Add flexGrow/flexShrink to left section so it takes available space
but yields to right items. Add flexShrink={0} to right section so
context usage, verbose, sandbox indicators are never compressed.
Add overflow="hidden" to left section for clean truncation.
The status line is now inlined in the footer's left section,
so horizontal padding is no longer applicable. Remove padding
from StatusLineConfig, settings schema, JSON schema, and docs.
Move status line from a dedicated row below the footer into the
footer's left section, replacing "? for shortcuts" when active.
High-priority messages (Ctrl+C/D, Esc, vim INSERT, shell mode)
still override the status line.
Move approval mode indicator to a separate row below the footer,
shown only when mode is non-default. This eliminates the empty
gap in default mode and matches upstream layout.
- Instruct agent to use "bash script.sh" pattern instead of direct
execution (agent cannot chmod +x without SHELL tool)
- Replace vague "skip optional locks" with concrete GIT_OPTIONAL_LOCKS=0
- Simplify "parent agent" framing to direct user-facing message
- Compute remaining_percentage as round(100 - used) to guarantee
used + remaining always sums to exactly 100.0
- Reject empty or whitespace-only command strings in config validation
useStatusLine hook accesses sessionStats.metrics.tools.totalCalls,
sessionStats.metrics.files.totalLinesAdded, and currentModel which
were missing from the mock UIState, causing a TypeError crash during
render and making 4 Footer tests fail in CI.
Restructure the status line stdin JSON for clarity and accuracy:
- Rename model.id → model.display_name, cwd → workspace.current_dir
- Replace raw context_window size/count with used_percentage,
remaining_percentage, current_usage, context_window_size, and
total_input_tokens/total_output_tokens
- Add version field from cfg.getCliVersion()
- Add git.branch, metrics.models, metrics.files
- Remove upstream-only fields: tokens.tool (never populated),
session (start_time/elapsed_time not live-updating),
streaming_state, approval_mode, terminal, metrics.tools
- Rename tokens.candidates → tokens.completion (Qwen API convention)
- Fix template string escaping in builtin-agents to avoid
templateString() placeholder collision
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(core): adaptive output token escalation (8K default + 64K retry)
99% of model responses are under 5K tokens, but we previously reserved
32K for every request. This wastes GPU slot capacity by ~4x.
Now the default output limit is 8K. When a response hits this cap
(stop_reason=max_tokens), it automatically retries once at 64K — only
the ~1% of requests that actually need more tokens pay the cost.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: add design doc and user doc for adaptive output token escalation
- Add design doc covering problem, architecture, token limit
determination, escalation mechanism, and design decisions
- Document QWEN_CODE_MAX_OUTPUT_TOKENS env var in settings.md
- Add max_tokens adaptive behavior explanation in model config section
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
"Yes, and manually approve edits" was restoring getPrePlanMode() which
could be YOLO, contradicting the label. Now hardcodes DEFAULT to match
the "manually approve" semantics.
Align with observed provider prompt-cache TTL (~5 min). Add
`context.gapThresholdMinutes` setting so users can tune the threshold
for providers with different cache TTLs.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Rename the subcommand to accurately reflect its behavior (exits plan
mode and restores previous approval mode, does not trigger execution).
Update source, tests, i18n keys (6 locales), and docs.
Most Qwen OAuth users don't have a fast model configured for this
feature, so it fires a wasted API request on every turn with no
visible benefit. Default to off; users can opt in via settings.
The iLink Bot API requires these headers for session authentication.
Without them, getupdates returns errcode -14 (session timeout).
The protocol version (2.0.0) is tracked independently from our channel
version, matching the current official plugin's API compatibility level.
Closes#2908
Same class of Windows CI timing flake — the backspace keypress
doesn't propagate through the paste/keypress pipeline fast enough
on slow runners, so replaceRangeByOffset is never called (0 calls).
The test has a stale closure race condition: the 50ms wait between
pressing '2' and Enter may not be enough for React/Ink to re-render
and re-subscribe the useKeypress callback with the updated
selectedIndex, causing it to read the default value (0) instead of
the expected value (1) on slow CI runners (Windows + Node 20).
The function only checked for string-form type inside anyOf/oneOf variants,
missing the array form (e.g., type: ["array", "null"]). This mirrors the
handling already done at the top-level property schema.
Remove core dependency from webui by inlining followup controller logic.
This fixes nightly release CI failure where npm version couldn't resolve
the core peer dependency for prerelease versions.
- Move FollowupState type and INITIAL_FOLLOWUP_STATE to src/types/followup.ts
- Inline createFollowupController into src/hooks/useFollowupSuggestions.ts
- Remove separate @qwen-code/webui/followup subpath and vite config
- Export useFollowupSuggestions from main entry
Fixes#2900
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
The vsce package was causing ESM module resolution errors when building
locally due to a dependency cycle between ansi-regex (ESM-only in v6)
and strip-ansi (CommonJS) pulled in by @textlint/linter-formatter.
CI already installs vsce globally before packaging, so this change
aligns local builds with CI behavior. Developers should install vsce
globally: npm install -g @vscode/vsce
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
The broad CODEOWNERS wildcard was adding notification noise without
providing meaningful ownership boundaries. Removing it so that any
team member with write access can provide approving reviews.
* feat(core): implement mid-turn queue drain for agent execution
Inject queued user messages between tool execution steps within a single
turn, so the model sees them immediately instead of waiting for the
entire round to complete.
- Add `dequeueAll()` to AsyncMessageQueue
- Add `midTurnDrain` callback to ReasoningLoopOptions
- Drain queue after processFunctionCalls, inject as text parts
- AgentComposer always enqueues directly (no local buffering)
- Add QUEUE_MESSAGES_CONSUMED event for UI sync
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(cli): add mid-turn queue drain to main session
Extend mid-turn queue drain to the main session's tool execution path
(useGeminiStream). Previously only agent tabs had this feature.
- Add midTurnDrainRef parameter to useGeminiStream
- Inject queued messages in handleCompletedTools before submitQuery
- Bridge useMessageQueue to drain ref in AppContainer via ref pattern
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address Copilot review feedback on mid-turn drain
- Guard midTurnDrain with abort check to prevent message loss on cancel
- Synchronously clear messageQueueRef to prevent duplicate drains
- Only clear pending display on IDLE status, not all status changes
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: scope mid-turn drain to main session only
Revert subagent-path changes (AgentCore, AgentInteractive,
AgentComposer, AsyncMessageQueue, agent-events) to keep the PR
focused on the main session, which is easier to test and validate.
Subagent mid-turn drain can be added in a follow-up PR.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address Copilot review on main session mid-turn drain
- Move synchronous queue ref into useMessageQueue itself, expose
drainQueue() for atomic drain (fixes race between addMessage and drain)
- Record drained messages as USER history items so the transcript
stays complete
- Simplify AppContainer bridge to just midTurnDrainRef.current = drainQueue
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: guard mid-turn drain against cancelled turns
- Skip drain when turnCancelledRef or abortController signal is set,
so queued messages stay for the next turn instead of being lost
- Restore ref-based queue bridge (drainQueue removed from useMessageQueue)
- Keep synchronous ref clear to prevent duplicate drains
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Per maintainer review (tanzhenxin): default verboseMode reverted to true
to preserve existing behavior — compact mode is opt-in via Ctrl+O.
Also addresses wenshao's security concern: in compact mode, tool groups
now force-expand on Error status (in addition to existing Confirming
handling), and ToolMessage force-shows result for both Confirming and
Error statuses so users always see diffs before approval and error
details for debugging.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
"Use the Agent tool with subagent_type" is more direct than
"Create an Agent", reducing ambiguity for the model.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Inline shell snippets need sh -c to execute via pipe, matching how
child_process.exec() runs the configured command.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Footer comment now accurately states only the "? for shortcuts"
hint is suppressed, not all left-section items
- Docs now note that Windows uses cmd.exe by default and suggest
wrapping commands with bash -c or using a bash script
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
PS1 \n should be removed or replaced with a space since the status
line only displays the first line of stdout. Also added a guideline
that commands must produce exactly one line of output.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Use echo "$input" instead of echo $input for proper shell variable
quoting, consistent with the script file example.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix "three distinct permission modes" → "four" (Plan was always listed)
- Update refactor example to use /plan command instead of /approval-mode
- Fix grammar in example description
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The settings parser uses stripJsonComments + JSON.parse, which does
not support trailing commas. Changed the config example from jsonc
to json and removed trailing commas so users can copy-paste safely.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add size > 0 check before computing context percentage to prevent
division by zero when context_window_size is unavailable.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add jq prerequisite section
- Clarify that settings changes take effect without restart
- Provide complete JSON in troubleshooting test command
- Move script filename out of code block to avoid shebang confusion
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
