- Added per-path edit versioning in `EditTool` to drop stale late diagnostics after later edits.
- Added deferred diagnostics queueing through `queueDeferredDiagnostics` and late-diagnostic yield batching.
- Updated `UiHelpers` to render late diagnostic file path and summary lines in the chat transcript.
- Added `isUserInterruptAbort` and `shouldRenderAbortReason` helpers so interrupt handling can distinguish Esc-based aborts from other abort reasons.
- Updated assistant transcript rendering to suppress the `Interrupted by user` line while continuing to show generic or other abort labels.
- Updated plan-review and transcript container tests to assert interrupted assistant messages no longer render the redundant interrupt line.
- Updated `convertToLlm` logic to emit `developer` role for custom, hook, and file-mention inputs.
- Simplified OpenAI compact output filtering to retain only `user` and `assistant` messages, removing legacy `system-reminder` pattern checks.
- Adjusted compaction and session tests to match the new developer-role mapping and expected compacted content.
- Removed `<turn-aborted>` guidance injection from `transformMessages`, deleted `turn-aborted-guidance.md`, and dropped the synthetic abort note path for aborted/error turns.
- Updated `c`/`.` continue shortcuts to submit `manual-continue.md` as a hidden synthetic `developer` message via `session.prompt(..., { synthetic: true })` instead of sending an empty user turn.
- Updated tests and changelog notes in AI and coding-agent to reflect the revised abort-context and continue behavior.
- Cached setting path segments and memoized `Settings.get()` results, clearing caches on updates.
- Triggered session-name and session-accent callbacks only when effective values changed, with error-safe dispatch.
- Memoized status-line and interactive accent resolution with cache invalidation on settings/theme/session changes.
- Added regression tests for keybinding precedence, status-line, settings, and accent cache behavior.
- Added first-party-first provider priority defaults for model ranking.
- Consolidated model resolution to use getModelMatchPreferences from session settings.
- Prioritized providerPriorityRank ahead of usage rank when picking preferred models.
- Added second-pass fallback to default-model or API-key-valid matching order.
- Added `getCredentialOrigin` and `getEnvApiKeyName` to classify auth source.
- Surfaced provenance tags in the `/login` and `/logout` provider picker.
- Made the picker search filter match credential origin and env var name.
- Added coverage for credential-origin precedence and env naming.
When a session's working directory is moved or renamed (e.g. `git worktree
move`), the session file stays under the old cwd-encoded bucket while the new
directory is empty. Resuming was lossy:
- `--continue` rejected the terminal breadcrumb purely on cwd mismatch and then
found nothing in the new bucket, silently starting a fresh empty session.
- cross-project `--resume <id>` only offered to *fork* (duplicate) the session
into the new directory, forcing manual id selection and leaving a stale copy.
Detect relocation via the strong, low-false-positive signal "recorded cwd no
longer exists on disk" and re-root in place with the existing `moveTo()`:
- `continueRecent` re-roots the terminal's last session into the current
directory when its recorded cwd is gone and the new location has no sessions
of its own (otherwise behavior is unchanged). `readTerminalBreadcrumb` is
refactored into `readTerminalBreadcrumbEntry` returning the raw cwd +
session file so callers can interpret a cwd mismatch.
- cross-project `--resume <id>` offers "Move (re-root)" instead of fork when the
source directory is gone; a still-existing different project still forks.
Tests: continue-relocation (re-root on move, no-hijack on plain cd, prefer
local recent) and cross-project move-vs-fork routing.
- Updated task call and result rendering to process shared context with the Markdown renderer, so context sections are now displayed with proper Markdown formatting.
- Stopped shimmer animation on pending bash/eval/task blocks once async state is `running`, preventing the committed frame from freezing a transient dark border segment.
- Adjusted rule path display to fall back to a root-relative path when cwd-relative resolution is unavailable.
- Updated InputController streaming submit handling to interrupt and resume when queued steering exists, refreshing the pending-message UI and render.
- Added AgentSession.interruptAndFlushQueuedMessages to abort active work and continue processing queued messages immediately.
- Added tests for queued steering interruption in both agent-session concurrency and input-controller keybinding flows.
- Passed a formatted TTSR match message into the agent abort call when streaming is interrupted by TTSR rules.
- Added a `#formatTtsrAbortReason` helper to include matched rule names in the abort reason.
- Added a concurrent-session test confirming aborted tool results mention the matched TTSR rule instead of `Request was aborted`.
- Added `/tan` slash command registration and interactive handling.
- Added TanCommandController validation and async task scheduling for `/tan` dispatch.
- Added session cloning that suppresses breadcrumbs, copies artifacts, and handles abort cleanup.
- Added `promptCacheKey` support in Agent and inherited `providerPromptCacheKey` in session creation.
- Added optional `reason` parameters to `Agent.abort` and `AgentSession.abort` APIs.
- Passed abort reasons through interrupt flows into underlying agent cancellation.
- Replaced hard-coded abort text with `resolveAbortLabel` for streaming and replayed messages.
- Fell back to generic `Request was aborted` text when no abort reason was provided.
- Added `AgentSession.freshSession()` to rotate provider-facing IDs and prune provider stream state.
- Added `/fresh` command handling in the builtin registry and mode command flow.
- Kept persisted session metadata intact during `/fresh` and cleared transient IDs on session switches.
- Invalidated `appendOnlyContext` and provider caches when refreshing provider state.
- Lazy-loaded OTEL SDK, HTML export, TTSR, and autoresearch modules.
- Made resolveMemoryBackend async to import backends on demand.
- Replaced backend resolution with direct settings reads for rekey checks.
- Made "auto" the default, hiding MCP tools past 40-tool threshold.
- Centralized discovery mode resolution in shared mode helper.
- Activated search tool in createAgentSession once full registry exists.
- Added image-reference rendering to make `[Image #N]` placeholders clickable in chat.
- Added MIME-aware image blob materialization with extensioned sidecar paths.
- Added clickable path, line, and URL hyperlinks for read, search, and fetch outputs.
- Hardened OSC8 hyperlink emission with URI validation and control-byte/idempotency checks.
When Anthropic Claude returns stopReason: "toolUse" but the assistant
message contains no actual toolCall, the session would append a spurious
toolResult entry. This creates tool_result blocks without matching
tool_use blocks — structurally invalid for Anthropic's API validator.
The symptom is overloaded_error on every subsequent request (in: 0 out: 0),
even though servers aren't overloaded. Other providers handle the same
corrupted history more leniently, making the problem appear Anthropic-specific.
The #isEmptyAssistantStop guard now checks for stopReason === "toolUse"
with no text and no toolCall. When the retry cap is hit, tool-use orphans
are still removed from active context (unlike regular empty stops) because
they corrupt message history. A regression test covers both the retry and
cap scenarios.
For affected sessions: run /compact to drop the corrupted history tail.
Fixes review feedback from chatgpt-codex-connector.
Add retry.modelFallback so users can keep automatic retry enabled while preventing retry recovery from switching through configured fallback model chains.
The default remains enabled, preserving existing fallback behavior. When disabled, retry still honors retry-after delays and retry limits while staying on the primary model.
Op: correct
Restores: spec:retry can stay enabled without automatic model switching
AgentSession now stores the same scoped AsyncJobManager reference that tools receive: owning top-level sessions use their constructed manager, subagents inherit the parent's manager, and secondary in-process top-level sessions get no manager when a singleton is already live.
getAsyncJobSnapshot and ACP delivery drains now use that scoped manager instead of AsyncJobManager.instance(), so secondary sessions cannot report or drain the primary session's background jobs. The regression test covers a secondary session created while the primary has a Main-owned running job.
- Added AES-GCM cache for at-rest broker snapshots keyed on token, with URL as additional data.
- Added `onSnapshot` hook to RemoteAuthCredentialStore for persisting applied snapshots.
- Exposed cache read/write and TTL defaults through the coding-agent re-exports.
- Added `getAuthBrokerSnapshotCachePath` with `OMP_AUTH_BROKER_SNAPSHOT_CACHE` override.
Any in-process secondary createAgentSession() (e.g. the Agent Control Center's create flow in agent-dashboard.ts) was constructing its own AsyncJobManager, overwriting the process-global singleton, and then clearing it on its own dispose. The primary session still held its #ownedAsyncJobManager reference, but AsyncJobManager.instance() was undefined for the rest of the process — the task async path hard-failed with "Async execution is enabled but no async job manager is available" and only a full restart cleared it.
- sdk.ts: skip constructing/installing a second AsyncJobManager when a singleton is already live, so secondary top-level sessions share the owning session's manager instead of clobbering it.\n- agent-session.ts: scope #cancelOwnAsyncJobs so a secondary session inheriting the singleton with the default MAIN_AGENT_ID can no longer cancel the primary session's running bash/task jobs at dispose time. Subagents still reach the inherited singleton via their unique agent ids; the owning session still cancels its own jobs through #ownedAsyncJobManager.
Fixes#1923
- Stopped leaking absolute home directory to the model in ttsr-interrupt and ttsr-tool-reminder blocks.
- Rendered rule paths as cwd-relative in-project, `~`-relative under home, else raw.
Mid-session edits to hindsight.bankId / bankIdPrefix / scoping kept the
active HindsightSessionState pinned to the bank selected at session
start, so retain/recall/reflect calls landed in the stale bank. Settings
hooks now fire onHindsightScopeChanged; the backend rebuilds the
primary state against the recomputed scope, disposing the previous one
after flushing its queue so queued tool-initiated retains still land in
the bank they were enqueued for.
Also:
- Renamed ensureBankMission to ensureBankExists. The old version
skipped creation entirely when bankMission was blank, so the first
mental-model POST (auto-seed) could land against a never-PUT bank.
Bank creation is now idempotent and unconditional, and runs before
mental-model bootstrap.
- Fixed AgentSession.dispose to flush the retain queue BEFORE clearing
the session state pointer. Reversed, HindsightRetainQueue.#doFlush's
identity guard would see the cleared pointer and drop the spliced
batch with a 'session vanished' warning.
- Snapshotted hindsightScopeCallbacks before iterating because each
rebuild subscribes a fresh callback inside the same fire; iterating
the live Set would spin.
Fixes#1902
- Marked steering user messages and wrapped them pre-LLM so the model sees a `` envelope.
- Kept transcripts and persisted history with the user's original raw text.
- Restored `AssistantMessageComponent` stable-prefix completion API.
- Registered and triggered a session-switch reconciler during init and after switch.
- Rebuilt resume flow to restore plan/goal mode state and clear stale mode flags.
- Marked fallback and context-promotion model switches ephemeral and skipped them on restore.
- Added regression tests for temporary model ordering, fallback precedence, and mode cleanup.
- Removed early FTS-only return so prefix and substring matches merge.
- Sorted merged results globally by prompt recency before limiting.
- Added /force, /copy, and /shake tips.
Centralized append-only context auto-mode resolution so SDK sessions, interactive sessions, and the status display use the same provider checks. Auto mode now enables for Xiaomi/SGLang hosts and explicit stored-request compat signals while preserving DeepSeek behavior.
Added focused regression coverage for Xiaomi Token Plan SGLang HiCache endpoints and explicit on/off behavior.
Fixes#1851
- Added `isReadOnlyAgent` and `READ_ONLY_TOOL_NAMES` to classify agents.
- Marked read-only agents and forbade edits, commands, and reasoning offload.
- Added tests for capability classification and description rendering.
- Renamed `TodoWriteTool` to `TodoTool` and its source/prompt files.
- Updated tool registration, schema, renderers, and gating to `todo`.
- Adjusted cursor provider native tool names and tests to match.
- Renamed strike-animation constants and `todo-error-reminder` type.
- Added `IndexedSessionStorage` with `SessionStorageBackend` for index-based storage reads.
- Removed `readTextSync` from the public `SessionStorage` API and sync backends.
- Changed Redis and SQL backends to warm `{size, mtimeMs}` metadata and read via `readTextSlices`.
- Added per-path write queues and `drain()` to serialize operations and surface first failures.
- Classified each session's final message as done, interrupted, aborted, error, or pending from a 32 KiB tail read.
- Rendered the status as a colored segment on the session metadata line.
- Added `peekFileTail` and `readTextSuffix` across storage backends to read file tails in one pass.
- Simplified `MemorySessionStorage` to a string array mirror with a sidecar mtime map.
- Added shared `getReadToolPath` API to extract paired read `path` values for protection matchers.
- Added `createPlanReadMatcher` and session wiring so compaction prune/shake keeps active plan reads intact.
- Updated `todo-write` instructions to initialize every user-supplied plan item as an individual task.
- Added compaction tests validating plan reads are protected from prune and shake while regular reads are still removable.
can1357