- Add the `providers.cacheRetention` setting to control prompt-cache retention options per request.
- Forward configured cache retention preferences through the settings-aware stream function.
- Update documentation and test coverage for long cache retention behaviors.
- Added `reasoning_effort` kwarg and top-level support for Qwen 3.8+ templates.
- Introduced `qwenTemplateReasoningEffort` compatibility option and identity helpers.
- Enabled default reasoning enforcement and updated cache provider invalidation.
- Added comprehensive unit and compatibility test suites for Qwen reasoning dials.
Retry: widened agent dequeue-hook deadline budgets from 25ms to 1s — the run loop checks the deadline before invoking dequeue hooks, so a cold or CPU-starved mock roundtrip expired the deadline first and the hooks never ran (deterministic failure in isolation, flaky under CI parallel load).
Retry: deflaked tui IME preedit border test (#5563) — VirtualTerminal.waitForRender's fixed 40ms sleep raced TUI's throttled render timer on starved CI runners, reading the pre-input frame; waitForRender now takes an optional settle predicate polled up to 2s and the test keys on the rendered content.
Retry: fixed changelog bundle probe asserting latest release equals VERSION (fails on releases with no coding-agent changelog content); widened issue-4593 watchdog test budgets from 5ms to 50ms against CI runner scheduling noise.
- Updated GPT-5.6 context window floor to 1,000,000 tokens across discovery, policies, and tests.
- Updated model configurations and pricing parameters in catalog models JSON.
Force process termination via `postmortem.quit(0)` in
`Completions.run()` after writing completion scripts to stdout. Loading
all command modules during completion generation leaves open event loop
handles (sockets, timers) that prevent natural process exit, causing
tools like chezmoi to hang.
Per review on #8717: the customSystemPrompt assignment ran after the hook,
so when both options.customSystemPrompt and an extension payload
replacement were set, the option silently won. Now the option is applied
before the hook (the extension can inspect or drop it in its replacement),
matching anthropic, where the hook runs right before serialization and is
the last word on the wire body.
Adds regression tests: replacement drops customSystemPrompt, replacement
overrides it, and the option still applies when the hook returns undefined.
Point xai and xai-oauth at grok-4.6, already in the bundled catalog.
Tests pin the default id in models.json and load picker fixtures from
the catalog so the next bump does not rot hardcoded name or cost.
prepareCompaction walked the branch from the last compaction and ignored reset_boundary markers, so /compact (and auto-compaction) resurrected pre-/clear turns into the summary even though buildSessionContext already starts the model context after the boundary.
Model reset_boundary as a first-class agent-core session entry and start the summarization window after the latest boundary, dropping the superseded pre-reset compaction summary. A boundary before the last compaction stays superseded by it.
Fixes#8718
The onPayload hook contract (README, docs/extensions.md) is that a non-undefined
return replaces the provider request payload, and every provider except these
three implements it (anthropic, openai-responses family, google, ollama — see
the earlier fix for the responses providers). openai-completions, amazon-bedrock
and cursor invoked the hook fire-and-forget and sent the original payload, so
extensions hooking before_provider_request could never transform the wire body
on these providers.
- openai-completions: await the hook and apply a non-undefined replacement to
the params used for the request body, raw request dump and error-path
fallback state
- amazon-bedrock: same for the ConverseStream command input
- cursor: await the hook for the AgentRunRequest; buildGrpcRequest becomes
async and is exported for direct testing (transport is HTTP/2)
- devin-agent intentionally unchanged: it does not fire the hook at all (its
payload is a protobuf object), which is a feature gap rather than a dropped
replacement; documented in README/docs instead
- regression tests: captured wire body reflects async/sync replacement, and an
undefined return keeps the original payload (completions + bedrock over a
mocked fetch; cursor by decoding the serialized run request)
The default snapcompact frame fonts (X.org 8x13 for every provider, plus the selectable 6x12 and legacy 5x8) drew digit zero as a bare oval visually indistinguishable from letter O. Image-based compaction OCRs the frames back, so 0 and O were mixed up and compacted identifiers (e.g. Slack IDs) got corrupted.
Zero now carries a disambiguating interior mark the O lacks: an ascending slash in 8x13 and a center bar in 6x12/5x8. unscii-8 (8x8/6x6u shapes) already shipped a slashed zero and is unchanged.
Fixes#8713
- Added live tracking and stale status warnings for agent activity snapshots.
- Fixed text wrapping with ANSI escape sequences to defer style open sequences after whitespace.
- Added VirtualRenderScheduler for deterministic virtual-clock rendering tests.
- Replaced the `setup` script in `package.json` with a call to `bun scripts/setup.ts`.
- Added `scripts/setup.ts` to run install, native build, coding-agent linking, and `link-omp` steps in order with step-level failure handling.
- Extended `scripts/bazel-natives.ts` with a `--cargo` flag, forbidding incompatible `--source`/bazel arg combinations, and using it to force local host backend selection.
- Replaced `join("\\n") + "\\n"` concatenations with template-literal interpolation in mid-spawn registry fixtures.
- Updated the three Bun.write calls in `persisted-mid-spawn-stub.test.ts` to use the template form.
BiomeClient#parseJsonOutput expected a stale --reporter=json shape
(location.path.file, byte-offset span, description), so the shape guard
dropped every diagnostic against Biome 2.x output and lint() returned []
with no warning. Parse the current schema instead: string location.path,
1-indexed location.start/end {line,column}, and message. Drop the now-dead
offsetsToPositions helper and warn when a non-empty diagnostics array has
no recognizable location, so future schema drift surfaces instead of
silently reporting "no lint issues".
Fixes#8694
Opened the current Bailian API-key management page from the China interactive login flow and updated its user guidance.
Added regression coverage for the emitted auth URL and instructions.
Fixes#8691
- Forwarded MCP image blocks to the agent and TUI without copying their base64 payloads.
- Retained existing text and resource formatting around image blocks.
- Added regression coverage for mixed text and image tool results.
Fixes#8687
can1357