- Added `images.describeForTextModels` configuration defaulting to true for text models.
- Added `describeAttachedImagesForTextModel` to persist images and generate local:// descriptions.
- Added image-description notices to session flow with hidden typing and pre-user insertion.
- Added fallback behavior that returns notes when vision is unavailable or output is empty.
- Added default system-prompt guidance to scan skill descriptions and read applicable skill:// content before work.
- Covered the rendered prompt contract with a frontend-design skill regression test.
Fixes#2829
Recorded todo reminder developer messages in the session log so JSONL transcripts match model-visible context when reminders are enabled.\n\nFixes #2824
Merge displayed bridge-backed range and multi-range read lines into the existing hashline snapshot provenance so INS.POST anchors pass visible-line validation after ACP reads.
Fixes#2773
- Added a new `--advisor` flag to argument parsing and launch flag definitions.
- Applied the parsed `advisor` flag as a runtime-only override of `advisor.enabled` during startup.
- Updated advisor-related docs and added parseArgs tests for `--advisor` behavior and position handling.
- Gave reasoning-capable local auto-thinking classifiers the safe 1024-token answer budget used by online reasoning classifiers.
- Raised the non-reasoning local classifier floor to 16 tokens and allowed tiny completions to honor larger explicit budgets.
- Added regression coverage for qwen3-1.7b and qwen2.5-1.5b local classifier budgets.
Fixes#2808
- Removed the Codex-preferred canonical remapping path for exact `provider/id` model matches.
- Resolved explicit `openai/gpt-5.5` references as `openai` provider without redirecting to `openai-codex`.
- Added regression tests to confirm explicit provider/id and enabled-model patterns are not coalesced to Codex.
- Added an optional `cwd` parameter to `looksLikeLocalPath` so bare-name local-directory detection resolves against an explicit path; the install-command test now passes a temp dir instead of `process.chdir`-ing into it.
- Removed `issue-1423-repro.test.ts`, whose package-dir-lookup repro relied on `process.chdir` to stage an isolated project.
- Made `JsRuntime` track the realm globals it installs (`#globalOwner`, `#ownedGlobalKeys`, `PRELUDE_GLOBAL_KEYS`) and reclaim them in `dispose()`, re-binding ownership through `#activateGlobals()` on cwd/run-scope/run; disposing an older inline/direct runtime no longer deletes a newer runtime's helper globals, and overlapping same-realm runs are serialized via `enterGlobalRun`.
- Added `WorkerCore.dispose()` (rejects pending tool calls with `ToolError` and disposes the runtime) and invoked it from `spawnInlineWorker` teardown in `context-manager.ts`.
- Updated the `js-static-import-rewrite` test to snapshot and restore any pre-existing `__omp_import__` global instead of unconditionally deleting it.
- Added `runtime-global-dispose.test.ts` covering newer-runtime global survival, older-runtime reactivation, and cross-runtime mutation rejection.
- Clarified the `runWorkerEntrypoint` comment in `cli.ts` about `parentPort` sync-prefix buffering for tab/eval workers.
Limit provider-priority ranking to provider defaults that share the first fallback default id, preserving mixed-provider startup precedence while keeping the OpenAI/Codex tie fix.\n\nFixes #2807
Route stale OpenAI GPT default roles through canonical Codex selection when the catalog prefers the Codex OAuth transport, and rank shared provider defaults by canonical provider priority.\n\nFixes #2807
- Removed the obsolete non-resumable idle-steer test and updated comments to reflect immediate continue scheduling for idle steering.
- Added a real-timer streaming scenario with a mock model to verify queued image steering is surfaced through clearQueue as normalized text/images while the session is streaming.
- Fixed cold revival flow so parked subagents are restored from persisted sessions at startup.
- Fixed session-init persistence to include spawns and readSummarize fields for replay accuracy.
- Fixed latest-session lookup by adding peekSessionInit for lock-free persisted contract access.
- Added lifecycle and session tests for cold-revive success, decline, and retry paths.
- Queued advisor concern cards now get reclaimed as visible advice during settle when auto-resume suppression is active and the session is idle.
- Preserve logic was narrowed to keep advisor cards hidden only during abort teardown, allowing steers during resumed streaming turns.
- A regression test was added to verify stranded advisor steers are persisted as visible advice without triggering an advisor-only resume turn.
- 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.
- Fixed Agent Hub display to render in editorContainer instead of floating ui overlay.
- Fixed close flow to clear editorContainer, re-add the editor, and restore editor focus.
- Updated Agent Hub activation tests and removed the probe test fixture.
Kept shutdown flushes lazy while allowing explicit atomic rewrites to materialize pre-assistant session entries.
Added regression coverage for rewriteEntries before the first assistant message.
Fixes#2800
- Added latexToBlock module that renders stacked fraction math with baseline-aware rows.
- Updated markdown rendering to route display math through latexToBlock with sole-display handling.
- Exported latexToBlock from the package entrypoint and updated changelog docs accordingly.
- Added advisor resume and suppression repro tests in coding-agent for interrupted turn recovery.
Prevented shutdown flushes from materializing sessions that never produced assistant output, and kept close from marking a non-existent session file current.
Added regression coverage for opening omp and exiting before any prompt or assistant turn reaches history.
Fixes#2800
Preserved Settings.disabledExtensions fallback when extension discovery is called without an explicit disabled list and kept hookCapability paths out of extension-module basename filtering.
Fixes#2796
- Added LaTeX math and Mermaid allowances in terminal and final-chat prompts.
- Added inline math tokenization in TUI for $, $$, \(\), and \[\].
- Added LaTeX-to-Unicode conversion helpers and exports for math rendering.
- Fixed inline math detection to skip escaped dollars and currency-like spans.
Included JS and TS hookCapability results in extension path discovery so hooks under hooks/pre and hooks/post bind to the extension runner without explicit settings entries.
Fixes#2796
- Removed render_mermaid from tool discovery, task definitions, and registries.
- Removed renderMermaid setting and prompt/docs references tied to the deleted tool.
- Added maxWidth and theme color options to Mermaid ASCII resolution in markdown flow.
- Re-rendered Mermaid ASCII in both directions and clipped output to available width.
- Rewrote `formatSessionDumpText` in `session-dump-format.ts` to emit the pre-16.x full dump: system-prompt prelude, model/thinking config, tool inventory with parameters, and the transcript as markdown role headings (`## User`, `## Assistant`, `### Tool Call`/`### Tool Result`), reusing `renderDelimitedThinking` for `<thinking>` blocks.
- Dropped the compact default and the `[raw]` flag from `/dump`: removed the `isRaw` parameter from `handleDumpCommand` in `command-controller.ts`, `interactive-mode.ts`, and `types.ts`, and removed the `inlineHint: "[raw]"`/`compact` plumbing in `builtin-registry.ts`.
- Updated the `formatSessionAsText` doc comment in `agent-session.ts` to describe the verbose dump shape.
- Removed the obsolete `formatSessionDumpText raw thinking` suite from `advisor.test.ts` and refreshed `session-dump-format.test.ts` to assert the verbose dump output.
- Recorded the revert in the coding-agent changelog and trimmed `/dump` from the compact transcript tool-intent-prefix entry.
- Introduced advisory note output as `<advisory>` tags with optional severity and guidance.
- Updated session transcript formatting to `### Session update` and inline watched role labels.
- Added shared `escapeXmlText` utility and escaped XML-sensitive text in advisor outputs.
- Added one-shot success run token metrics and one-shot statistics reporting.
- Generalized `isUserQueuedMessage` to a user-attribution predicate (`role === "user"` or custom `attribution === "user"` and not display-suppressed) so visible agent-authored steers (advisor cards, IRC/extension asides) and hidden goal/plan/budget steers are all excluded from editor restore, not just advisor cards.
- Gave `AgentSession.clearQueue` a `{ forInterrupt }` option: plain Alt+Up dequeue restores user messages and preserves every other queued message for the continuing stream, while Esc+abort keeps only advisor cards (for `abort()`'s `#extractQueuedAdvisorCards` preservation) and drops other internal steers so the post-abort `#drainStrandedQueuedMessages` can't auto-resume the interrupted run.
- Threaded `forInterrupt: options?.abort` from `InputController.restoreQueuedMessagesToEditor` and kept `queuedMessageCount` on actual displayable-queue semantics so `hasPendingMessages()`/RPC and the empty-submit abort gate stay accurate.
- Updated skill-queue tests to cover both policies (hidden and visible agent-authored steers preserved on dequeue, dropped on interrupt) and refreshed the changelog entry.
- Added a `suppressBreadcrumb` option to `SessionManager.open()` so headless opens skip writing the per-TTY `--continue` breadcrumb, and passed it from the subagent opens in `task/executor.ts` and the HTML export open in `export/html/index.ts`, which run in the parent's terminal and were clobbering the breadcrumb with their own artifact-dir session file.
- Added `resolveBreadcrumbToInteractiveRoot()` and applied it in `continueRecent()` so already-poisoned breadcrumbs pointing inside a parent's artifacts dir (`<parent>/<agentId>.jsonl`) resolve back up to the top-level interactive session.
- Added `subagent-breadcrumb.test.ts` covering both that a subagent open keeps `--continue` on the parent and that a stale subagent-pointing breadcrumb is recovered.
- Added `isUserQueuedMessage()` to `agent-session.ts`, treating only plain user turns and visible `attribution: "user"` custom messages (e.g. `/skill`) as restorable, so advisor concern/blocker notes, hidden goal/plan/budget steers, and IRC/extension asides no longer leak into the editor on Esc/Alt+Up.
- Reworked `clearQueue()` to return only user-authored messages while re-queuing advisor cards via `replaceQueues()` (so the user-interrupt abort path still re-records them as advice) and dropping other agent-authored steers to prevent a silent auto-resume on leftover internal context.
- Filtered `getQueuedMessages()` chips and rewrote `popLastQueuedMessage()` to skip agent-authored cards and pull the last user-authored entry, while `queuedMessageCount` still counts all displayable queued work.
- Extended `input-controller-skill-queue.test.ts` with a `queueAdvisorSteer` helper and cases asserting advisor/IRC cards count as pending work but stay out of chips, restore, and `popLastQueuedMessage`, and survive `clearQueue()`.
- Changed `InputController`'s no-input-waiter submit path to call `session.prompt(text, { streamingBehavior: "steer", images })` instead of `session.steer(text, images)`, so a submission made while the loop is idle between turns starts a real prompt rather than queueing behind a non-resumable transcript; the steer streaming behavior still preserves queueing if a background turn races in.
- Updated the failure-recovery comment to reference prompt dispatch rejection.
- Rewrote `input-controller-orphan-submit.test.ts` to assert the `prompt` dispatch path and added a real-session case proving an orphaned idle submit starts via `agent.prompt` (not `continue`) and leaves no queued messages.
- Added the `### Fixed` CHANGELOG block under `[Unreleased]`; its three entries are adjacent lines forming one indivisible run, so this commit also carries the changelog text for the queued-restore and breadcrumb fixes that follow.
Install a subagent's ordered model candidates as child-session retry fallback chains so a retryable provider failure advances to the next candidate instead of killing the worker (issue #2750).
Isolate the plugin-discovery test from the real ~/.omp on all platforms via an os.homedir mock, cleared XDG vars, and a pre-write guard (issue #2721). Supersedes #2724 (Windows-only).
Auto-retry empty/reasonless provider aborts without model fallback (issue #2685). Includes review fix b7a3d01439: skip the retry while the session is disposing to avoid a shutdown hang.
Re-inject eager task/todo reminders after compaction (reminder-only, no forced tool_choice; issue #2681). Supersedes #2686. Known follow-up: shake-strategy compaction may duplicate a surviving prelude.
Default Windows bash child processes to a UTF-8 locale; win32-gated so POSIX behavior is byte-identical, and existing user LANG/LC_* values are preserved.
Load .github/instructions/*.instructions.md as rules. Includes review fix c509a5d59c: split comma-separated applyTo via parseCSV and treat **/* as an always-apply glob.
can1357