- Ensures in-memory overlay edits are durably written to the plan file before proceeding with approval.
- Avoids asynchronous write races by awaiting the final plan file serialization.
- Aligns synthetic approved-plan prompts with reference-only expectations.
- Thread the postmortem reason through the session teardown pipeline to the session dispose process.
- Prevent generic "dispose" logs from overwriting real triggers like SIGTERM, SIGHUP, or uncaught exceptions.
- Ensure the first teardown trigger's reason is preserved when concurrent disposal calls occur.
- Add comprehensive test coverage verifying signal-specific reason mapping inside exit diagnostics.
- Fix a minor unhandled-exception test utility expectation in input controller tests.
- Guard against 16-bit snapshot tag collisions by requiring live text to be byte-identical to the retained snapshot.
- Transition base text resolution to query exact matches via `snapshots.byHashExact`.
- Prevent applying incorrect preview edits when live file contents drift to a colliding state.
- Fixed grep and ast-grep tools rejecting fuzzy url-shaped paths like schemeless www. or collapsed-scheme spellings.
- Applied the extra-CA wrapper to the model registry default fetch to respect the NODE_EXTRA_CA_CERTS environment variable.
- Moved isReadableUrlPath utility to path-utils to share recognition logic between reading and searching pipelines.
- Implemented a fallback that checks if a directory matching a fuzzy URL path exists locally before resolving it as an external URL.
- Added explicit errors for unsupported URL schemes to replace misleading local-path errors.
- Implemented safe `releasePermit` helper to track whether a concurrency permit has been acquired before releasing.
- Guarded against double-releasing or releasing unacquired semaphore permits during queued job cancellation or abort events.
- Added comprehensive unit tests validating concurrency cap enforcement when queued jobs are cancelled.
- Extends output schema validation to support `oneOf` and `anyOf` closed union schemas.
- Prevents unknown section label submissions when all union variants constraint allowed properties.
- Permits arbitrary yield labels when at least one union variant remains open.
- Supports JTD discriminator output schemas by treating union constraints disjunctively.
- Prevents connection hangs during initial join by immediately failing when a host rejects a guest prior to welcome.
- Short-circuits the connection welcome timeout upon receiving a pre-welcome error frame.
- Surfaces exact protocol mismatch and hello rejection reasons directly to the joining guest interface.
- Ensures `CollabGuestLink` and `GuestClient` transition immediately to ended/failed states with host error details.
Added AnthropicOptions.fallbacks + wire types + response parsing gated on the opt-in — server-side fallback stays fully inert on every request that does not set the option.
Coding-agent surfaces the feature via providers.anthropic.serverSideFallback (default off). When enabled, Fable/Mythos requests inject fallbacks: [{ model: claude-opus-4-8 }]; caller-supplied fallbacks always win.
transformMessages centrally strips persisted fallback blocks on cross-provider hops and non-official Anthropic replays so a stored fallback turn never wedges downstream converters. Retry resets restore output.model to the requested id.
Fixes#4177
- Extracted decodeStreamedToolArgs into tool-args-reveal.ts and used it from both the live event path and transcript rebuilds, so mid-write theme/settings/focus replays no longer show stale streamed write/edit/eval content.
- Fixed the smoothing-off live path returning stale provider-parsed args.
- Documented the mandatory shared decode in the AGENTS.md streaming-preview hazard note; added changelog entries for this batch.
- CollabGuestLink now handles ui-request/ui-request-end frames via the existing hook selector/editor dialogs and round-trips ui-response; cancellation, resync replay, and read-only peers are handled.
- Added GIT_NETWORK_TIMEOUT_MS (30 min) for clone/fetch with an overridable timeoutMs option; local plumbing keeps the 5-minute cap.
- Migrated fetch() from a positional AbortSignal to an options object.
- Bumped the dynamic-model cache namespace rich-v1 -> rich-v2 in the catalog manager and the coding-agent configured-discovery callsite so the #3717 reseller-suffix mappers reach users with a warm 24h cache.
- Made CompactionSettings.reserveTokens optional so field presence carries provenance; the proportional small-window fallback only applies to genuinely defaulted reserves.
- Clamped the fallback reserve to >= 1 and the derived threshold strictly below the context window.
- Changed the coding-agent settings-schema default from 16384 to unset so Settings.get() no longer materializes a default that masks provenance.
Clarified hashline minus-row errors and model-facing prompt examples so Markdown list rows use the + body-row prefix instead of triggering write fallbacks.
Fixes#4179
Failed stash-pop cleanup now invokes git clean with literal pathspecs for
stash-derived untracked paths. Filenames such as `:(glob)*` are valid POSIX
filenames and valid Git pathspec magic; passing them as ordinary pathspecs with
`-x` could delete unrelated ignored artifacts that were never stashed and are
not recoverable from the preserved stash.
Extend the fallback regression with a literal `:(glob)*` stash file and an
ignored `build.log` that must survive cleanup.
Fixes#4175
When a task branch adds ignore rules for a path that was untracked in the
user's stashed WIP, a failed stash pop can restore the file and then leave it
hidden from normal status after reset. Default `git clean -fd -- <path>` does
not remove ignored files, so the partial restore could still leak into later
isolated task baselines.
Add an includeIgnored clean mode and use `git clean -fdx -- <stash path>` for
failed stash-pop cleanup. Extend the fallback regression so the task branch adds
.gitignore for the restored untracked path and verify both normal and ignored
status return clean.
Fixes#4175
- Restored CustomInputRow.priority field dropped in 3b80dc01d ask row budgeting.
- Narrowed dereferenced schema properties via isRecord in yield-assembly and output-schema-validator instead of untyped object access.
- Renamed stale advisorReadOnlyTools to advisorTools in advisor parity test.
- Narrowed AgentMessage content access in session-loader-stream test.
- Reformatted browser-schema test to satisfy biome.
- Removed a duplicated branch.reverse() left by the PR #3862 merge in
SessionEntryIndex.pathTo(), which returned branches leaf-to-root and made
getLastModelChangeRole() read the oldest model change instead of the
newest — pinning the ctrl+p cycle to one slot and breaking session model
restore.
- Hardened getRoleModelCycle() to trust the recorded role only while its
resolved model still equals the active model, falling back to matching by
model after switches through alt+m, /model, or retry fallback.
- Added mutation-verified regression tests for branch ordering and the
stale-role fallback.
A failed `git stash pop --index` can restore unrelated untracked files before
exiting on a tracked conflict while still preserving the stash entry. The
previous fallback only reset tracked/index state, leaving those untracked files
in the working tree for subsequent task baselines.
Record the top stash entry's untracked paths before popping and clean exactly
those paths if the pop fails after preflight. Add a regression that forces the
fallback branch and verifies the worktree returns clean with the stash preserved.
Fixes#4175
mergeTaskBranches and applyNestedPatches both stashed dirty WIP, cherry-picked
task branches, then called `git stash pop` in a finally block. On conflict git
left stage 1/2/3 unmerged entries in .git/index with no MERGE_HEAD to abort;
neither call cleaned up. The corrupted index persisted indefinitely, and every
subsequent overlay-isolated task inherited it through the lower layer —
captureRepoDeltaPatch then emitted `diff --cc` (combined merge format) that
git apply rejects with "No valid patches in input", failing every downstream
task merge with 'Branch merge failed before a task branch could be created'.
Fix at the git API level: git.stash.tryPop now runs `git apply --3way --check`
on `git stash show -p --binary stash@{0}` before popping (`--3way` matches
what git stash pop does internally, so context that drifted after cherry-pick
is still accepted). Preflight failure short-circuits — stash entry preserved,
index untouched. Preflight pass falls through to pop; if pop still leaves
unmerged entries (mode-only or delete/modify conflicts the preflight can miss),
a `reset --hard HEAD" fallback restores the merged HEAD without losing the
cherry-picked commits (stash is preserved by git on failed pop, so the user's
WIP stays recoverable).
Both call sites now share this contract via git.stash.tryPop.
Fixes#4175
- Consolidated `browserOpenSchema`, `browserCloseSchema`, and `browserRunSchema` into a single `browserSchema`.
- Simplified the `action` type definition to accept `'open' | 'close' | 'run'`.
- Updated schema validation tests to reflect the unified schema definition.
Ports only the thinking double-format fix: resolveThinkingDisplay reuses block.thinking when rawThinking is set (buildDisplayMessage already formatted it), plus a single-entry memo in formatThinkingForDisplay and a rawThinking regression test. The PR's incremental reveal slicing is superseded by the already-merged #3848 (memoized grapheme slicing).
Cherry-pick of the reserve-budget clamp only (resolveBudgetReserveTokens + no-op compaction guard): applies compaction.ts + agent-session.ts + compaction/shake/progress-guard tests. Excludes unrelated Julia prelude timeout and ai/test churn from the PR head.
/quit and /exit hung for many seconds because AgentSession.dispose()
awaited MnemopiSessionState.dispose() unconditionally, and that path
runs consolidate() (state.ts:421) which fires a fresh LLM fact
extraction for the just-retained transcript and then awaits
flushExtractions() per owned bank. One LLM round-trip per shutdown,
no upper bound, no visible status.
- Add a timeoutMs option to MnemopiSessionState.dispose. When the cap
fires the in-flight consolidate is detached to the background and the
SQLite handles close once it settles, so writes never race a closed
handle.
- AgentSession.dispose passes SHUTDOWN_CONSOLIDATE_BUDGET_MS = 1_500 on
the user-visible shutdown path. Per-turn maybeRetainOnAgentEnd has
already retained earlier turns, so the worst case is losing episodic
promotion for the last few turns. State-replacement disposes
(mnemopiBackend.start) stay unbounded.
- InteractiveMode.shutdown surfaces a 'Closing session…' status before
dispose runs so the brief pause is explained rather than mysterious.
Two regression tests in memory-tools.test.ts cover (1) dispose returns
within the budget when flushExtractions stalls and the deferred close
still runs once consolidate settles, and (2) unbounded dispose still
runs the full #2320 consolidate-then-close pipeline.
Fixes#3641
can1357