* feat(cli): unify notification queue for cron and background agents
Migrate cron from its own queue (cronQueueRef / cronQueue) to the shared
notification queue used by background agents. Both producers now push the
same item shape { displayText, modelText, sendMessageType } and a single
drain effect / helper processes them in FIFO order.
Cron fires render as HistoryItemNotification (● prefix) instead of
HistoryItemUser (> prefix), with a "Cron: <prompt>" display label.
Records use subtype 'cron' for clean resume and analytics separation.
Lift the non-interactive rejection for background agents. Register a
notification callback in nonInteractiveCli.ts with a terminal hold-back
phase (100ms poll) that keeps the process alive until all background
agents complete and their notifications are processed.
* feat(cli): emit SDK task events for background subagents
Emit `task_started` when a background agent registers and
`task_notification` when it completes, fails, or is cancelled, so
headless/SDK consumers can track lifecycle without parsing display
text. Model-facing text is now structured XML with status, summary,
truncated result, and usage stats. Completion stats (tokens, tool
uses, duration) are captured from the subagent and included in both
the SDK payload and the model XML.
* fix: address codex review issues for background subagents
- Background subagents now inherit the resolved approval mode from
agentConfig instead of the raw session config, so a subagent with
`approvalMode: auto-edit` (or execution in a trusted folder) keeps
that override when it runs asynchronously.
- Non-interactive cron drains are single-flight: concurrent cron fires
now await the same in-flight drain, and the cron-done check gates
on it, preventing the final result from being emitted while a cron
turn is still streaming.
- Background forks go through createForkSubagent so they retain the
parent's rendered system prompt and inherited history instead of
degrading to a plain FORK_AGENT.
* fix(cli): restore cancellation, approval, and error paths in queued drain
- Hold-back loop now reacts to SIGINT/SIGTERM: when the main abort
signal fires it calls registry.abortAll() so background agents with
their own AbortControllers stop promptly instead of pinning the
process open.
- Queued-turn tool execution forwards the stream-json approval update
callback (onToolCallsUpdate) so permission-gated tools inside a
background-notification follow-up emit can_use_tool requests.
- Queued-turn stream loop mirrors the main loop's text-mode handling
of GeminiEventType.Error, writing to stderr and throwing so provider
errors produce a non-zero exit code instead of silently succeeding.
- Interactive cron prompts go through the normal slash/@-command/shell
preprocessing again; only Notification messages skip that path.
* fix(cli): skip duplicate user-message item for cron prompts
Cron prompts already render as a `● Cron: …` notification via the queue
drain, so adding them again as a `USER` history item produced a
duplicate `> …` line.
* fix(cli): honor SIGINT/SIGTERM during cron scheduler wait
The non-interactive cron phase awaits a Promise that resolves only when
scheduler.size reaches 0 and no drain is in flight. Recurring cron jobs
never drop the scheduler size to 0 on their own, so the previous abort
handling (added to the hold-back loop) was unreachable — the process
hung indefinitely after SIGINT/SIGTERM. Attach an abort listener inside
the promise so abort stops the scheduler and resolves immediately,
allowing the hold-back loop to run and the process to exit cleanly.
* feat(core): propagate tool-use id through background agent notifications
Plumb the scheduler's callId into AgentToolInvocation via an optional
setCallId hook on the invocation, detected structurally in
buildInvocation. The agent tool forwards it as toolUseId on the
BackgroundTaskRegistry entry so completion notifications can carry a
<tool-use-id> tag and SDK task_started / task_notification events can
emit tool_use_id — letting consumers correlate background completions
back to the original Agent tool-use that spawned them.
* fix(cli): drain single-flight race kept task_notification from emitting
drainLocalQueue wrapped its body in an async IIFE and cleared the
promise reference via finally. When the queue is empty the IIFE has
no awaits, so its finally runs synchronously as part of the RHS of
the assignment `drainPromise = (async () => {...})()` — clearing
drainPromise BEFORE the outer assignment overwrites it with the
resolved promise. The reference then stayed stuck on that fulfilled
promise forever, so later calls short-circuited through
`if (drainPromise) return drainPromise` and never processed
queued notifications.
Symptom: in headless `--output-format json` (and `stream-json`),
task_started emitted but task_notification never did, even after
the background agent completed. The process sat in the hold-back
loop until SIGTERM.
Fix: move the null-clearing out of the async body into an outer
`.finally()` on the returned promise. `.finally()` runs as a
microtask after the current synchronous block, so it clears the
latest drainPromise reference instead of the pre-assignment null.
* fix(cli): append newline to text-mode emitResult so zsh PROMPT_SP doesn't erase the line
Headless text mode wrote `resultMessage.result` without a trailing newline.
In a TTY, zsh themes that use PROMPT_SP (powerlevel10k, agnoster, …) detect
the missing `\n` and emit `\r\033[K` before drawing the next prompt, which
wipes the final line off the screen. Pipe-captured output was unaffected,
so the bug only surfaced for interactive shell users — most visibly in the
background-agent flow where the drain-loop's final assistant message is
the *only* stdout write in text mode.
Append `\n` to both the success (stdout) and error (stderr) writes.
* docs(skill): tighten worked-example blurb in structured-debugging
Mirror the simplified blurb from .claude/skills/structured-debugging/SKILL.md
(knowledge repo). Drops the round-by-round narrative; keeps the contradiction
+ two lessons.
* docs(skill): mirror SKILL.md improvements (reframing failure mode, generalized path, value-logging guidance)
Mirror of knowledge repo commit 38eb28d into the qwen-code .qwen/skills
copy.
* docs(skill): mirror worked example into .qwen/skills/structured-debugging/
Mirrors knowledge/.claude/skills/structured-debugging/examples/
headless-bg-agent-empty-stdout.md so the .qwen copy of the skill links
resolve.
* docs(skill): mirror generalized side-note path guidance
* fix(cli): harden headless cron and background-agent failure paths
Three regressions surfaced by Codex review of feat/background-subagent:
- Cron drain rejections were dropped by a bare `void`, so a failing
queued turn left the outer Promise unresolved and hung the run. Route
drain failures through the Promise's reject so they propagate to the
outer catch.
- The background-agent registry entry was inserted before
`createForkSubagent()` / `createAgentHeadless()` was awaited. Failed
init returned an error from the tool call but left a phantom `running`
entry, and the headless hold-back loop (`registry.getRunning()`) waited
forever. Register only after init succeeds.
- SIGINT/SIGTERM during the hold-back phase aborted background tasks,
then fell through to `emitResult({ isError: false })`, so a cancelled
`qwen -p ...` exited 0 with the prior assistant text. Route through
`handleCancellationError()` so cancellation exits non-zero, matching
the main turn loop.
* test(cli): update stdout/stderr assertions for trailing newline
`feadf052f` appended `\n` to text-mode `emitResult` output, but the
nonInteractiveCli tests still asserted the pre-change strings. Update
the 11 affected assertions to expect the trailing newline.
* fix: address review comments on background-agent notifications
Four additional issues from the PR review that the prior regression-fix
commit didn't cover:
- Escape XML metacharacters when interpolating `description`, `result`,
`error`, `agentId`, `toolUseId`, and `status` into the task-notification
envelope. Subagent output (which itself may carry untrusted tool output,
fetched HTML, or another agent's notification) could contain
`</result>` or `</task-notification>` and forge sibling tags the parent
model would treat as trusted metadata. Truncate result text *before*
escaping so the truncation never slices through an entity like `&`.
- Emit the terminal notification from `cancel()` and `abortAll()`. The
fire-and-forget `complete()`/`fail()` from the subagent task is guarded
by `status !== 'running'` and was no-op'd after cancellation, so SDK
consumers saw `task_started` with no matching `task_notification`,
breaking the contract this PR establishes. Updated two race-guard
tests that asserted the old behavior.
- Call `adapter.finalizeAssistantMessage()` before the abort-triggered
early return inside `drainOneItem`'s stream loop. Without it,
`startAssistantMessage()` had already been called, so stream-json mode
left `message_start` unpaired.
- Enforce `config.getMaxSessionTurns()` in `drainOneItem` for symmetry
with the main turn loop. Cron fires and notification replies otherwise
bypass the budget cap in headless runs.
- Inherit bgConfig from agentConfig so the resolved approval mode is
preserved for background agents (foreground would run AUTO_EDIT but
background fell back to DEFAULT, which combined with shouldAvoid-
PermissionPrompts would auto-deny every permission request).
- Honor SubagentStop blocking decisions in background runs by looping
on hook output up to 5 iterations, matching runSubagentWithHooks.
- Check terminate mode before reporting completion; non-GOAL modes
(ERROR, MAX_TURNS, TIMEOUT) are now reported as failures instead of
emitting a success notification for an incomplete run.
- Exclude SendMessageType.Notification from the UserPromptSubmit hook
guard so background completion messages are not rewritten or blocked
as if they were user input.
Subagent definitions can now declare `background: true` in their YAML
frontmatter to always run as background tasks. This is OR'd with the
`run_in_background` tool parameter — useful for monitors, watchers, and
proactive agents so the LLM doesn't need to remember to set the flag.
Resolve conflict in agent.ts: adopt #3255's runSubagentWithHooks
method and fork dispatch, add background execution path before the
fork/normal dispatch with its own hook firing and fire-and-forget
pattern.
Resolve conflicts in client.ts (keep both notificationDisplayText and
modelOverride fields), useGeminiStream.ts (combine both options), and
agent.ts (integrate background subagent feature with fork subagent
refactor and resolvedMode improvements).
* test(core): stabilize glob truncation tests
Mock glob results in truncation-specific tests instead of creating large
numbers of real files. This keeps the tests focused on GlobTool boundary
logic and avoids filesystem timing issues on Windows CI.
* test(cli): stabilize selection list scroll test
Wait for the newly active item to render after rerendering the list so the
scroll assertions do not read a stale frame on slower Windows CI runs.
When a background auto-update finished while the model was streaming,
the success/failure notification was inserted mid-conversation via
addItem(), disrupting the user's reading flow.
Introduce a "defer until idle" mechanism in setUpdateHandler():
- Accept an `isIdleRef` param that tracks whether StreamingState is Idle
- Queue notifications in a `pendingNotifications` array when not idle
- Expose a `flush()` method that drains the queue once idle
- AppContainer keeps `isIdleRef.current` in sync with `streamingState`
and calls `flush()` via a useEffect when transitioning back to Idle
All four event types (update-received, update-success, update-failed,
update-info) are routed through the same addItemOrDefer() helper.
The third parameter defaults to `{ current: true }` for backward
compatibility.
Co-authored-by: 思晗 <housihan.hsh@alibaba-inc.com>
* docs: add auto-memory implementation log
* feat(core): add managed auto-memory storage scaffold
* feat(core): load managed auto-memory index
* feat(core): add managed auto-memory recall
* feat(core): add managed auto-memory extraction
* feat(cli): add managed auto-memory dream commands
* feat(core): add auxiliary side-query foundation
* feat(memory): add model-driven recall selection
* feat(memory): add model-driven extraction planner
* feat(core): add background task runtime foundation
* feat(memory): schedule auto dream in background
* feat(core): add background agent runner foundation
* feat(memory): add extraction agent planner
* feat(core): add dream agent planner
* feat(core): rebuild managed memory index
* feat(memory): add governance status commands
* feat(memory): add managed forget flow
* feat(core): harden background agent planning
* feat(memory): complete managed parity closure
* test(memory): add managed lifecycle integration coverage
* feat: same to cc
* feat(memory-ui): add memory saved notification and memory count badge
Feature 3 - Memory Saved Notification:
- Add HistoryItemMemorySaved type to types.ts
- Create MemorySavedMessage component for rendering '● Saved/Updated N memories'
- In useGeminiStream: detect in-turn memory writes via mapToDisplay's
memoryWriteCount field and emit 'memory_saved' history item after turn
- In client.ts: capture background dream/extract promises and expose
via consumePendingMemoryTaskPromises(); useGeminiStream listens
post-turn and emits 'Updated N memories' notification for background tasks
Feature 4 - Memory Count Badge:
- Add isMemoryOp field to IndividualToolCallDisplay
- Add memoryWriteCount/memoryReadCount to HistoryItemToolGroup
- Add detectMemoryOp() in useReactToolScheduler using isAutoMemPath
- ToolGroupMessage renders '● Recalled N memories, Wrote N memories' badge
at the top of tool groups that touch memory files
Fix: process.env bracket-access in paths.ts (noPropertyAccessFromIndexSignature)
Fix: MemoryDialog.test.tsx mock useSettings to satisfy SettingsProvider requirement
* fix(memory-ui): auto-approve memory writes, collapse memory tool groups, fix MEMORY.md path
Problem 1 - Auto-approve memory file operations:
- write-file.ts: getDefaultPermission() checks isAutoMemPath; returns 'allow'
for managed auto-memory files, 'ask' for all other files
- edit.ts: same pattern
Problem 2 - Feature 4 UX: collapse memory-only tool groups:
- ToolGroupMessage: detect when all tool calls have isMemoryOp set (pure memory
group) and all are complete; render compact '● Recalled/Wrote N memories
(ctrl+o to expand)' instead of individual tool call rows
- ctrl+o toggles expand/collapse when isFocused and group is memory-only
- Mixed groups (memory + other tools) keep badge-at-top behaviour
- Expanded state shows individual tool calls with '● Memory operations
(ctrl+o to collapse)' header
Problem 3 - MEMORY.md path mismatch:
- prompt.ts: Step 2 now references full absolute path ${memoryDir}/MEMORY.md
so the model writes to the correct location inside the memory directory,
not to the parent project directory
Fix tests:
- write-file.test.ts: add getProjectRoot to mockConfigInternal
- prompt.test.ts: update assertion to match full-path section header
* fix(memory-ui): fix duplicate notification, broken ctrl+o, and Edit tool detection
- Remove duplicate 'Saved N memories' notification: the tool group badge already
shows 'Wrote N memories'; the separate HistoryItemMemorySaved addItem after
onComplete was double-counting. Keep only the background-task path
(consumePendingMemoryTaskPromises).
- Remove ctrl+o expand: Ink's Static area freezes items on first render and
cannot respond to user input. useInput/useState(isExpanded) in a Static item
is a no-op. Removed the dead code; memory-only groups now always render as
the compact summary (no fake interactive hint).
- Fix Edit tool detection: detectMemoryOp was checking for 'edit_file' but the
real tool name constant is 'edit'. Also removed non-existent 'create_file'
(write_file covers all writes). Now editing MEMORY.md is correctly identified
as a memory write op, collapses to 'Wrote N memories', and is auto-approved.
* fix(dream): run /dream as a visible submit_prompt turn, not a silent background agent
The previous implementation ran an AgentHeadless background agent that could
take 5+ minutes with zero UI feedback — user saw a blank screen for the entire
duration and then at most one line of text.
Fix: /dream now returns submit_prompt with the consolidation task prompt so it
runs as a regular AI conversation turn. Tool calls (read_file, write_file, edit,
grep_search, list_directory, glob) are immediately visible as collapsed tool
groups as the model works through the memory files — identical UX to Claude Code.
Also export buildConsolidationTaskPrompt from dreamAgentPlanner so dreamCommand
can reuse the same detailed consolidation prompt that was already written.
* fix(memory): auto-allow ls/glob/grep on memory base directory
Add getMemoryBaseDir() to getDefaultPermission() allow list in ls.ts,
glob.ts, and grep.ts — mirrors the existing pattern in read-file.ts.
Without this, ListFiles/Glob/Grep on ~/.qwen/* would trigger an
approval dialog, blocking /dream at its very first step.
* fix(background): prevent permission prompt hangs in background agents
Match Claude Code's headless-agent intent: background memory agents must never
block on interactive permission prompts.
Wrap background runtime config so getApprovalMode() returns YOLO, ensuring any
ask decision is auto-approved instead of hanging forever. Add regression test
covering the wrapped approval mode.
* fix(memory): run auto extract through forked agent
Make managed auto-memory extraction follow the Claude Code architecture:
background extraction now uses a forked agent to read/write memory files
directly, instead of planning patches and applying them with a separate
filesystem pipeline.
Keep the old patch/model path only as fallback if the forked agent fails.
Add regression tests covering the new execution path and tool whitelist.
* refactor(memory): remove legacy extract fallback pipeline
Delete the old patch/model/heuristic extraction path entirely.
Managed auto-memory extract now runs only through the forked-agent
execution flow, with no planner/apply fallback stages remaining.
Also remove obsolete exports/tests and update scheduler/integration
coverage to use the forked-agent-only architecture.
* refactor(memory): move auxiliary files out of memory/ directory
meta.json, extract-cursor.json, and consolidation.lock are internal
bookkeeping files, not user-visible memories. Move them one level up
to the project state dir (parent of memory/) so that the memory/
directory contains only MEMORY.md and topic files, matching the
clean layout of the upstream reference implementation.
Add getAutoMemoryProjectStateDir() helper in paths.ts and update the
three path accessors + store.test.ts path assertions accordingly.
* fix(memory): record lastDreamAt after manual /dream run
The /dream command submits a prompt to the main agent (submit_prompt),
which writes memory files directly. Because it bypasses dreamScheduler,
meta.json was never updated and /memory always showed 'never'.
Fix by:
- Exporting writeDreamManualRunToMetadata() from dream.ts
- Adding optional onComplete callback to SubmitPromptActionReturn and
SubmitPromptResult (types.ts / commands/types.ts)
- Propagating onComplete through slashCommandProcessor.ts
- Firing onComplete after turn completion in useGeminiStream.ts
- Providing the callback in dreamCommand.ts to write lastDreamAt
* fix(memory): remove scope params from /remember in managed auto-memory mode
--global/--project are legacy save_memory tool concepts. In managed
auto-memory mode the forked agent decides the appropriate type
(user/feedback/project/reference) based on the content of the fact.
Also improve the prompt wording to explicitly ask the agent to choose
the correct type, reducing the tendency to default to 'project'.
* feat(ui): show '✦ dreaming' indicator in footer during background dream
Subscribe to getManagedAutoMemoryDreamTaskRegistry() in Footer via a
useDreamRunning() hook. While any dream task for the current project is
pending or running, display '✦ dreaming' in the right section of the
footer bar, between Debug Mode and context usage.
* refactor(memory): align dream/extract infrastructure with Claude Code patterns
Five improvements based on Claude Code parity audit:
1. Memoize getAutoMemoryRoot (paths.ts)
- Add _autoMemoryRootCache Map, keyed by projectRoot
- findCanonicalGitRoot() walks the filesystem per call; memoize avoids
repeated git-tree traversal on hot-path schedulers/scanners
- Expose clearAutoMemoryRootCache() for test teardown
2. Lock file stores PID + isProcessRunning reclaim (dreamScheduler.ts)
- acquireDreamLock() writes process.pid to the lock file body
- lockExists() reads PID and calls process.kill(pid, 0); dead/missing
PID reclaims the lock immediately instead of waiting 2h
- Stale threshold reduced to 1h (PID-reuse guard, same as CC)
3. Session scan throttle (dreamScheduler.ts)
- Add SESSION_SCAN_INTERVAL_MS = 10min (same as CC)
- Add lastSessionScanAt Map<projectRoot, number> to ManagedAutoMemoryDreamRuntime
- When time-gate passes but session-gate doesn't, throttle prevents
re-scanning the filesystem on every user turn
4. mtime-based session counting (dreamScheduler.ts)
- Replace fragile recentSessionIdsSinceDream Set in meta.json with
filesystem mtime scan (listSessionsTouchedSince)
- Mirrors Claude Code's listSessionsTouchedSince: reads session JSONL
files from Storage.getProjectDir()/chats/, filters by mtime > lastDreamAt
- Immune to meta.json corruption/loss; no per-turn metadata write
- ManagedAutoMemoryDreamRuntime accepts injectable SessionScannerFn
for clean unit testing without real session files
5. Extraction mutual exclusion extended to write_file/edit (extractScheduler.ts)
- historySliceUsesMemoryTool() now checks write_file/edit/replace/create_file
tool calls whose file_path is within isAutoMemPath()
- Previously only detected save_memory; missed direct file writes by
the main agent, causing redundant background extraction
* docs(memory): add user-facing memory docs, i18n for all locales, simplify /forget
- Add docs/users/features/memory.md: comprehensive user-facing guide covering
QWEN.md instructions, auto-memory behaviour, all memory commands, and
troubleshooting; replaces the placeholder auto-memory.md
- Update docs/users/features/_meta.ts: rename entry auto-memory → memory
- Update docs/users/features/commands.md: add /init, /remember, /forget,
/dream rows; fix /memory description; remove /init duplicate
- Update docs/users/configuration/settings.md: add memory.* settings section
(enableManagedAutoMemory, enableManagedAutoDream) between tools and permissions
- Remove /forget --apply flag: preview-then-apply flow replaced with direct
deletion; update forgetCommand.ts, en.js, zh.js accordingly
- Add all auto-memory i18n keys to de, ja, pt, ru locales (18 keys each):
Open auto-memory folder, Auto-memory/Auto-dream status lines, never/on/off,
✦ dreaming, /forget and /remember usage strings, all managed-memory messages
- Remove dead save_memory branch from extractScheduler.partWritesToMemory()
- Add ✦ dreaming indicator to Footer.tsx with i18n; fix Footer.test.tsx mocks
- Refactor MemoryDialog.tsx auto-dream status line to use i18n
- Remove save_memory tool (memoryTool.ts/test); clean up webui references
- Add extractionPlanner.ts, const.ts and associated tests
- Delete stale docs/users/configuration/memory.md and
docs/developers/tools/memory.md (content superseded)
* refactor(memory): remove all Claude Code references from comments and test names
* test(memory): remove empty placeholder test files that cause vitest to fail
* fix eslint
* fix test in windows
* fix test
* fix(memory): address critical review findings from PR #3087
- fix(read-file): narrow auto-allow from getMemoryBaseDir() (~/.qwen) to
isAutoMemPath(projectRoot) to prevent exposing settings.json / OAuth
credentials without user approval (wenshao review)
- fix(forget): per-entry deletion instead of whole-file unlink
- assign stable per-entry IDs (relativePath:index for multi-entry files)
so the model can target individual entries without removing siblings
- rewrite file keeping unmatched entries; only unlink when file becomes
empty (wenshao review)
- fix(entries): round-trip correctness for multi-entry new-format bodies
- parseAutoMemoryEntries: plain-text line closes current entry and opens
a new one (was silently ignored when current was already set)
- renderAutoMemoryBody: emit blank line between adjacent entries so the
parser can detect entry boundaries on re-read (wenshao review)
- fix(entries): resolve two CodeQL polynomial-regex alerts
- indentedMatch: \s{2,}(?:[-*]\s+)? → [\t ]{2,}(?:[-*][\t ]+)?
- topLevelMatch: :\s*(.+)$ → :[ \t]*(\S.*)$
(github-advanced-security review)
- fix(scan.test): use forward-slash literal for relativePath expectation
since listMarkdownFiles() normalises all separators to '/' on all
platforms including Windows
* fix(memory): replace isAutoMemPath startsWith with path.relative()
Using path.relative() instead of string startsWith() is more robust
across platforms — it correctly handles Windows path-separator
differences and avoids potential edge cases where a path prefix match
could succeed on non-separator boundaries.
Addresses github-actions review item 3 (PR #3087).
* feat(telemetry): add auto-memory telemetry instrumentation
Add OpenTelemetry logs + metrics for the five auto-memory lifecycle
events: extract, dream, recall, forget, and remember.
Telemetry layer (packages/core/src/telemetry/):
- constants.ts: 5 new event-name constants
(qwen-code.memory.{extract,dream,recall,forget,remember})
- types.ts: 5 new event classes with typed constructor params
(MemoryExtractEvent, MemoryDreamEvent, MemoryRecallEvent,
MemoryForgetEvent, MemoryRememberEvent)
- metrics.ts: 8 new OTel instruments (5 Counters + 3 Histograms)
with recordMemoryXxx() helpers; registered inside initializeMetrics()
- loggers.ts: logMemoryExtract/Dream/Recall/Forget/Remember() — each
emits a structured log record and calls its recordXxx() counterpart
- index.ts: re-exports all new symbols
Instrumentation call-sites:
- extractScheduler.ts ManagedAutoMemoryExtractRuntime.runTask():
emits extract event with trigger=auto, completed/failed status,
patches_count, touched_topics, and wall-clock duration
- dream.ts runManagedAutoMemoryDream():
emits dream event with trigger=auto, updated/noop status,
deduped_entries, touched_topics, and duration; covers both
agent-planner and mechanical fallback paths
- recall.ts resolveRelevantAutoMemoryPromptForQuery():
emits recall event with strategy, docs_scanned/selected, and
duration; covers model, heuristic, and none paths
- forget.ts forgetManagedAutoMemoryEntries():
emits forget event with removed_entries_count, touched_topics,
and selection_strategy (model/heuristic/none)
- rememberCommand.ts action():
emits remember event with topic=managed|legacy at command
invocation time (before agent decides the actual memory type)
* refactor(telemetry): remove memory forget/remember telemetry events
Remove EVENT_MEMORY_FORGET and EVENT_MEMORY_REMEMBER along with all
associated infrastructure that is no longer needed:
- constants.ts: remove EVENT_MEMORY_FORGET, EVENT_MEMORY_REMEMBER
- types.ts: remove MemoryForgetEvent, MemoryRememberEvent classes
- metrics.ts: remove MEMORY_FORGET_COUNT, MEMORY_REMEMBER_COUNT constants,
memoryForgetCounter, memoryRememberCounter module vars,
their initialization in initializeMetrics(), and
recordMemoryForgetMetrics(), recordMemoryRememberMetrics() functions
- loggers.ts: remove logMemoryForget(), logMemoryRemember() functions
and their imports
- index.ts: remove all re-exports for the above symbols
- memory/forget.ts: remove logMemoryForget call-site and import
- cli/rememberCommand.ts: remove logMemoryRemember call-sites and import
* change default value
* fix forked agent
* refactor(background): unify fork primitives into runForkedAgent + cleanup
- Merge runForkedQuery into runForkedAgent via TypeScript overloads:
with cacheSafeParams → GeminiChat single-turn path (ForkedQueryResult)
without cacheSafeParams → AgentHeadless multi-turn path (ForkedAgentResult)
- Delete forkedQuery.ts; move its test to background/forkedAgent.cache.test.ts
- Remove forkedQuery export from followup/index.ts
- Migrate all callers (suggestionGenerator, speculation, btwCommand, client)
to import from background/forkedAgent
- Add getFastModel() / setFastModel() to Config; expose in CLI config init
and ModelDialog / modelCommand
- Remove resolveFastModel() from AppContainer — now delegated to config.getFastModel()
- Strip Claude Code references from code comments
* fix(memory): address wenshao's critical review findings
- dream.ts: writeDreamManualRunToMetadata now persists lastDreamSessionId
and resets recentSessionIdsSinceDream, preventing auto-dream from firing
again in the same session after a manual /dream
- config.ts: gate managed auto-memory injection on getManagedAutoMemoryEnabled();
when disabled, previously saved memories are no longer injected into new sessions
- rememberCommand.ts: remove legacy save_memory branch (tool was removed);
fall back to submit_prompt directing agent to write to QWEN.md instead
- BuiltinCommandLoader.ts: only register /dream and /forget when managed
auto-memory is enabled, matching the feature's runtime availability
- forget.ts: return early in forgetManagedAutoMemoryMatches when matches is
empty, avoiding unnecessary directory scaffolding as a side effect
* fix test
* fix ci test
* feat(memory): align extract/dream agents to Claude Code patterns
- fix(client): move saveCacheSafeParams before early-return paths so
extract agents always have cache params available (fixes extract never
triggering in skipNextSpeakerCheck mode)
- feat(extract): add read-only shell tool + memory-scoped write
permissions; create inline createMemoryScopedAgentConfig() with
PermissionManager wrapper (isToolEnabled + evaluate) that allows only
read-only shell commands and write/edit within the auto-memory dir
- feat(extract): align prompt to Claude Code patterns — manifest block
listing existing files, parallel read-then-write strategy, two-step
save (memory file then index)
- feat(dream): remove mechanical fallback; runManagedAutoMemoryDream is
now agent-only and throws without config
- feat(dream): align prompt to Claude Code 4-phase structure
(Orient/Gather/Consolidate/Prune+Index); add narrow transcript grep,
relative→absolute date conversion, stale index pruning, index size cap
- fix(permissions): add isToolEnabled() to MemoryScopedPermissionManager
to prevent TypeError crash in CoreToolScheduler._schedule
- test: update dreamScheduler tests to mock dream.js; replace removed
mechanical-dedup test with scheduler infrastructure verification
* move doc to design
* refactor(memory): unify extract+dream background task management into MemoryBackgroundTaskHub
- Add memoryTaskHub.ts: single BackgroundTaskRegistry + BackgroundTaskDrainer shared
by all memory background tasks; exposes listExtractTasks() / listDreamTasks()
typed query helpers and a unified drain() method
- extractScheduler: ManagedAutoMemoryExtractRuntime accepts hub via constructor
(defaults to defaultMemoryTaskHub); test factory gets isolated fresh hub
- dreamScheduler: same pattern — sessionScanner + hub injection; BackgroundTask-
Scheduler initialized from injected hub; test factory gets isolated hub
- status.ts: replace two separate getRegistry() calls with defaultMemoryTaskHub
typed query methods
- Footer.tsx (useDreamRunning): subscribe to shared registry, filter by
DREAM_TASK_TYPE so extract tasks do not trigger the dream spinner
- index.ts: re-export memoryTaskHub.ts so defaultMemoryTaskHub/DREAM_TASK_TYPE/
EXTRACT_TASK_TYPE are available as top-level package exports
* refactor(background): introduce general-purpose BackgroundTaskHub
Replace memory-specific MemoryBackgroundTaskHub with a domain-agnostic
BackgroundTaskHub in the background/ layer. Any future background task
runtime (3rd, 4th, …) plugs in by accepting a hub via constructor
injection — no new infrastructure required.
Changes:
- Add background/taskHub.ts: BackgroundTaskHub (registry + drainer +
createScheduler() + listByType(taskType, projectRoot?)) and the
globalBackgroundTaskHub singleton. Zero knowledge of any task type.
- Delete memory/memoryTaskHub.ts: its narrow listExtractTasks /
listDreamTasks helpers are replaced by the generic listByType() call.
- Move EXTRACT_TASK_TYPE to extractScheduler.ts (owned by the runtime
that defines it); replace 3 hardcoded string literals with the const.
- Move DREAM_TASK_TYPE to dreamScheduler.ts; use hub.createScheduler()
instead of manually wiring new BackgroundTaskScheduler(reg, drain).
- status.ts: globalBackgroundTaskHub.listByType(EXTRACT_TASK_TYPE, ...)
- Footer.tsx: globalBackgroundTaskHub.registry (shared, filtered by type)
- index.ts: export background/taskHub.js; drop memory/memoryTaskHub.js
* test(background): add BackgroundTaskHub unit tests and hub isolation checks
- background/taskHub.test.ts (11 tests):
- createScheduler(): tasks registered via scheduler appear in hub registry;
multiple calls return distinct scheduler instances
- listByType(): filters by taskType, filters by projectRoot, returns []
for unknown types, two types co-exist in registry but stay separated
- drain(): resolves false on timeout, resolves true when tasks complete,
resolves true immediately when no tasks in flight
- isolation: tasks in hubA do not appear in hubB
- globalBackgroundTaskHub: is a BackgroundTaskHub instance with registry/drainer
- extractScheduler.test.ts (+1 test):
- factory-created runtimes have isolated registries; tasks in runtimeA
are invisible to runtimeB; all tasks carry EXTRACT_TASK_TYPE
- dreamScheduler.test.ts (+1 test):
- factory-created runtimes have isolated registries; tasks in runtimeA
are invisible to runtimeB; all tasks carry DREAM_TASK_TYPE
* refactor(memory): consolidate all memory state into MemoryManager
Replace BackgroundTaskRegistry/Drainer/Scheduler/Hub helper classes and
module-level globals with a single MemoryManager class owned by Config.
## Changes
### New
- packages/core/src/memory/manager.ts — MemoryManager with:
- scheduleExtract / scheduleDream (inline queuing + deduplication logic)
- recall / forget / selectForgetCandidates / forgetMatches
- getStatus / drain / appendToUserMemory
- subscribe(listener) compatible with useSyncExternalStore
- storeWith() atomic record registration (no double-notify)
- Distinct skippedReason 'scan_throttled' vs 'min_sessions' for dream
- packages/core/src/utils/forkedAgent.ts — pure cache util (moved from background/)
- packages/core/src/utils/sideQuery.ts — pure util (moved from auxiliary/)
### Deleted
- background/taskRegistry, taskDrainer, taskScheduler, taskHub and all tests
- background/forkedAgent (moved to utils/)
- auxiliary/sideQuery (moved to utils/)
- memory/extractScheduler, dreamScheduler, state and all tests
### Modified
- config/config.ts — Config owns MemoryManager instance; getMemoryManager()
- core/client.ts — all memory ops via config.getMemoryManager()
- core/client.test.ts — mock MemoryManager instead of individual modules
- memory/status.ts — accepts MemoryManager param, drops globalBackgroundTaskHub
- index.ts — memory exports reduced from 14 modules to 5 (manager/types/paths/store/const)
- cli/commands/dreamCommand.ts — via config.getMemoryManager()
- cli/commands/forgetCommand.ts — via config.getMemoryManager()
- cli/components/Footer.tsx — useSyncExternalStore replacing setInterval polling
- cli/components/Footer.test.tsx — add getMemoryManager mock
* fix(cli): remember "Start new chat session" until summary changes
Persist a project-scoped Welcome Back restart choice keyed to the
current PROJECT_SUMMARY fingerprint.
This suppresses the Welcome Back dialog after choosing "Start new chat
session", while still showing it again after the project summary is
updated.
* fix conflict
prepareTools() treated asStrings.length === 0 as "add all registry tools",
which is correct when no tools are specified at all, but wrong when the
caller provides only inline FunctionDeclaration[] (no string names). The
fork path passes parent tool declarations as inline decls for cache parity,
so prepareTools was adding the full registry set on top — duplicating every
non-excluded tool.
Add onlyInlineDecls.length === 0 to the condition so that pure-inline
toolConfigs bypass the registry entirely.
child_process.exec() throws synchronously for spawn errors libuv does not
report via the async 'error' event (EBADF, EINVAL, …). On macOS with Node
22, EBADF can surface during stdio pipe setup, and the uncaught throw
escapes the debounce setTimeout callback and crashes the CLI.
Wrap the exec call in try/catch so a failing statusline degrades to no
output while the rest of the CLI keeps running.
* fix(sdk): avoid leaking process exit listeners in ProcessTransport
* Strengthen ProcessTransport cleanup during process exit.
This updates the shared process-exit cleanup path to use a best-effort
SIGTERM/SIGKILL sequence and adds coverage to verify the global exit
handler terminates all active child processes.
It keeps the listener leak fix in place while closing the remaining gaps
found in review.
* add http/async/function type
* fix url error
* resolve comment
* align cc non blocking error
* fix hookRunner for async
* fix(hooks): update hook type validation to support http and function types
- Change validated hook types from ['command', 'plugin'] to ['command', 'http', 'function']
- Add validation for HTTP hooks requiring url field
- Add validation for function hooks requiring callback field
- Add comprehensive test coverage for all hook type validations
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* fix(hooks): align SSRF protection with Claude Code behavior
- Allow 127.0.0.0/8 (loopback) for local dev hooks
- Allow localhost hostname for local dev hooks
- Allow ::1 (IPv6 loopback) for local dev hooks
- Add 100.64.0.0/10 (CGNAT) to blocked ranges (RFC 6598)
- Update tests to match Claude Code's ssrfGuard.ts behavior
This fixes HTTP hooks failing to connect to local dev servers.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* refactor(hooks): align HTTP hook security with Claude Code behavior
- Add CRLF/NUL sanitization for env var interpolation (header injection)
- Implement combined abort signal (external signal + timeout)
- Upgrade SSRF protection to DNS-level with ssrfGuard
- Allow loopback (127.0.0.0/8, ::1) for local dev hooks
- Block CGNAT (100.64.0.0/10) and IPv6 private ranges
- Increase default HTTP hook timeout to 10 minutes
- Fix VS Code hooks schema to support http type
- Add url, headers, allowedEnvVars, async, once, statusMessage, shell fields
- Note: "function" type is SDK-only (callback cannot be serialized to JSON)
* feat(hooks): enhance Function Hook with messages, skillRoot, shell, and matcher support
- Add MessagesProvider for automatic conversation history passing to function hooks
- Add FunctionHookContext with messages, toolUseID, and signal
- Add skillRoot support for skill-scoped session hooks
- Add shell parameter support for command hooks (bash/powershell)
- Add regex matcher support for hook pattern matching
- Add statusMessage to CommandHookConfig
- Change default function hook timeout from 60s to 5s
- Add comprehensive unit tests for all new features
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* add session hook for skill
* fix function hook parsing
* refactor ui for http hook/async hook/function hook
* update doc and add integration test
* change telemetryn type and refactor SSRF
* fix project level bug
---------
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* feat: optimize compact mode UX — shortcuts, settings sync, and safety improvements
- Add Ctrl+O to keyboard shortcuts list (?) and /help command
- Sync compact mode toggle from Settings dialog with CompactModeContext
- Protect tool approval prompts from being hidden in compact mode
(MainContent forces live rendering during WaitingForConfirmation)
- Remove snapshot freezing on toggle — treat as persistent preference,
not temporary peek (differs from Claude Code's session-scoped model)
- Add compact mode tip to startup Tips rotation for non-intrusive discovery
- Remove compact mode indicator from footer to reduce UI clutter
- Add competitive analysis design doc (EN + ZH) comparing with Claude Code
- Update user docs (settings.md) and i18n translations (en/zh/ru/pt)
Relates to #3047, #2767, #2770
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: remove frozenSnapshot dead code and Chinese design doc
- Remove frozenSnapshot state, useEffect, and all related logic from
AppContainer, MainContent, CompactModeContext, and test files
- Simplify MainContent to always render live pendingHistoryItems
- Delete compact-mode-design-zh.md (redundant Chinese translation)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address PR review feedback for compact mode optimization
- Add refreshStatic() call after setCompactMode in SettingsDialog
so already-rendered Static history updates immediately
- Fix outdated column split comment in KeyboardShortcuts (5+4+4)
- Update design doc: remove all frozenSnapshot references, renumber
optimization recommendations, fix file reference descriptions
- Add missing i18n keys for de.js and ja.js locales
- Add test for SettingsDialog compact mode sync with CompactModeContext
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: prevent subagent confirmation from being hidden in compact mode
hasConfirmingTool only checks ToolCallStatus.Confirming, but subagent
approvals arrive via resultDisplay.pendingConfirmation while the tool
status remains Executing. Add hasSubagentPendingConfirmation to the
showCompact guard so tool groups with pending subagent confirmations
are always force-expanded.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: force show subagent confirmation result in compact mode
The previous fix (47ee03c) correctly force-expanded the tool group
wrapper when a subagent had pending confirmation, but each inner
ToolMessage still hid its resultDisplay due to compactMode check,
which hid the AgentExecutionDisplay containing the inline confirmation
UI.
Add isAgentWithPendingConfirmation to forceShowResult conditions so
the inner AgentExecutionDisplay is rendered even in compact mode.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(compact-mode): merge consecutive tool groups across hidden items
In compact mode, sequential tool calls across multiple LLM turns each
produced a separate bordered box, defeating the "compact" intent. The
model typically emits a `gemini_thought` between consecutive tool calls,
which is hidden in compact mode — so visually the boxes look adjacent,
but in `history` they are separated by hidden items.
This commit adds render-time merging of consecutive tool_group history
items, where "consecutive" allows hidden-in-compact items
(`gemini_thought`, `gemini_thought_content`) between them.
Key pieces:
- New `mergeCompactToolGroups` utility that merges adjacent mergeable
tool_groups, skipping hidden items between them. Force-expand
conditions (Confirming/Error tools, subagent pending confirmation,
user-initiated, focused embedded shell) preserve group boundaries so
authorization prompts, errors, and shell focus stay visible.
- `MainContent.tsx` applies the merger only when `compactMode === true`
(verbose mode is unchanged) and calls `refreshStatic()` when a merge
consolidates items, because Ink's `<Static>` is append-only and
cannot replace already-committed terminal content.
- `CompactToolGroupDisplay.tsx` shows a `× N` count when a merged
group contains more than one tool, matching the existing single-turn
multi-tool display style.
- 19 unit tests covering empty/single/multiple groups, hidden-item
skipping (the 8-tool real-world scenario), force-expand boundaries,
mixed tool types, and complex sequences.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: 秦奇 <gary.gq@alibaba-inc.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
PR #3291 discontinued the Qwen OAuth free tier but intentionally left the
ModelDialog unchanged, relying on server rejection for qwen-oauth models.
This follow-up adds proper UI handling consistent with the AuthDialog:
- Mark qwen-oauth model entries with "(Discontinued)" label and warning color
- Replace descriptions with "Discontinued — switch to Coding Plan or API Key"
- Block selection with inline error message instead of calling switchModel
- Show ⚠ discontinuation notice in the detail panel for highlighted entries
- Runtime OAuth models (existing cached tokens) remain selectable until server
rejects them (soft cutoff principle from PR #3291)
- Add i18n strings for the new error message across all 7 locale files
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
DingTalk provides two user identifiers: `senderId` (an internal platform ID
like `$:LWCP_v1:xxx`) and `senderStaffId` (the human-readable staff/employee
ID). The current code uses `senderId` first when constructing the Envelope,
which means `allowedUsers` configuration cannot match against the staff ID
that users actually know and configure.
Swap the priority so `senderStaffId` is preferred when available, falling back
to `senderId` only when `senderStaffId` is absent.
Made-with: Cursor
* feat(auth): discontinue Qwen OAuth free tier (2026-04-15 cutoff)
The Qwen OAuth free tier has reached its end-of-life date. This updates
all client-side messaging, blocks new OAuth signups, and guides existing
users to alternative providers.
* fix(test): add getModelsConfig mock and update QWEN_OAUTH test expectations
- Add getModelsConfig() to Config mocks in gemini.test.tsx (3 failures)
- Update validateNonInterActiveAuth test to expect exit for QWEN_OAUTH
since validateAuthMethod now returns an error for discontinued free tier
Fork subagent now reads system instruction and tool declarations from
the live GeminiChat via getGenerationConfig() instead of the global
getCacheSafeParams() snapshot. This removes the cross-module coupling
between the agent tool and the followup infrastructure.
These fields were never populated from subagent frontmatter and served
no purpose in the fork path either. The ModelConfig interface retains
only the actively-used model field.
* refactor(BaseTextInput): ignore literal Tab input in keyboard handler
- Prevent insertion of literal tab characters in the BaseTextInput component
- Require consumers to intercept Tab via onKeypress for custom behavior
- Ensure smoother handling of Tab key without affecting buffer content
* fix(cli): preserve tabbed paste in paste workaround
- Mark single-line raw chunks containing tabs as paste events in the pasteWorkaround path
- Keep a literal Tab key as a non-paste keypress
- Add KeypressContext coverage for literal Tab keys and single-line tab-separated raw chunks
* feat(acp): LLM-based message rewrite middleware
Add MessageRewriteMiddleware that intercepts ACP messages and appends
LLM-rewritten versions with _meta.rewritten=true at turn boundaries.
Original messages pass through unmodified. At the end of each turn
(before tool calls or at response end), accumulated thought/message
chunks are sent to LLM for rewriting into business-friendly text.
- TurnBuffer: accumulates chunks per turn
- LlmRewriter: calls LLM with configurable prompt
- MessageRewriteMiddleware: orchestrates intercept → buffer → rewrite → emit
- BaseEmitter.sendUpdate: routes through middleware when configured
- Session: initializes middleware from settings.messageRewrite config
Enable via settings.json:
{
"messageRewrite": {
"enabled": true,
"target": "both",
"prompt": "custom system prompt for rewriter"
}
}
Rewritten messages carry _meta.rewritten=true for frontend to
prioritize display. Original messages remain for debugging.
* fix: TypeScript 编译错误修复 + 优化默认改写 prompt（参考竞品风格）
* fix: 从 user/workspace originalSettings 读取 messageRewrite 配置（绕过 schema 校验）
* feat: 非交互 CLI 模式也支持 message rewrite（eval 可用）
* fix: 禁用 rewriter LLM 的 thinking，过滤 thought 部分只取纯文本输出
* fix: cron 路径补齐 message rewrite flush + 代码质量优化
- Session.ts cron 路径添加 messageRewriter.flushTurn() 调用
- nonInteractiveCli.ts cron 路径添加 turnBuffer 累积 + flush + rewrite
- 提取 loadRewriteConfig() 共享函数，消除两处重复配置读取
- 主路径和 cron 路径添加 turnBuffer.markToolCall()
- rewrite 调用添加 30s 超时保护（AbortSignal.timeout）
- 修复 import 语句被 const 声明分割的问题
* feat: rewrite 支持 async/sync 模式（默认 async，不增加执行时间）
* feat: rewrite prompt 通用化 + 上下文连贯 + promptFile + async 修复
- 默认 prompt 改为通用英文版（适配任意 coding agent，不绑定数据分析场景）
- 支持 promptFile 配置项，从文件加载自定义 prompt（优先于 inline prompt）
- 上下文连贯性：lastOutput 记录上一轮改写结果，拼接到下一轮输入，
避免连续 turn 间信息重复
- 修复 CLI 非交互模式 async rewrite 丢失：void doRewrite() 改为
pendingRewrites 数组 + emitResult 前 Promise.allSettled
- 增加 debug logging：REWRITE INPUT/OUTPUT 完整内容 + prev_output 长度
* refactor: remove sync rewrite mode, always use async (non-blocking) rewrite
- Remove `async` field from MessageRewriteConfig
- MessageRewriteMiddleware.flushTurn() always fires in background
- nonInteractiveCli.ts main & cron paths always push to pendingRewrites
- No user-facing latency from rewrite calls
* fix: address review feedback — trust check, timeout, history replay
1. loadRewriteConfig: skip workspace settings when !isTrusted, preventing
untrusted repos from enabling rewriter with a custom prompt
2. MessageRewriteMiddleware.flushTurn: always enforce 30s timeout internally,
even when caller provides no AbortSignal (interactive path)
3. Install rewriter AFTER history replay completes (Session.installRewriter),
so historical messages are never rewritten on session load
* fix: address second round review — target filter, timeout, rewrite queue
1. nonInteractiveCli: apply rewriteConfig.target filter to accumulation
(main path and cron path), matching MessageRewriteMiddleware behavior
2. nonInteractiveCli: add 30s AbortSignal.timeout to rewrite calls in
both main and cron paths
3. MessageRewriteMiddleware: replace single pendingRewrite slot with
pendingRewrites array + Promise.allSettled, ensuring all rewrites
complete before session exits
* test: add unit tests for TurnBuffer, loadRewriteConfig, MessageRewriteMiddleware
- TurnBuffer: flush, reset, isEmpty, markToolCall, whitespace filtering (12 tests)
- loadRewriteConfig: isTrusted gating, workspace/user precedence (5 tests)
- MessageRewriteMiddleware: target filtering, tool_call boundary flush,
pendingRewrites queue, rewrite metadata (9 tests)
* fix: config.test.ts use unknown cast for LoadedSettings stub (fix tsc --build)
* fix: filter LLM literal "empty string" responses in rewriter output
LLM sometimes outputs "（空字符串）" or similar text instead of actual
empty string when instructed to "return empty string". Add regex patterns
to catch common variants and treat them as null (skip rewrite output).
* revert: remove LLM empty-string pattern defense, rely on prompt fix instead
* fix: prevent async rewrite from corrupting adapter state + honor config.model
1. nonInteractiveCli: rewrite promises now return data only, adapter
emission happens synchronously via emitSettledRewrites() at safe
boundaries (before next turn starts, before cron next turn, before
final result). Prevents concurrent startAssistantMessage corruption.
2. LlmRewriter: use rewriteConfig.model when set, fallback to
config.getModel(). Previously model field was defined but ignored.
* docs: add messageRewrite configuration guide to settings.md
* Revert "docs: add messageRewrite configuration guide to settings.md"
This reverts commit ecd57e2d5a.
* feat: add contextTurns config for rewrite history context
Allow configuring how many previous rewrite outputs are included as
context when rewriting a new turn:
- contextTurns: 1 (default) = last rewrite only
- contextTurns: 0 = no context
- contextTurns: N = last N rewrites
- contextTurns: "all" = all previous rewrites
* refactor: rename target 'both' to 'all' + add LlmRewriter unit tests
- Rename target value 'both' → 'all' for future extensibility (e.g. 'tool')
- Add LlmRewriter tests: contextTurns (0/1/N/all), model override, filtering
- Total: 35 tests across 4 test files
* refactor: remove message rewrite from non-interactive CLI mode
Non-interactive mode (qwen -p "..." --output-format json) consumers are
scripts/programs that don't need user-friendly rewrites. Additionally,
the JSON output adapter doesn't support _meta fields, so rewritten text
was silently mixed into normal assistant messages without any marker.
Rewrite middleware is now ACP-only (Session path).
* revert: restore package-lock.json and nonInteractiveCli.ts to main state
* docs: add README for message rewrite middleware
Explain the feature purpose (business-oriented output customization),
mark it as a temporary solution, and reference the hook-based
alternative (#3266) for future discussion.
* docs: move temporary-solution notice to top of README
* docs: simplify temporary-solution notice in rewrite README
Models using thinking/reasoning modes may emit only thought content
without explicit text output. The stream validation previously rejected
these as 'empty' responses. Now accepts responses that contain either
text content or thought content when a finish reason is present.
(cherry picked from commit a0b13911f4)
Co-authored-by: mingholy.lmh <mingholy.lmh@alibaba-inc.com>
* fix(vscode): limit session tab title length to prevent tab bar overflow
- Extract truncatePanelTitle() into panelTitleUtils.ts; operates on
Unicode code points to avoid splitting surrogate pairs (e.g. emoji);
truncates to first 50 code points + '…'
- Apply truncation uniformly in WebViewProvider for all updatePanelTitle
messages, covering both createOrShowPanel and restorePanel paths
- Remove redundant 50-char truncation in SessionMessageHandler; panel
title truncation is now the sole responsibility of WebViewProvider
- Align getSessionTitle() to use the same limit (50 code points + '…')
for visual consistency between session list and tab title
- Add unit tests for truncatePanelTitle covering empty string, boundary,
long title, and emoji surrogate-pair edge cases
Fixes#2873
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(vscode): reuse truncatePanelTitle in getSessionTitle and fix fallback title logic
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
DashScope throttling (`Throttling.AllocationQuota`) surfaces as an
SSE `event:error` frame mid-stream with `:HTTP_STATUS/429` as a
comment and a non-numeric `code` in the payload. The existing
detection paths missed it, so subagents failed immediately with
`Failed to run subagent: id:1 event:error ...` instead of retrying.
- `getErrorStatus`: add a final fallback that parses `HTTP_STATUS/NNN`
out of `error.message`, bounded by `\b` and the 100-599 range, so
streamed errors where the SDK never sees a real HTTP status can
still be classified.
- `getErrorCode`: fix three `|| null` early-returns that swallowed
later fall-through paths when the provider code was non-numeric
(`isApiError` top-level, `isApiError` JSON-in-message, and
`isStructuredError`). The branches now fall through on non-numeric
values so `.status` or the new `HTTP_STATUS/NNN` fallback can
recover the real code.
* feat(vscode-ide-companion): add /account for account display
* fix(account): intercept typed /account command and read session-level config
1. Handle literal /account in useMessageSubmit.ts so typing it triggers
the account dialog instead of sending it as a chat message.
2. Pass sessionId through extMethod params and read from session config
instead of agent-level config, so /account reflects model changes
made via /model within the current session.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
---------
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Identity-shaping fork inputs (parent history, generationConfig, tool decls,
env-skip flag) were threaded through `AgentHeadless.execute()`'s options bag
and re-passed by the SubagentStop hook retry loop. They belong on the agent's
construction-time configs, not its per-invocation options.
- PromptConfig gains `renderedSystemPrompt` (verbatim, bypasses templating
and userMemory injection) and drops the `systemPrompt`/`initialMessages`
XOR so fork can carry both. createChat skips env bootstrap when
`initialMessages` is non-empty.
- AgentHeadless.execute() shrinks to (context, signal?). Fork dispatch in
agent.ts builds synthetic PromptConfig/ModelConfig/ToolConfig from the
parent's cache-safe params and calls AgentHeadless.create directly
(bypassing SubagentManager). Parent's tool decls flow through verbatim
including the `agent` tool itself for cache parity.
- Recursive-fork prevention switches from fork-side tool stripping to a
runtime guard. The previous `isInForkChild(history)` helper was dead
code (it scanned the main GeminiClient's history, not the fork child's
chat). Replaced with `isInForkExecution()` backed by AsyncLocalStorage:
the fork's background execution runs inside `runInForkContext`, and the
ALS frame propagates through the standard async chain into nested
AgentTool.execute() calls where the guard fires.
* feat(core): implement fork subagent for context sharing
- Make subagent_type optional in AgentTool
- Add forkSubagent.ts to build identical tool result prefixes
- Run fork processes in the background to preserve UX
* fix(core): fix test failures related to root execution and optional subagent_type
- Skip pathReader and edit tool permission tests when running as root
- Fix agent.test.ts to correctly mock execute call with extraHistory
- Remove unused imports in forkSubagent.ts
* fix(core): fix fork subagent bugs and add CacheSafeParams integration
Bug fixes:
- Fix AgentParams.subagent_type type: string -> string? (match schema)
- Fix undefined agentType passed to hook system (fallback to subagentConfig.name)
- Fix hook continuation missing extraHistory parameter
- Fix functionResponse missing id field (match coreToolScheduler pattern)
- Fix consecutive user messages in Gemini API (ensure history ends with model)
- Fix duplicate task_prompt when directive already in extraHistory
- Fix FORK_AGENT.systemPrompt empty string causing createChat to throw
- Fix redundant dynamic import of forkSubagent.js (merge into single import)
- Fix non-fork agent returning empty string on execution failure
- Fix misleading fork child rule referencing non-existent system prompt config
- Fix functionResponse.response key from {result:} to {output:} for consistency
CacheSafeParams integration:
- Retrieve parent's generationConfig via getCacheSafeParams() for cache sharing
- Add generationConfigOverride to CreateChatOptions and AgentHeadless.execute()
- Add toolsOverride to AgentHeadless.execute() for parent tool declarations
- Fork API requests now share byte-identical prefix with parent (DashScope cache hits)
- Graceful degradation when CacheSafeParams unavailable (first turn)
Docs:
- Add Fork Subagent section to sub-agents.md user manual
- Add fork-subagent-design.md design document
* fix(core): apply subagent tool exclusion to forked agents
Fork children were inheriting parent's cached tool declarations directly,
bypassing prepareTools() filtering and gaining access to AgentTool and
cron tools. Extract EXCLUDED_TOOLS_FOR_SUBAGENTS as a shared constant
and apply it to forkToolsOverride.
* fix(core): skip env history whenever extraHistory is provided
Previously gated on generationConfigOverride, which meant the no-cache
fallback path (CacheSafeParams unavailable) still ran getInitialChatHistory
and duplicated env bootstrap messages already present in the parent's
history. Gate on extraHistory instead so both fork paths skip env init.
* fix(core): use explicit skipEnvHistory flag for fork env handling
The previous fix gated env-init skipping on the presence of extraHistory,
but agent-interactive (arena) also passes extraHistory — its chatHistory is
env-stripped by stripStartupContext() and DOES need fresh env init for the
child's working directory. Skipping env there broke the interactive path.
Replace the implicit gate with an explicit skipEnvHistory option that only
fork sets (when extraHistory is present, since fork's history comes from
getHistory(true) and already contains env).
* fix(core): defend skipEnvHistory gate against empty extraHistory
Edge case: when the parent's rawHistory ends with a user message and has
length 1, extraHistory becomes []. The previous gate (extraHistory !==
undefined) would set skipEnvHistory: true, leaving the fork with neither
env bootstrap nor parent history. Check length > 0 so empty arrays fall
through to the normal env-init path.
* fix(core): apply skipEnvHistory to stop-hook retry execute
The second subagent.execute() call in the SubagentStop retry loop was
missing skipEnvHistory, so on retry the fork's env context would be
duplicated — same bug as the initial tanzhenxin report, just on a less
common code path.
feat(cli): add startup performance profiler (#3219)
Add a lightweight startup profiler activated via QWEN_CODE_PROFILE_STARTUP=1.
When enabled, collects performance.now() timestamps at 7 key phases in main()
and writes a JSON report to ~/.qwen/startup-perf/. Also records
process.uptime() at T0 to capture module loading time not covered by
checkpoint-based measurement.
Key design decisions:
- Only profiles inside sandbox child process to avoid duplicate reports
- initStartupProfiler() is idempotent (resets state on each call)
- Filename uses report.sessionId for consistency with JSON content
- Zero overhead when disabled (single env var check)
Initial measurement: module loading ~1342ms (94%), main() ~85ms (6%),
confirming barrel exports and eager dependency loading as primary
optimization targets for #3011.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* feat(cli): implement non-interactive /context output and diagnostic
- Extract collectContextData() from contextCommand.ts for shared usage.
- Register /context in ALLOWED_BUILTIN_COMMANDS_NON_INTERACTIVE.
- Extend SDK control protocol with GET_CONTEXT_USAGE request.
- Implement handleGetContextUsage in SystemController for programmatic token queries.
- Expose getContextUsage() method in the TypeScript SDK Query interface.
* fix: address review feedback and fix critical bugs in context usage feature
- Add missing `get_context_usage` route in ControlDispatcher (SDK calls would throw)
- Fix `executionMode` defaulting: use `?? 'interactive'` to match other commands
- Validate dynamic import of `collectContextData` before invoking
- Preserve original error message in handleGetContextUsage catch block
- Add ControlDispatcher test for get_context_usage routing
- Add JSDoc comment for context command in non-interactive allowlist
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: re-check abort signal after async operations in handleGetContextUsage
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: add getContextUsage() to SDK TypeScript documentation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: clarify getContextUsage showDetails is a display hint, not a data filter
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: make showDetails affect response shape, add getContextUsage test
- When showDetails is false, return empty detail arrays instead of full
data so /context and /context detail produce different payloads
- Add unit test for Query.getContextUsage() covering request payload
and response handling
* fix: strip UI type from SDK response, sync Java SDK protocol
- Remove leaked `type: 'context_usage'` from control response payload
- Add GET_CONTEXT_USAGE to Java SDK protocol mirror (enum, interface,
union type)
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: update quota exceeded alternatives to OpenRouter and Fireworks
- Update README.md news section to recommend OpenRouter and Fireworks
as primary alternatives, with ModelStudio as third option
- Update retry.ts quota error message to include OpenRouter and
Fireworks URLs for users whose OAuth quota has been exhausted
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* fix(test): update retry test assertions to match new quota error message
* docs: update free tier quota to 100 req/day with sunset notice and alternatives
Update all references to reflect the Qwen OAuth free tier policy change:
- 1,000 → 100 requests/day across code, i18n, and docs
- Add 2026-04-15 sunset date everywhere
- Guide users to OpenRouter, Fireworks AI, or ModelStudio in docs
- Remove CHANGELOG.md
---------
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Co-authored-by: tanzhenxin <tanzhenxing1987@gmail.com>
* feat(core): add microcompaction for idle context cleanup
Clear old tool result content from chat history when the user returns
after an idle period (default 60 min). Replaces functionResponse output
with a sentinel string for compactable tools (read_file, shell, grep,
glob, web_fetch, web_search, edit, write_file), keeping the N most
recent results intact (default 5). Runs before full compression so it
can shed tokens cheaply without an API call.
- Time-based trigger reuses lastApiCompletionTimestamp from thinking cleanup
- Per-part counting so keepRecent applies to individual tool results
even when batched in parallel
- Preserves tool error responses (only clears successful outputs)
- Configurable via settings.json (context.microcompaction) with env var
overrides for E2E testing
- Enabled by default
* refactor(config): unify idle cleanup settings under clearContextOnIdle
Consolidate thinking block cleanup and tool results microcompaction
config into a single `context.clearContextOnIdle` settings group:
{
"context": {
"clearContextOnIdle": {
"thinkingThresholdMinutes": 5,
"toolResultsThresholdMinutes": 60,
"toolResultsNumToKeep": 5
}
}
}
- Use -1 on either threshold to disable that cleanup (no enabled bool)
- Remove separate `microcompaction` and `gapThresholdMinutes` settings
- Thinking cleanup: 5 min default (unchanged)
- Tool results cleanup: 60 min default
- Preserve tool error responses (only clear successful outputs)
* feat(vscode-ide-companion): add clearContextOnIdle settings configuration
- Add gapThresholdMinutes settings for thinking blocks, tool results, and retention count
- Remove deprecated gapThresholdMinutes from root settings level
This reorganizes the context clearing settings into a dedicated clearContextOnIdle object with configurable thresholds for thinking blocks and tool results.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* fix(core): restrict microcompaction to user-initiated messages only
Move microcompactHistory() inside the UserQuery/Cron guard so model
latency during tool-call loops doesn't count as user idle time.
* docs: update settings docs for clearContextOnIdle config rename
Replace stale `context.gapThresholdMinutes` entry with the new
`context.clearContextOnIdle.*` settings group introduced in the
microcompaction feature.
* fix(core): address review comments on microcompaction PR
- Guard against NaN in toolResultsNumToKeep with Number.isFinite()
- Report effective keepRecent (after Math.max) in meta, not raw config
- Fix comment to mention cron messages alongside user messages
---------
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
The agent name validation regex only permitted ASCII letters, numbers,
hyphens, and underscores, silently rejecting agents with non-ASCII names
(e.g., Chinese "项目管理"). Replace the regex with Unicode property
escapes (\p{L}\p{N}) to allow letters and numbers from any script.
Also guard the lowercase naming convention warning so it only fires when
the name contains ASCII letters, since case is meaningless for CJK
scripts.
Fixes#3149
* feat(subagents): add disallowedTools field to agent definitions
Add a `disallowedTools` blocklist to agent frontmatter, letting agents
specify tools they should not have access to. Supports exact tool names,
MCP server-level patterns (e.g., `mcp__slack`), and display name aliases.
Applied as a post-filter in AgentCore.prepareTools() after the existing
`tools` allowlist. Persisted through serialize/parse roundtrips.
* docs: document disallowedTools and MCP tool behavior for subagents
Add Tool Configuration section to sub-agents docs explaining:
- tools allowlist and disallowedTools blocklist
- How MCP tools follow the same allowlist/blocklist rules
- MCP server-level patterns in disallowedTools
* fix(subagents): validate disallowedTools in SubagentValidator
Reuse the existing validateTools() method to validate disallowedTools
entries at config validation time, catching non-string and empty entries
before they reach runtime.
* test: remove flaky BaseSelectionList scroll test on Windows
Typing `exit`, `quit`, `:q`, `:q!`, `:wq`, or `:wq!` at the prompt now
exits the CLI — same as `/quit`. This matches Claude Code behavior and
helps users on mobile (e.g. Termux) where Ctrl+C is harder to type.
Closes#3169
When ESC (or Ctrl+C) cancelled an in-progress model response, the
input buffer was being repopulated with the just-submitted prompt.
The handler unconditionally read userMessages.at(-1) and called
buffer.setText with it, surprising users who expected ESC to leave
the input clean. The previous prompt is still recoverable via Up
arrow / Ctrl+P history navigation.
Queued follow-up messages still get moved into the buffer for
editing on cancel, but now via the atomic popAllMessages helper,
and any in-progress draft the user typed is preserved by prepending
the queued text instead of clobbering it (matching the existing
popQueueIntoInput convention in InputPrompt).
Fixes#3204
validateAuthMethod's pre-flight check only inspected OPENAI_API_KEY (and
settings.security.auth.apiKey), so credentials supplied via --openai-api-key
were rejected even though refreshAuth would have accepted them. macOS users
were unaffected because OPENAI_API_KEY is commonly exported in their shell
profile; on Linux without that env var, the CLI failed to start.
hasApiKeyForAuth now prefers the API key already resolved into
generationConfig.apiKey when a Config is provided. The unified resolver
folds CLI flags, env vars, settings, and modelProvider envKey lookups into
this single value, so validation matches runtime behavior.
Fixes#3171
* fix(core): show clear error when MCP server cwd does not exist
Validate that the configured cwd directory exists before spawning the
MCP server process. Previously, a non-existent cwd caused Node.js to
emit "spawn <cmd> ENOENT" — indistinguishable from the command binary
being missing. Now throws a descriptive error naming the server and
the missing path.
Fixes#3163
* test(core): add test for MCP stdio transport without cwd
* feat(skills): add model override support via skill frontmatter
Allow skills to specify a `model` field in YAML frontmatter to override
which model is used for subsequent turns within the same agentic loop.
The override flows through ToolResult → ToolCallResponseInfo →
SendMessageOptions and naturally expires when the loop ends.
Resolves#2052
* fix(core): only include modelOverride in response when defined
Fixes strict equality test failures in nonInteractiveToolExecutor.test.ts
where the extra undefined modelOverride field caused object mismatch.
* fix(skills): fix model override pipeline issues
- Wire up modelOverride in interactive CLI path (useGeminiStream)
- Fix inherit/no-model unable to clear a prior override by using
'in' operator instead of truthiness checks in scheduler and CLI
- Reject empty/whitespace model strings in parseModelField()
- Extract shared parseModelField() to deduplicate skill-load and
skill-manager parsing logic
- Propagate modelOverride through stop-hook continuation in client
* fix(skills): persist model override across turns in interactive and cron paths
The interactive path stored the skill model override in a local variable,
causing it to be lost when subsequent non-skill tool turns ran. Use a ref
to persist the override for the duration of the agentic loop, resetting on
new user messages. Also propagate modelOverride in the cron execution loop
for consistency with the main non-interactive path.
* fix(skills): preserve model override on retry and add unit tests
Retry in interactive mode was clearing modelOverrideRef, causing the
skill-selected model to silently fall back to session default. Guard
the reset so retries preserve the active override.
Add unit tests for parseModelField (edge cases, type validation) and
modelOverride propagation through the skill tool result path.
pathReader.ts hardcoded respectGitIgnore: true when filtering files for
@{path} injection (used by slash commands), ignoring the user's
context.fileFiltering.respectGitIgnore setting. This meant gitignored
files were silently dropped even when the user explicitly set the
setting to false.
Now reads the filtering options from config instead of hardcoding.
Fixes#3142
* feat(subagents): propagate approval mode to sub-agents
Replace hardcoded PermissionMode.Default with resolution logic:
- Permissive parent modes (yolo, auto-edit) always win
- Plan-mode parents keep sub-agents in plan mode
- Agent definitions can declare approvalMode in frontmatter
- Default fallback is auto-edit in trusted folders
- Untrusted folders block privileged mode escalation
Also maps Claude permission aliases (acceptEdits, bypassPermissions,
dontAsk) to qwen-code approval modes in the converter.
* fix(subagents): correct dontAsk mapping and add approval mode resolution tests
Map Claude's `dontAsk` to `default` instead of `auto-edit` — `dontAsk`
denies prompts (restrictive) so `default` is a closer semantic match.
Add 9 unit tests covering the full `resolveSubagentApprovalMode` decision
matrix: permissive parent override, agent-declared modes, trusted/untrusted
folder blocking, and plan-mode fallback.
* test: remove flaky InputPrompt tab-suggestion test on Windows
* feat: add contextual tips system with post-response context awareness
Add a context-aware tips system that proactively shows helpful tips based
on session state. Post-response tips warn when context usage exceeds 80%
or 95%, suggesting /compress. Startup tips rotate across sessions via LRU
scheduling with cross-session persistence (~/.qwen/tip_history.json).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: use value import for runtime values in useContextualTips
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address PR review feedback
- Use lastSessionTimestamp instead of totalShown for cross-session LRU
- Move getTipHistory singleton from Tips.tsx to services/tips/index.ts
- Defer TipHistory.load() when hideTips is true (no side effects)
- Use os.tmpdir() in tests for cross-platform portability
- Add proper translations for de/ja/pt/ru locale files
- Accept TipHistory | null in useContextualTips
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address Copilot review feedback
- Validate tips field type in TipHistory.load() to handle corrupted JSON
- Split approval-mode tip into platform-specific variants using ctx.platform
- Add afterEach cleanup for temp files in all test suites
- Guard useContextualTips against null tipHistory
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: import shared DEFAULT_TOKEN_LIMIT, harden tipHistory, set file permissions
- Import DEFAULT_TOKEN_LIMIT from @qwen-code/qwen-code-core instead of
hardcoding 1_048_576 in tipRegistry.ts and useContextualTips.ts
- Add normalizeEntry() to defensively handle corrupted tip history entries
- Write tip_history.json with mode 0o600 for privacy on multi-user systems
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove unused compressionThreshold from TipContext
compressionThreshold was defined in TipContext but never used by any tip's
isRelevant check. Remove it to avoid misleading consumers into thinking
tips respect the user's compression settings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: sanitize sessionCount and getLastShown against corrupted tip history
- Validate sessionCount is finite and non-negative in TipHistory.load()
- Use normalizeEntry() in getLastShown() for corrupted lastSessionTimestamp
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: add contextual tips user documentation
Add docs/users/features/tips.md covering startup tips, post-response
context warnings, tip history persistence, and the hideTips setting.
Update settings.md description and register the new page in _meta.ts.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Change default model from qwen3.6-plus to qwen3.5-plus for both China and Global regions
- qwen3.6-plus requires Pro subscription, Lite users cannot use it
- Add description to qwen3.6-plus indicating Pro subscription requirement
- Update MAINLINE_CODER_MODEL to qwen3.5-plus for OpenAI-compatible API default
Fixes#3037
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
