- Fixed `SYSTEM.md` integration to correctly include custom-rendered sections like rules and skills.
- Consolidated system prompt validation by requiring `<skills>` tag presence instead of specific prose.
- Removed redundant system prompt math-formatting tests and orphaned task batch documentation tests.
- Replaced regex-based markdown detection with a stateful parser in `detectLiveReflowingMarkdown`.
- Correctly ignore table delimiters and mermaid markers when they appear inside fenced code blocks.
- Added tests to verify that code blocks containing markdown-like syntax do not prevent commit stability.
- Prevent object reference sharing between agent snapshots and stream events by deep-cloning tool-call arguments.
- Stabilize GFM tables and Mermaid diagrams during streaming by delaying transcript block commits until content finalization.
- Implement session resume safety to prevent crashes when working directories are missing.
- Add comprehensive test suites to verify streaming commit stability and immutable snapshot isolation.
Added an advisorEnabled visibility predicate and wired the advisor dependent settings through it so the Model Advisor sub-options hide unless Enable Advisor is active. Added regression coverage for the settings UI adapter.\n\nFixes #3027
- Switch all UI components and tests from sharp box corners (`boxSharp`) to rounded ones (`boxRound`).
- Update `Theme` to re-export sharp junction symbols (tees and cross) under `boxRound` to ensure consistent divider rendering in rounded boxes.
- Remove outdated architectural notes regarding forced tool-choice queues in documentation.
- Added `typeof theme === "undefined"` guards to all four theme getters.
- Fallbacks return a usable plain-ASCII or plain-text theme instead of crashing.
- Added a pre-init test asserting the getters never throw.
Fix all Windows-specific test failures caused by path handling problems
and EBUSY errors from unclosed SQLite database handles.
Root causes fixed:
1. POSIX path assumptions: replaced hard-coded file:///tmp, /repo, etc.
with pathToFileURL/path.resolve/path.join computed expectations
2. shortenPath() now normalizes backslashes to forward slashes after ~
and respects home directory boundaries
3. HistoryStorage.resetInstance() leaked its Database — added #close()
that finalizes all prepared statements and closes the DB
4. AgentStorage gained the same resetInstance()/#close() pattern
5. SqliteAuthCredentialStore.close() leaked one-off prepared statements
from inline this.#db.prepare() calls — wrapped each in try/finally
6. model-cache.ts used a process-global DB even for custom dbPath —
now opens/closes per-call via withModelCacheDb
7. createAgentSession leaked AuthStorage on construction failure —
added ownsAuthStorage cleanup in catch block
8. MnemopiBackend.removeDbFiles() now truly best-effort (catches errors)
9. TempDir retry window expanded from 4x10ms to 40x25ms
10. TempDir prefix convention: non-@ prefixes created dirs relative to
cwd instead of os.tmpdir() — all test temp dirs now use @ prefix
11. Shell-escaped interpolated paths in bash tool tests
12. git core.autocrlf false in autoresearch test repo init
All 522 previously-failing Windows tests now pass.
A login entry can store credentials under a different provider id via
storeCredentialsAs (e.g. openai-codex-device => openai-codex). Filtering
only on provider.id left such alias logins visible after disabling the
underlying model provider. Surface storeCredentialsAs on OAuthProviderInfo
and hide a login entry when either its own id or its storeCredentialsAs
target is in disabledProviders.
Addresses Codex review on #2906.
- Migrated all wire protocol, schema definitions, and tools validation from Zod to ArkType across multiple packages.
- Updated extension runtimes, custom tools loader, and TypeBox compatibility shim to expose and use ArkType instances.
- Added a comprehensive ArkType migration guide, validation parity tests, and helper utilities.
- Removed redundant PDF asset routing and parsing implementations from the read tool.
The /login selector listed every OAuth-capable provider regardless of the
disabledProviders setting, so providers hidden from the model picker still
appeared as login targets. Filter them out in login mode (logout stays
unfiltered so stored credentials of a now-disabled provider can still be
removed).
- Added cursor save/restore escape handling around direct image emission.
- Replaced the previous up-and-down cursor movement sequence with restore logic to keep renderer output positioned correctly.
- Ensured direct image replay path no longer depends on moving back down after placement to align the cursor.
- Added Matplotlib figure PNG rendering and display tracking in Python runner to emit PNG output immediately when figures are displayed via display(fig).
- Extended session persistence to externalize oversized image payloads in both content and details.images, enabling tool result images to survive session reload.
- Enhanced session loader to resolve image data payloads and blob references across content and details.images during session reconstruction.
- Added image cache invalidation in TUI image component when image protocol, cell dimensions, or Kitty Unicode placeholder mode changes.
- Added comprehensive test coverage for Matplotlib display, image persistence across reload, and TUI image rendering with protocol and dimension changes.
- Updated `executeSearch` to read `providers.antigravityEndpoint` once and catch uninitialized-settings errors, so web search fallback no longer aborts before any provider runs.
- Added missing `Vision` and `Git` entries to `TAB_GROUPS` so those new settings now render in their intended setting-section groups.
- Adjusted context and idle-compaction tests to wait for prompt-in-flight transitions and provide `getContextUsage` for deterministic snapshots during pending turns.
- Forwarded `parentAgentId` through task and eval launch paths when spawning subagents.
- Mapped `parentAgentId` to `parentId` in `createAgentSession`.
- Passed each caller's session `getAgentId` (or `MAIN_AGENT_ID`) as the parent for spawned agents.
- Added advisor context maintenance hook and token estimation before prompting for auto-upkeep.
- Added re-prime replay handling to reset advisor context and recover deferred prompts.
- Implemented session-level context compaction with model promotion and snapcompact-first fallback summarization.
- Surfaced advisor settings in the model tab and updated advisor system guidance text.
Render a breathing dots pulse (·‥…‥) in place of a hidden thinking block while the model is actively reasoning, so streaming progress is visible with hideThinkingBlock enabled. The pulse shows only while the block is live (not finalized), thinking is hidden, no tool call has started, and the tail block is thinking; it yields to streamed text and is removed when the block is sealed.
- WelcomeComponent now lazily selected and cached a tip per instance, preserving it across re-renders.
- With the unicode preset, it showed a special nerdfont tip 10% of the time and otherwise used the regular tip rotation.
- Added tests that mocked theme preset and Math.random to verify standard and special tip selection behavior.
- Tracked seen-line provenance in snapshots and propagated it from read/search/ast-grep rows.
- Rejected hashline edits on unseen lines before patching, throwing unseen-line errors.
- Rejected single-line block anchors in strict mode and dropped them in unresolved lenient mode.
- Trimmed one-sided keeper-echo duplicates during multi-line replacements with warning output.
- Removed the streaming guard that previously rejected /tan while the parent response was still generating.
- Passed "deliverAs: \"nextTurn\"" when sending the background dispatch breadcrumb and kept "triggerTurn: false" so an in-flight turn is not steered.
- Skipped rebuilding chat messages during streaming sessions and updated tests to cover the non-blocking dispatch path.
- Added a setup-system-deps action with preloaded-runner guards and apt fallbacks.
- Updated CI workflows to download Linux x64 native artifacts and gate on native job success.
- Renamed coding-agent fast mode to singleton in scripts and test partitioning logic.
- Added settings test-state begin/restore helpers with recursive cleanup in affected tests.
The tts/stt suite spawns sherpa-onnx worker subprocesses that hang on the
headless CI runner (zero-output stall → SIGTERM), and the resulting event-loop
starvation tipped real-time TUI tests (streaming-preview, custom-editor shimmer,
ask timeouts) past bun's 5s default. Remove the tts/stt tests and give the
timing-sensitive tests an explicit 30s timeout.
- model-resolver: removed three resolveAgentModelPatterns cases that pinned exact
priority.json model names (gpt-5.4 / gemini-3 designer list); priority.json now
leads slow with gpt-5.5 and includes gemini-3.5-flash, so the hardcoded lists
were stale. The remaining cases still cover cross-role alias inheritance and
configured-override precedence.
- settings-selector: removed the condition-hidden group-title assertion that
depended on the pre-autolearn memory-tab group layout.
- Stopped and cleared the working loader before auto-compaction and auto-retry.
- Ensured stale loadingAnimation is removed so agent_start recreates the Working loader.
- Set catalog model input/output costs to 0.09/0.18 and reduced maxTokens to 65536.
- Routed `customType: "handoff"` messages to the compact divider path in Agent Hub and UI helpers.
- Added handoff summary expansion that extracts context text and strips `<handoff-context>` wrappers.
- Refactored shared divider rendering into `SummaryDividerComponent` used by compaction and handoff messages.
`restoreQueuedMessagesToEditor` prepended queued text but appended queued
images to `pendingImages`. Positional `[Image #N]` lookup at submit time
therefore broke whenever the editor draft already held pending image(s):
queued markers (numbered 1..K against their own image list) collided with
draft markers (1..M) and resolved to the wrong images; queued images
landing past slot M were orphaned.
Add `shiftImageMarkers(text, offset)` to `image-references.ts` and have
`restoreQueuedMessagesToEditor` walk each queued message in order,
shifting its markers by the running pending-image count (existing draft
images plus images already pulled in from earlier queued messages). Draft
markers stay untouched because draft images keep their original slots.
Paste markers are left alone — those are owned by the editor's paste store,
not the pending-image buffer, and queued message text never carries
unmaterialized `[Paste #N]` because the editor expands paste markers in
`getExpandedText()` before `onSubmit` fires.
Regression test seeds a draft image + a queued image-message in
`input-controller-compaction-image.test.ts` (per acceptance) and locks the
marker -> image mapping after restore. Unit tests for
`shiftImageMarkers` cover the WxH tail, Paste-marker passthrough, and
the zero-offset no-op.
Fixes#2531
- Added session-domain modules and exports for session-entries, context, listing, loader, and migrations.
- Changed persistence to async append writes plus writeTextAtomic, removing sync line APIs.
- Added compaction-aware session context rebuild with dangling tool-call cleanup.
- Added resumable session resolution with status inference, id/stem/suffix matching, and backup recovery.
- Added a changelog entry describing that submitted user messages no longer pair OSC 133 command-start markers with missing end markers.
- Annotated the user-message component with guidance to avoid emitting OSC 133 command-start markers for submitted prompts.
With display.showTokenUsage on, the usage row was rendered inside the
assistant block above the turn's tool blocks. Finalizing the assistant
block was therefore deferred, and the late append recommitted the
already-committed tool rows, duplicating them in scrollback (worst with
parallel tool calls).
The assistant block now always finalizes as soon as a tool-call appears,
and the usage row is emitted as a standalone finalized block below the
turn's tool blocks across all three render paths (live event-controller,
transcript rebuild, agent-hub). The now-dead setUsageInfo/#usageInfo path
on AssistantMessageComponent is removed.
The whole-line editor decorate ran on `displayText` after the editor appended
the zero-width CURSOR_MARKER and cursor glyph; both start with ESC, so the
magic-keyword regex's right-boundary `(?!\S)` rejected `ultrathink` glued to
the marker and dropped the gradient until a trailing character was typed.
- `Editor.#decorate` (pi-tui) now splits around CURSOR_MARKER and decorates
each user-text segment independently, so word-boundary lookarounds resolve
correctly on both sides; the matching comment block is corrected.
- `KeywordHighlighter` / `highlightMagicKeywords` gain an optional `phase` in
[0, 1) that cyclically rotates the gradient stops. `0` (default) yields
the static palette, so sent-bubble rendering is unaffected.
- `CustomEditor.decorateText` derives `phase` from `Date.now()` and chains
`setTimeout(SHIMMER_FRAME_MS)` ticks while focused, the buffer holds a
magic keyword, and `magicKeywords.enabled` is on — the render itself
schedules the next frame, so losing focus, deleting the keyword, or
flipping the setting stops the animation on its own. `interactive-mode`
wires the repaint hook to `requestComponentRender(editor)` on construction
and after `setEditorComponent`.
- Adds `hasMagicKeyword(text)` (cheap prose-aware probe) and tests for the
seam fix, the phase cycle, the gating, and timer cleanup.
Fixes#2475
- Added tail-only transcript rendering via `renderViewportTail`, stopping at `maxRows` and returning `EMPTY_TAIL`.
- Added `ViewportTailProvider`/`asViewportTailProvider` API and resize getters for viewport state.
- Implemented viewport-only painting during non-mux resize with deferred full repaint after settle.
- Added settle-resize helpers and coverage for deferred repaint timing and cancel paths.
can1357