- The xd registry reconciles before the async prompt rebuild while the
active tool swap lands after it; polling the mount alone raced the
write-transport activation on slow runners.
- Implemented native UTF-16 text processing in Rust diff module with support for unpaired surrogates.
- Removed `similar` crate from Rust workspace and `diff` npm package from coding-agent, hashline, and natives.
- Removed jsdiff fallback wrappers and `isWellFormed()` guards from TypeScript diff implementations.
- Added comprehensive test suite for native diff functions covering random inputs and edge cases including surrogates and emoji.
- Renamed model `codex-auto-review` to `gpt-5.3-codex-spark` with updated pricing and context window.
- Replaced the subprocess-based delayed-banner test with in-process
tests of the exported waitForTcpServerListening gate (banner split
across chunks, stdout end without banner).
- Dropped wall-clock elapsed assertions from the ghost-socket tests;
the connection-closed rejection message already distinguishes the
wake path from a request timeout.
- logger-multiprocess asserted the UTC day (toISOString) while DailyRotateFile names files with the LOCAL date, failing nightly between 00:00 and 02:00 local (UTC+2); the per-pid rotation-file invariant now matches any dated name.
- kimi-code k3 bundled compat moved to thinkingFormat 'kimi' with the catalog regen; the K3 named-tool-choice downgrade gate keys on provider/id/baseUrl, so only the stale precondition needed updating.
- Repointed tests off removed gpt-5.2/5.3 codex variants and devin models (e06ac0b787): context-promotion and TTSR tests pin gpt-5.5 -> gpt-5.6-sol via per-test modelOverrides since no bundled codex model has a runtime-effective promotion target anymore; replay-boundary and history-payload suites use gpt-5.5; advisor quota fallback uses devin/swe-1-6-slow with suffix-less selectors per #4579 devin-agent semantics; gateway-reference pins kilo/giga-potato and now asserts the reference carries effortRouting so the cross-provider no-inherit contract stays meaningful.
- Verified cross-provider gateway references do not inherit wire routing after variant collapse (identity/reference.ts:145-154) - stale test, no product bug.
- Added transcriptMessageComponents to every InteractiveMode ctx test literal; #6033's reuse cache made the field required and addMessageToChat populates it unconditionally.
- Wired setTodoPhases into the eager-todo ToolSession fixture to mirror sdk.ts; the test relied on the stale message_end todo replay #6148 removed.
- Adopted the regression tests from #6228 (@roboomp) on top of the #6233 fix, which supersedes it; both LM Studio cold-cache cases pass against the merged resolver.
A deleted/nonexistent cwd also makes Bun.spawn throw ENOENT; only claim
'git is not installed.' when the working directory actually exists, else
name the missing directory. Addresses the Codex P2 review on #6237.
Aligns the shim's runtime safeParse/__validator with the wire/tool-call
path, so legacy draft-07 documents (tuple items) accept the same values
validateToolArguments does. Adds a regression test.
customToolToDefinition rebuilt ToolDefinition without strict, so the
Task proxies' (and startup MCP tools') explicit strict:false was dropped
before RegisteredToolAdapter and the OpenAI-family serializers saw it.
Declare strict on ToolDefinition, copy it in the bridge, and cover the
proxy -> definition -> registered adapter path in the parity test.
The new global smart-paste listener reused handleImagePaste(), whose
image branches insert [Image #N] into the hidden main editor when a
login/API-key prompt is focused. Mirror the enhanced-paste behavior:
show 'Image paste is not supported in this prompt' and skip image-path
detection so only clipboard text reaches the focused prompt.
Pre-fix resumed sessions wrote cumulative transcript rows under the
incremental ${sessionId}-<ts> source_id shape, so summing every prefixed
legacy row could overshoot the real retained prefix and permanently skip
unseen turns. Use per-row max instead: it can only under-count, which at
worst re-stores one suffix before an explicit cursor row takes over.
Adds a regression seeding a legacy bank with two incremental rows plus a
cumulative resumed row and asserting turns 7-8 still get retained.
can1357