulated time preserved). #closeStaleActiveWindow now
routes through #meter() so the file-change check applies there too.
Adds two regression tests covering the real-to-real swap and the
first-save no-reset.
Address PR review: collab guest reconciles a state frame with
isStreaming === false by stopping the loader when the host's
agent_end never reached us (typically across a reconnect). With the
new active-time meter, the same path also has to call markActivityEnd
or the per-session window stays open and time_spent ticks forever.
Extract the close logic as reconcileGuestIdleHostState so a unit test
can exercise it directly without bringing up the full host/relay
welcome train.
Address PR review: SessionFocusController synthesizes agent_start on
mid-turn attach but does not pair it with a synthetic agent_end on
unfocus. With a single shared StatusLineComponent meter, returning to
the main session while a subagent was still streaming left
#activeStartedAt open, so the main status line kept ticking through
idle time after the subagent finished.
Replace the single #activeMs / #activeStartedAt fields with a WeakMap
keyed on AgentSession. markActivityStart / markActivityEnd /
getActiveMs / resetActiveTime all operate on the currently-attached
session's meter, so detaching from a subagent never bleeds its open
window into main. setSession closes a stale window (in-flight + new
session not streaming) on re-focus so a subagent that finished while
we were detached does not credit the detached gap.
Adds two regression tests covering both cases.
The time_spent segment rendered Date.now() - sessionStartTime, so an
idle session displayed hours of "time spent" while the agent did
nothing — the only inputs were wall-clock and the unmoving session
start.
Replace sessionStartTime with activeMs in SegmentContext and accumulate
inside StatusLineComponent across agent_start -> agent_end windows.
markActivityStart/markActivityEnd are idempotent (reentrant agent_start
events and superseded agent_end events never double-count); the segment
ticks live during an open window and freezes when the agent yields.
The session-boundary hook drops the now-meaningless wall-clock argument
and is renamed setSessionStartTime -> resetActiveTime; it zeroes the
accumulator and drops any in-flight window so /clear / fresh-session /
joined-collab paths start the meter at zero.
Fixes#3681
Codex discovery surfaced every `~/.codex/hooks/*.{ts,js}` file as an OMP
hook (silently defaulting untyped names to `pre:<basename>`), and
`discoverExtensionPaths` then handed those paths to `loadExtension` for
dynamic import. A standalone Codex hook script with a top-level
`process.exit(0)` terminated the host CLI cleanly — `try/catch` around
`await import()` cannot intercept a synchronous exit, so OMP died at the
`loadExtensions:start` startup marker with no error surface.
Two-layer fix:
- `packages/coding-agent/src/extensibility/utils.ts`: new
`withExitGuard` helper patches `process.exit` for the duration of a
guarded callback so an exit raises `ExtensionExitError` instead of
terminating the process; nested and concurrent guards restore correctly
via depth counter.
- `extensibility/extensions/loader.ts`, `extensibility/hooks/loader.ts`,
and `extensibility/plugins/manager.ts` wrap their dynamic-import sites
in `withExitGuard` so the existing per-module `try/catch` records the
intercepted exit as a load error and OMP keeps starting.
- `discovery/codex.ts:loadHooks` no longer treats arbitrary files as
OMP hooks: only `pre-<tool>.{ts,js}` and `post-<tool>.{ts,js}` are
registered. Files like `memory-bank-reminder.ts` are silently skipped
rather than imported as extension factories.
Adds regression coverage:
- `test/extension-loader-process-exit.test.ts` — `loadExtensions` /
`loadHooks` return errors and leave `process.exit` restored when a
module exits at import time; sibling modules still load.
- `test/discovery/codex-hooks-discovery.test.ts` — codex provider
registers `pre-*` / `post-*` files and drops everything else.
Fixes#3680
Adapted the existing high-non-ASCII idle-compaction regression to the new auto-downgrade contract: compact() is now expected to run, action ends as context-full, and the downgrade warning notice is asserted. Start event keeps reporting snapcompact since preflight runs inside the controller-installed try block.
Auto-compaction now falls back to context-full on any snapcompact preflight or post-render rejection (non-ASCII, kept history too large, projection overflow), matching the text-only-model handling. Manual /compact snapcompact keeps its local-only failure contract per #3599.
Fixes#3659
Propagated the first observed reasoning-content unlock to the active streaming assistant component before the reveal controller re-renders it. Added a regression that starts a hidden thinking-off stream and verifies the first reasoning delta becomes visible.
Tracked received thinking content per interactive session so OpenAI-compatible providers that omit reasoning metadata can still reveal streamed reasoning blocks. Added a Ctrl+T regression covering the unlocked visibility path.
Fixes#3669
The HTML session export bound "toggle thinking" and "toggle tools"
to `Ctrl+T` and `Ctrl+O`. Both are reserved by every major browser
(new tab and open file), so the chord never reached the page and the
advertised toggles were unreachable.
Switch to bare `T` / `O`, ignore the keystroke while focus is in an
`<input>`/`<textarea>`/`[contenteditable]` (so the sidebar search
still accepts those letters), and let any chord with Ctrl/Meta/Alt
pass through to the browser. Help bar updated to match.
Fixes#3670
The handler called event.systemPrompt.join("\n\n") on a value that
upstream system prompt resolution can leave unset, crashing the
extension with 'event.systemPrompt is undefined'. Coerce defensively
so the autoresearch block still renders.
Fixes#3665
Kept the ask tool question and options visible when switching to the Other custom input editor.
Added a regression test for the custom editor title context.
Fixes#3660
Auto snapcompact now switches automatic maintenance to context-full when the active model cannot read image frames, preserving manual snapcompact's local-only failure contract while keeping text-only sessions running.
Fixes#3659
`handleShakeCommand` calls `rebuildChatFromMessages()`, which clears
`chatContainer` and replays only committed `state.messages`. The agent's
in-flight `streamMessage` and its still-pending tool calls live OUTSIDE
`state.messages` until `message_end`, so the live `streamingComponent`
and `pendingTools` entries were detached while their references stayed
live — every subsequent `message_update`/`message_end` event then
updated orphaned components that never re-rendered, and the in-flight
LLM output disappeared from the chat. Other mid-stream rebuild paths
(setting toggles such as `display.cacheMissMarker` and
`tui.renderMermaid`) had the same flaw.
Snapshot the live `streamingComponent` and `pendingTools` (in their
original chat-container order) before clear, re-append after the
historical replay, and restore the `pendingTools` map so the next
streamed tool-call delta routes back into the preserved component
instead of stacking a duplicate ToolExecutionComponent below it. Idle
rebuilds are unchanged.
Fixes#3656
PR #3648 review (codex): the first iteration emitted every envelope
path alongside one combined digest, so a multi-file payload that added
`: any` to a README.md hunk and merely touched src/ok.ts would surface
a *.ts path in the TTSR match context and trip the bundled
tool:edit(*.ts) ts-no-any rule on text that belonged to the Markdown
hunk — aborting valid edits under interruptMode:always.
Add a per-file matcherEntries(args) hook on AgentTool / EditStreaming-
Strategy returning [{ path, digest }] entries, one per touched file
(same-path sections/hunks merged):
- replace / patch: one entry from the top-level path + matcherDigest
- hashline: regex-split by [path#TAG] section, body added-lines per
entry (tolerant of streaming partial payloads)
- apply_patch: expandApplyPatchToPreviewEntries grouped by path
AgentSession.#checkTtsrStream / #checkTtsrAstStream now prefer
matcherEntries and iterate per-file with isolated filePaths + streamKey,
so each file's buffer and repeat-tracking are independent. Tools
without matcherEntries keep the existing combined matcherDigest +
matcherPaths path.
- Standardized retry logic to ensure mocked assistant turns and generic aborts share the same reset path as live provider failures.
- Introduced a classification helper that forces retry policy alignment with the currently active session model.
- Enabled retries for generic reason-less abort sentinels and stale OpenAI response errors.
AgentSession's TTSR match context only scanned top-level path/paths
arguments, so hashline and apply_patch edit streams (whose only target
path lives inside the wire payload — section headers or envelope
markers — not as a top-level argument) arrived without any filePaths
and silently skipped path-scoped rules like the bundled ts-no-any
(scope: tool:edit(*.ts)).
Add an optional AgentTool.matcherPaths(args) hook, companion to the
existing matcherDigest(args), so tools whose wire grammar embeds paths
can surface them. Implement on each edit streaming strategy:
- replace / patch: top-level path
- hashline: parse [path#TAG] (and tag-less [path]) section headers
tolerant of streaming partial payloads
- apply_patch: parse *** Add/Update/Delete File: markers, also tolerant
of pre-End-Patch buffers
AgentSession.#getTtsrToolMatchContext consults tool.matcherPaths first,
normalising its output through the existing path-candidate helper, and
falls back to the generic top-level argument scan for tools that don't
implement it.
Fixes#3646
- Replaced functional streaming logic with a stateful `CodexStreamProcessor` class.
- Converted `CodexStreamRuntime` into a class with explicit state initializers and lifecycle methods.
- Encapsulated tool call delta tracking and interruption logic within dedicated class methods.
- Integrated `textSignature` generation into text-type output blocks using versioned encoders.
can1357