* feat(web-shell): add adaptive navigation rail and unified Live settings
* style(web-shell): add space below the Home action section
* Revert "style(web-shell): add space below the Home action section"
This reverts commit a2e1c76223.
* fix(web-shell): Preserve navigation and Live drafts across refreshes
* fix(web-shell): keep rail navigation state, drag widths, and Live settings drafts consistent
Address the Critical findings from the latest review rounds:
- Build the standalone shell sidebar config from the sidebar's exported
defaults so the Agents entry can no longer silently drop out.
- Gate rail navigation's persisted uncollapse behind restoresColumn so
opening a full page (Settings, Plugins, ...) no longer rewrites the
user's collapse preference; only Home/Channels/Live restore the column.
- Reset the sidebar section when a panel closes and stop leaking 'split'
as a sidebar page, so a wide split keeps the home column and a working
collapse control.
- Clamp drag widths to the container-aware cap the CSS already renders,
floor the visual drag at the layout minimum, and restore the persisted
width from state instead of a mid-animation/container-capped rect.
- Cap the compact drawer's min-width at the container width.
- Keep the Live voice trigger reachable from the Live page header when
the sidebar's slot is hidden.
- Settle Live settings draft fields (and their conflict baselines) that a
refresh converges onto, so a later edit is not blocked by a stale
baseline.
* fix(web-shell): keep rail panel sections, status dots, and Live drafts consistent
Address review findings on the navigation-rail change: retain the
Channels/Live sidebar section when its panel closes (an explicit Home
choice sticks on the first click), load secondary-workspace attention
status whenever the Home column is hidden (idling the poll when nothing
runs), ignore zero-displacement presses on the resize handle, settle
padded Live settings drafts on trimmed refresh convergence, disable the
shortcut capture until status loads, key the empty-chat welcome chrome
off the shell container signal, and document /live in the pre-auth path
lists.
* fix(web-shell): close rail-era gaps in shortcut, dock, and status handling
Address the round-5 review findings on the navigation-rail change. The
Cmd/Ctrl+B handler resolved its target with e.target, which shadow-DOM
retargeting replaces with the portal host, so the editable-target
exemption never fired for portaled dialogs; it now reads
composedPath()[0] like its siblings. The same handler toggled the raw
sidebarCollapsed state, silently inverting the persisted preference in
the split-view fold band where the sidebar renders folded regardless;
the shortcut, the sidebar prop, and the environment-panel dock budget
now share one effective-collapsed expression. The rail's 56px is
excluded from the dock budget so the environment panel keeps docking at
1440px windows instead of being force-closed on load, with the e2e step
re-pinned at 1440 and the consequence recorded in the sidebar docs. The
secondary-workspace status queries now stay active while the Live
section column is open (the rail Home button is the only status surface
there), and the rail branch resets the project search when Live unmounts
its autoFocus field so a Home round-trip cannot steal focus. The Live
Voice card gates key removal and the required marker on the saved key
state, so a model edit leaving a route can no longer offer removal of a
key that was never stored.
* fix(web-shell): stop silent collapse-preference and drag-width rewrites
Address the round-5 review findings on the navigation-rail change, plus
the residual direction of the round-4 fold-band fix:
- The Cmd/Ctrl+B toggle computed from the effective folded state is a
constant expansion in the split-view fold band; it now rewrites the
unchanged preference there instead of flipping a stored `true` to
`false` on a keypress that changes nothing on screen.
- The rail's column restore fires `onCollapsedChange(false)` only when
the sidebar is actually collapsed, so a drawer tap on Channels/Live no
longer silently clears the desktop preference from the forced-open
drawer.
- The Channels rail entry restores the column only when the Channels
column exists (`channelNavigationEnabled`), matching openNavigation's
rule for full-page entries.
- The App's rail-Home callback drops its redundant preference write; the
sidebar's openNavigation already owns column restoration.
- A drag released at or past the container cap while the cap already
bound the start width no longer persists the capped width over a wider
stored preference, and releasing at the drag start restores the
pre-drag state width as well.
- The Live settings settle effect now runs only on a genuine status
change, so typing a value that briefly trims onto the saved one no
longer loses the just-typed characters.
Each behaviour is pinned by a unit case that goes red without its fix.
* fix(web-shell): settle Live drafts only on genuinely changed values
Follow-up to the round-5 settle fix: the daemon SDK returns a fresh
status object per fetch, so keying the settle effect on object identity
still let a 1s install poll or focus refresh with unchanged data
converge a padded draft the user was typing. Compare the settle-relevant
saved values against the previous status instead: only a refresh that
actually moved a saved value settles, while draft-only re-renders and
unchanged polls leave the in-progress text alone. Pinned by `does not
settle a padded draft when a poll returns unchanged values`, red against
the identity comparison and green with value comparison; the convergence
cases stay green.
* fix(web-shell): keep capped drags window-scoped and drop detached rail hints
Address the two round-6 Critical findings:
- The container-cap guard added last round only covered a release past the
cap. While the cap binds, the rendered edge cannot follow the pointer, so
the rect-based delta is container-scoped in both directions: a 2px
leftward jitter stored 298 over a 420 preference, and a later host
widening rendered the narrow value. Map the pointer delta onto the state
width whenever the cap bound at drag start, so persistence stays
window-scoped (418), while the past-cap branch keeps priority and an
uncapped drag still persists what the user saw.
- navigationHint held a live rail button and was only cleared by DOM
handlers on the nav. Removed elements fire neither pointerout nor blur,
so an unmounted rail - or just an unmounted hinted button, when its
feature gate flips - left the tooltip Popover open against a detached
node, painting the previous icon label near the viewport origin when the
rail returned. Clear the hint when the rail is gone or its anchor is
detached; the check runs every render because a dependency list cannot
observe a child unmounting while both deps stay unchanged.
Both are pinned by cases that go red without their fix: a leftward jitter
stores 418 (298 without the mapping, with the two neighbouring width cases
still green), and a rail tooltip does not survive a rail -> single -> rail
round trip.
* fix(web-shell): re-baseline hidden-surface and failed-save trackers
Address the two round-7 Critical findings:
- The secondary-workspace completion tracker only re-baselined while the
status surface was hidden, leaving a frozen running snapshot across a
visible Home period. Comparing the next refetch against it repainted a
completion the user watched happen as an unread one. The visible path now
nulls the per-source baseline, so the first hidden cycle after a visible
period is baseline-only: only completions actually observed while hidden
produce a dot. The always-hidden sibling path (and its existing test in
WebShellSidebar.collapse-persist.test.tsx) is untouched.
- A save rejected after the daemon persisted some of its writes (its
settings writes land before setEnabled, which rolls back only `enabled`)
was reported as settings.liveSetup.conflict: the stale apiKey baseline
compared against the refreshed keyConfigured/storedKey flipped by the
card's own request. The rejected save now queues a re-baseline of the
request keys and refreshes, and conflict with those keys is suspended
until the refreshed status lands and re-anchors them (state, not a ref,
so the re-baseline provokes the render that clears it).
Both pinned by cases that go red without the fix: no completed badge after
a plugins -> home -> plugins round trip while the sibling always-hidden
case stays green, and no conflict plus a retryable Save after a partially
landed save.
* fix(web-shell): stop certifying unfreshed secondary workspace status
Address the round-8 Critical (body-level, independently confirmed by
qqqys): the secondary catalog page is loaded and polled only while the
Home column is hidden, but the rail Home button folded its retained
snapshots into the indicator unconditionally. An approval resolved
elsewhere kept painting the amber dot and the "Waiting for approval"
accessible name until the user hid the Home column again — two render
sites for one stale certification, and a regression over the pre-PR
surface, which could only render the dot from a live, fetchable path.
build the rail indicator from the primary page plus only those secondary
sessions whose queries are currently armed. While the Home column is
visible the secondary contribution is dropped entirely; hiding the Home
column re-arms the queries and the still-waiting state comes back. On
live-state daemons the secondary catalog path is unloaded regardless, so
nothing live is hidden by this gate. Pinned by a plugins -> home ->
plugins round trip asserting both the dot attribute and the accessible
name, red without the gate while the always-hidden attention case stays
green.
* fix(web-shell): gate the completion tracker baseline on page freshness
Address round-9 Critical R9-1: nulling the secondary baseline on the
visible path closes only half the leak. On re-entering the hidden
surface the tracker installed the store's retained, never-refetched
catalog page as the new baseline (the guard rejected only loading and
error, never a stale page), so the poll arriving seconds later was
diffed against a snapshot taken before the visible window and a
completion the user watched was repainted as unread — exactly what the
visible-path null was supposed to prevent.
Stamp the moment the surface becomes hidden and refuse to install or
compare any secondary snapshot that is not provably fresh
(`(snapshot.updatedAt ?? 0) < hiddenSince`, an unstamped page counting
as not-fresh). The first after-hidden poll then installs the baseline
from truly fresh data. The strengthened round-trip case drives retained
running -> stale re-entry -> fresh idle; it is red without the gate
(the completion badge and the Finished accessible name both appear) and
green with it, while the always-hidden completion case stays green.
* fix(web-shell): clamp every collapse entrance and clear More on rail teardown
Address round-9 Criticals R9-2 and R9-3 (body-level):
- The split-view fold-band clamp lived only at the Cmd+B entrance; the
rail's Collapse/Expand button reached handleSidebarCollapsedChange
unclamped, so a click that visibly does nothing still overwrote the
stored preference and a stored `true` could never be re-written inside
the band. The clamp now lives once in the shared writer: in the fold
band it re-stores the current raw preference regardless of which value
was requested. (`sidebarCollapsed` and `splitFoldedSidebar` reach the
stable []-callback through refs — the former would close over the
mount-time value and the latter is declared later, TDZ.) The Cmd+B
site shrinks back to passing the toggle intent. Pinned by a third arm
in the fold-band App test that clicks the collapse toggle at 1100px
and finds the stored `true` untouched — red with the clamp removed.
- The More reset effect did not watch layout, so a rail -> single ->
rail round trip left moreOpen=true against an unmounted owner and the
rail returned with a phantom open menu (content in the document,
focus inside, never reopened). `layout` joins the dependency list and
a round-trip case in WebShellSidebar.collapse-persist.test.tsx goes
red without it.
* fix(web-shell): let exit-split navigation restore the column under the fold clamp
Address maintainer P2 inline: after the shared-writer clamp landed, a
Home click from the split-view fold band was still intercepted — the
rail's restoresColumn `onCollapsedChange(false)` wrote the folded raw
value back (correct for taps that stay in split view), and `onOpenHome`
then closed split view with the raw preference unchanged, leaving the
Home column folded until a second click.
Split the intent at the shared writer: `exitFoldBand` marks entrances
that reorganize the layout away from split view, bypassing preservation,
and the rail Home handler uses it when the fold band was the overriding
state at click time. Taps that stay in the fold (Cmd/Ctrl+B, the rail
Collapse/Expand button) keep their preference protection untouched, and
the write still never happens inside the mobile drawer, where
splitFoldedSidebar is forced false by construction — so the drawer case
is unaffected (drawer protection is preserved).
Pinned by a fourth arm in `does not invert the stored collapse
preference in the split-view fold band`: stored `true` at 1100px split
view, click `[data-testid="open-home"]` once, and the column is expanded
with the stored key `false`; dropping the bypass inverts that arm while
the three protected arms stay green.
* fix(web-shell): cover Channels and Live in the exit-split fold exception
Address maintainer P2 follow-up: the exitFoldBand carve-out applied only
to Home, so Channels and Live — whose `openPanel` call exits split view
through the web-shell page set (`setMainView('chat')`) the same way —
still had their restoresColumn write clamped when the fold band owned
the sidebar, leaving the section column folded until a second rail tap.
Extent the same bypass to those two entrances, with each entry's own
column-existing gate: Channels applies it only when channelSidebarEnabled
would actually produce a column (mirroring the rail's
channelNavigationEnabled rule, which still leaves the full-page channels
variant folded), and the Live handler inherits the liveSidebarEnabled
guard it's already defined under.
Pinned by two parallel cases beside the fold-band keyboard/click arms:
stored `true` at 1100px split view → one rail tap on `[data-testid=
"open-channels"]` (with `session_source_metadata`) and one on
`[data-testid="open-live"]` (with showLive) — each expands the column and
writes `false`; dropping both bypasses turns both cases red while the
protected Home arm stays green.
---------
Co-authored-by: 钉萁 <[email protected]>
Co-authored-by: qwen-code-dev-bot <[email protected]>
Co-authored-by: qwen-code-dev-bot <[email protected]>
Co-authored-by: Shaojin Wen <[email protected]>
71 KiB
Configuration Reference
Overview
This page collects every setting that affects the qwen serve daemon and its adapters: environment variables, CLI flags, settings.json keys, and programmatic options. Feature-specific pages link back here when they need cross-cutting configuration details.
CLI flags (qwen serve)
| Flag | Type | Default | Effect |
|---|---|---|---|
--hostname <host> |
string | 127.0.0.1 |
Bind address. Loopback values: any 127.0.0.0/8 address, localhost, ::1, [::1]; localhost is resolved once and pinned, and trusted mode also verifies the actual listener address before startup completes. A non-loopback result always carries a bearer token: operator-supplied, or generated at startup when neither --token nor QWEN_SERVER_TOKEN is present — generation keys on the requested spelling, so a localhost that resolves off-loopback never generates, and boots only when a token source resolved (the refusal reads the resolved address), while a non-literal name that resolves to loopback generates and prints its bearer token-only. host:port input is rejected with guidance to use --port. |
--port <n> |
number | 4170 |
Listen port; 0 means ephemeral. |
--token <s> |
string | env | Bearer token. Overrides QWEN_SERVER_TOKEN and is trimmed at boot. It appears in the process command line, so prefer env in deployments. When neither this flag nor the env var is present, a non-loopback bind generates an ephemeral 128-bit base64url bearer (22 characters) and prints it once at startup; loopback spellings generate nothing. An explicitly empty value is a supplied source, not an absent one: it shadows the env var, so a non-loopback bind refuses to boot, and on loopback it selects the trusted token-less mode (or refuses under --require-auth). |
--open |
boolean | false |
Open the mounted Web Shell after runtime readiness. A resolved token (configured or generated) is delivered as a URL fragment. Bare --open remains a silent no-op when browser launch is ineligible. |
--open-with-auth |
boolean | false |
Open the Web Shell with bearer authentication on loopback. Requires an enabled Web Shell and built assets. Reuses a selected --token / QWEN_SERVER_TOKEN, or generates a process-lifetime 256-bit bearer before listen — that generated value is installed on the options token before boot, which makes this flag a third token source that satisfies --require-auth on loopback. In a browser-ineligible environment, starts and prints the secret-bearing fragment URL. Not a ServeOptions or SDK setting. |
--require-auth |
boolean | false |
Extends bearer auth to loopback and /health. Boot refuses to start when no token source resolves, which after the non-loopback generation step means a loopback bind: on a non-loopback bind the generated ephemeral token satisfies the flag, so its "no configured secret, no daemon" fail-fast is loopback-only. Loopback token sources are --token, QWEN_SERVER_TOKEN, and --open-with-auth. |
--workspace <dir> |
absolute path / repeatable | process.cwd() |
Startup workspace runtime; repeat to register additional isolated runtimes. The first is primary. Every value must be absolute and a directory; canonicalized at boot. |
--memory-project-scope <mode> |
git-root / workspace |
workspace |
Project-memory partitioning. workspace isolates by exact workspace directory; git-root is the legacy compatibility scope shared by workspaces at the same Git root. Overrides QWEN_CODE_MEMORY_PROJECT_SCOPE. |
--max-sessions <n> |
number | 32 |
Per-workspace active session cap. 0 / Infinity means unlimited; NaN / negative values throw. |
--max-total-sessions <n> |
number | 800, or derived at capacity 25 or less |
Daemon-wide active session cap. When omitted, it is 800 at registration capacities above 25 (including the default 256), even with one workspace. At capacities of 25 or less it is derived once from the per-workspace cap and the startup/restored workspace count, and one such workspace is unlimited. 0 / Infinity means unlimited. |
--max-pending-prompts-per-session <n> |
number | 5 |
Accepted but pending/running prompt cap per session. Excess prompt returns 503. 0 / Infinity means unlimited; negative or non-integer values throw. |
--max-connections <n> |
number | 256 |
HTTP listener server.maxConnections; 0 / Infinity means unlimited. |
--enable-session-shell |
boolean | false |
Enables direct POST /session/:id/shell execution. Effective with bearer auth or trusted-loopback authority; every call must carry a session-bound X-Qwen-Client-Id. |
--event-ring-size <n> |
number | 8000 |
Per-session SSE replay ring; soft cap is 1_000_000. |
--session-prompt-settled-close-grace-ms <n> |
non-negative integer | 0 |
Grace period after a prompt settles before an otherwise-idle session may be auto-closed (ms). Poll-based SSE clients use this window to reconnect without triggering a session rebuild. 0 = immediate close. |
--compacted-replay-max-bytes <n> |
positive integer | 4194304 |
Byte cap for the bounded in-memory replay snapshot returned by POST /session/:id/load; hard cap is 268435456. |
--max-journal-events <n> |
positive safe integer | 10000 |
Per-session baseline cap on in-flight liveJournal replay entries for the unfinished turn. Adaptive growth can raise it (see --max-journal-bytes); pinning either journal flag disables growth. |
--max-journal-bytes <n> |
positive safe integer | 8388608 (8 MiB) |
Per-session baseline byte cap on the in-flight liveJournal. When a turn breaches it, adaptive growth raises the session's caps on demand, toward double but limited by the remaining pool headroom and never past a 256 MiB per-session hard cap — within one daemon-wide pool of 5% of the effective --memory-budget-mb (capped at 1024 MB; 0 — growth disabled — when the effective budget is below the 1024 MB minimum), shared by every workspace bridge; without headroom the oldest entries are dropped with a history_truncated marker. Pinning either journal flag disables growth. |
--memory-budget-mb <n> |
integer in [1024, 1048576] |
50% of cgroup-constrained or host memory, capped at the flag maximum (1048576 MB) | Total memory budget for the daemon process tree, capped at resolved available memory. Reported under limits.memory in daemon status; it supplies the fixed child partition selected by --child-heap-mode and adaptive live-journal growth (see --max-journal-bytes), not a total RSS bound. Boot rejects out-of-range values. |
--memory-pressure-mode <mode> |
off | observe |
observe |
Whether the daemon derives a memory-pressure level from its own RSS and V8 heap. Both modes report runtime.memory.pressure; only observe raises daemon_memory_pressure. Root process only; no remediation. |
--child-heap-mode <mode> |
string | observe |
off publishes no partition; observe reports it without changing spawning; admit enforces the modeled child count; experimental opt-in enforce also applies the fixed per-child old-space ceiling. Admission may reclaim one eligible idle ACP from another trusted daemon-owned workspace, then retry once; live sessions and pending work are protected. If none qualifies or capacity remains full, the new child is rejected. Both admission modes require managed process wiring and a nonzero partition. enforce normalizes inherited fixed heap flags and rejects percentage flags, reports limits.memory.enforced: true, and requires workload calibration. Restart with admit to roll back; no mode bounds total RSS. |
--http-bridge |
boolean | true |
Stage 1 bridge mode. --no-http-bridge still falls back to http-bridge and prints to stderr. |
--mcp-client-budget <n> |
positive integer | unset | Sets WorkspaceMcpBudget.clientBudget and forwards it to the ACP child through childEnvOverrides. |
--mcp-budget-mode <m> |
off / warn / enforce |
warn when budget is set, otherwise off |
Sets WorkspaceMcpBudget.mode; enforce requires --mcp-client-budget. |
--external-tool-guard-mode <m> |
off / required |
off |
Enables the managed ACP external pre-execution Guard. required fails startup unless its loopback provider completes the v1 handshake. |
--external-tool-guard-endpoint <url> |
loopback HTTP(S) origin | unset | Provider origin used only in required mode. It must be origin-only and use 127.0.0.1, localhost, or ::1; paths, credentials, redirects, and proxy routing are rejected. |
--external-tool-guard-timeout-ms <n> |
integer 100..30000 |
3000 |
Per-handshake and per-prepare deadline. A timeout fails startup during the handshake or fails the invocation closed during a turn. |
--allow-origin <pattern> |
repeatable string | unset | Cross-origin allowlist that replaces the default CORS denial. Wildcard and non-loopback HTTP(S) origins require a resolved token, so on a non-loopback bind the generated ephemeral bearer satisfies both guards and the refusals are loopback-only; tokenless HTTP(S) origins must be loopback. |
--allow-private-auth-base-url |
boolean | false |
Allows /workspace/auth/provider to install localhost / private-network auth provider baseUrl; use only in trusted local development. |
--web / --no-web |
boolean | true |
Serve the built Web Shell SPA at the daemon root (GET /, /assets/*, and /session/:id, /plugins, /channels, /live, /scheduled-tasks, /goals, and /settings document navigations). These entry points are mounted before bearerAuth; API calls still follow configured bearer auth or trusted-loopback authority. --no-web leaves the daemon API-only. |
--prompt-deadline-ms <n> |
positive integer | unset | Server-side prompt wallclock limit in ms. Timeout aborts and returns an error. |
--writer-idle-timeout-ms <n> |
positive integer | unset | Per-SSE-connection idle timeout in ms. The daemon closes the SSE connection when no event is sent for this duration. |
--channel-idle-timeout-ms <n> |
non-negative integer | 0 |
ACP child auto-reap delay after runtime work drains. Plain preheat is preserved for first use. An explicit keepalive can extend the configured delay; the longer remaining delay wins. |
--initialize-timeout-ms <n> |
positive integer | 10000 |
ACP child startup deadline (channel factory + initialize handshake) and default request timeout (ms). |
--session-restore-timeout-ms <n> |
positive integer | 60000 |
ACP session load/resume timeout (ms). When this flag is omitted, an explicitly supplied initialize timeout raises the budget but never lowers it below the default. |
--permission-response-timeout-ms <n> |
non-negative integer | 0 |
Shared wall-clock timeout for ordinary permission and ask_user_question responses. 0 or an omitted flag waits indefinitely; a positive value enables the timer. |
--session-reap-interval-ms <n> |
non-negative integer | 60000 |
Session reaper scan interval; 0 disables it. |
--session-idle-timeout-ms <n> |
non-negative integer | 1800000 |
Disconnected-session idle reaping time; 0 disables it. |
--rate-limit / --no-rate-limit |
boolean | env / off | Enables per-tier HTTP rate limiting for prompt, mutation, and read routes. |
--rate-limit-prompt <n> |
positive integer | 10 |
Prompt request limit per window; requires rate limiting to be enabled. |
--rate-limit-mutation <n> |
positive integer | 30 |
Mutation request limit per window; requires rate limiting to be enabled. |
--rate-limit-read <n> |
positive integer | 120 |
Read request limit per window; requires rate limiting to be enabled. |
--rate-limit-window-ms <n> |
integer >= 1000 |
60000 |
Rate limit window length; requires rate limiting to be enabled. |
| no flag | - | - | QWEN_SERVE_NO_MCP_POOL=1 fully disables the pool. |
The Web Shell also exposes /manifest.webmanifest and /sw.js when --web
is enabled. They are public bootstrap resources; authenticated API routes keep
their configured bearer or trusted-loopback policy.
Environment variables
Read by runQwenServe / Express middleware
| Env | Effect |
|---|---|
QWEN_SERVER_TOKEN |
Bearer token; trimmed at boot. --token wins. An explicitly empty value counts as supplied rather than absent, so it resolves to no token — and --token '' likewise shadows a set value here. When neither this variable nor --token is set, a non-loopback bind generates an ephemeral bearer and prints it once; the daemon never writes this variable back into the environment. |
QWEN_SERVE_DEBUG |
1 / true / on / yes (case-insensitive) enables verbose stderr logs. See 19-observability.md. |
QWEN_SERVE_NO_MCP_POOL |
1 disables the workspace MCP transport pool and falls back to per-session McpClientManager; capabilities stop advertising mcp_workspace_pool / mcp_pool_restart. |
QWEN_SERVE_PROMPT_DEADLINE_MS |
Env fallback for --prompt-deadline-ms. |
QWEN_SERVE_WRITER_IDLE_TIMEOUT_MS |
Env fallback for --writer-idle-timeout-ms. |
QWEN_SERVE_RATE_LIMIT |
1 / true enables per-tier HTTP rate limiting; CLI --rate-limit / --no-rate-limit wins. |
QWEN_SERVE_RATE_LIMIT_PROMPT |
Env fallback for --rate-limit-prompt. |
QWEN_SERVE_RATE_LIMIT_MUTATION |
Env fallback for --rate-limit-mutation. |
QWEN_SERVE_RATE_LIMIT_READ |
Env fallback for --rate-limit-read. |
QWEN_SERVE_RATE_LIMIT_WINDOW_MS |
Env fallback for --rate-limit-window-ms. |
QWEN_SERVE_NEW_FILE_MODE |
New-file mode policy for daemon text writes: owner (default — NEW files are created 0600, umask-independent) or system (NEW files follow 0o666 & ~umask). Case-insensitive; the literal 0600 is accepted as an alias for owner (no other octal modes are supported), and unrecognized values warn on stderr and keep the 0600 default. Existing files always preserve their mode. See qwen-serve.md — New-file mode for agent text writes. |
QWEN_SERVE_SESSION_ATTACHMENTS_ROOT |
Overrides where session attachments are stored; reads/removes that miss the configured root fall back to the default runtime temp dir so pre-switch attachments stay readable. Accepts an absolute path, a path relative to the daemon cwd, or ~ / ~/…. See qwen-serve.md — Session attachment storage. |
QWEN_CODE_MEMORY_PROJECT_SCOPE |
workspace keys project memory by the exact workspace dir; git-root selects the legacy shared scope. When unset, the daemon injects workspace; unrecognized values warn once and retain the legacy git-root behavior. Propagates via the runtime base env, not childEnvOverrides; --memory-project-scope wins. Each workspace remember/forget/dream lane caps pending tasks at MAX_PENDING = 16; N workspaces allow up to 16·N queued tasks with no daemon-wide cap. |
Blank QWEN_CODE_MEMORY_PROJECT_SCOPE values are treated as unset and therefore default to workspace; unrecognized non-empty values still warn once and retain the legacy git-root behavior.
Read by the qwen serve CLI wrapper
| Env | Effect |
|---|---|
QWEN_CODE_EXTERNAL_TOOL_GUARD_TOKEN |
Non-blank bearer token of at most 8192 UTF-16 code units without control characters, copied into ServeOptions.externalToolGuard only in required mode. The CLI then deletes the ambient value before runtime environments are frozen; ACP children, channel workers, and executor environments also scrub it defensively. |
Forwarded to the ACP child through BridgeOptions.childEnvOverrides
runQwenServe builds these per handle so two daemons in one process do not race on process.env. The budget variables are not parent-process env fallbacks for qwen serve; the CLI path must generate them from --mcp-client-budget / --mcp-budget-mode.
| Env | Effect |
|---|---|
QWEN_SERVE_MCP_CLIENT_BUDGET |
Positive integer string consumed by the ACP child's readBudgetFromEnv(). |
QWEN_SERVE_MCP_BUDGET_MODE |
off / warn / enforce. |
QWEN_SERVE_MCP_POOL_TRANSPORTS |
Comma-separated transport allowlist; default pooled transports are stdio,websocket; can explicitly include http,sse. |
QWEN_SERVE_MCP_POOL_DRAIN_MS |
Pool entry idle drain delay; default 30000, clamped to 1000..600000 ms. |
Read by SDK / adapters
| Env | Effect |
|---|---|
QWEN_DAEMON_URL |
Daemon base URL for CLI TUI adapter, channels, and IDE companion. |
QWEN_DAEMON_TOKEN |
Bearer token. |
QWEN_DAEMON_WORKSPACE |
Overrides the cwd sent to POST /session. |
settings.json keys
The daemon constructs each workspace runtime from that workspace's merged settings and environment overlay. Process-global listener/auth options are resolved once, while runtime-specific services and ACP children receive the owning runtime snapshot. Malformed settings follow the documented startup fallback or failure behavior for the affected runtime; they must not cause another workspace's settings to be reused.
| Key | Type | Effect |
|---|---|---|
policy.permissionStrategy |
'first-responder' | 'designated' | 'consensus' | 'local-only' |
Sets BridgeOptions.permissionPolicy; the active value appears in /capabilities as policy.permission. Boot validates through validatePolicyConfig() against SERVE_CAPABILITY_REGISTRY.permission_mediation.modes. Unknown literals throw InvalidPolicyConfigError and fail boot explicitly. |
policy.consensusQuorum |
positive integer | N for the consensus policy. Default is floor(M/2) + 1 over votersAtIssue.size (M=2 means unanimous; larger even M means more than half). If set under a non-consensus policy, it is ignored and boot prints a stderr warning. Non-positive integers throw InvalidPolicyConfigError. See 04-permission-mediation.md. |
context.fileName |
string | Workspace memory filename. qwen serve snapshots it through extractContextFilename() and passes it to the workspace service as contextFilename; POST /workspace/init writes that file. |
tools.disabled |
string[] | Tools disabled for the next ACP child spawn. Normalized through normalizeDisabledToolList() (packages/cli/src/config/normalizeDisabledTools.ts): non-array becomes [], non-string entries are skipped, whitespace is trimmed, empty entries are dropped, and duplicates are removed while preserving first occurrence. Boot and restartMcpServer settings refresh both run through this function. ToolRegistry.has(name) is exact and case-sensitive. POST /workspace/tools/:name/enable and tool_toggled update this key. |
tools.approvalMode |
'default' | 'auto' | ... |
Default session approval mode; POST /session/:id/approval-mode writes here when persist: true. |
telemetry |
object | OTel config. Keys include enabled, otlpEndpoint, otlpProtocol, otlpTracesEndpoint, otlpLogsEndpoint, otlpMetricsEndpoint, target, outfile, userId, includeSensitiveSpanAttributes, sensitiveSpanAttributeMaxLength, resourceAttributes, and metrics.includeSessionId. resolveTelemetrySettings() reads it at boot and initializes initializeTelemetry(). userId is process-wide and must not be configured as end-user identity when the daemon serves multiple users. |
ServeOptions (programmatic embedding)
packages/cli/src/serve/types.ts defines the typed options passed through the public serve APIs. It mirrors the CLI flags above and adds:
| Field | Effect |
|---|---|
eventRingSize |
Overrides the default per-session ring size. |
sessionPromptSettledCloseGraceMs |
Grace period after a prompt settles before an otherwise-idle session may be auto-closed. 0 = immediate close. |
memoryProjectScope |
runQwenServe only; precedence is option, launch env, then workspace. Direct createServeApp callers use deps.daemonEnv. |
maxPendingPromptsPerSession |
Pending prompt cap per session; 0 / Infinity means unlimited. |
mcpPoolActive |
Programmatic switch, defaulting from QWEN_SERVE_NO_MCP_POOL. |
externalToolGuard |
Optional {mode:'required', endpoint, token, timeoutMs?}. Omission is fully off; required mode performs the provider handshake before listening. |
allowOrigins |
Cross-origin allowlist (string[]), corresponding to --allow-origin. |
allowPrivateAuthBaseUrl |
Allows private / localhost auth provider baseUrl installation. |
serveWebShell |
Serve the built Web Shell SPA at the daemon root (default true); false (the CLI's --no-web) leaves the daemon API-only. No effect when the build omits the shell assets. |
enableSessionShell |
Enables session shell execution; bearer auth or trusted-loopback authority and a session-bound client id are still required. |
promptDeadlineMs |
Prompt wallclock limit. |
writerIdleTimeoutMs |
SSE writer idle timeout. |
channelIdleTimeoutMs |
ACP child auto-reap delay after runtime work drains. Plain preheat is preserved for first use; active keepalive windows may extend the delay. |
initializeTimeoutMs |
ACP child request timeout, including the initialize handshake. |
sessionRestoreTimeoutMs |
ACP session load/resume timeout. Precedence: explicit restore value; otherwise an explicit initialize value raises the 60000 default but never lowers it; otherwise 60000. |
sessionReapIntervalMs |
Session reaper scan interval. |
sessionIdleTimeoutMs |
Disconnected-session idle reaping time. |
rateLimit* |
Per-tier HTTP rate limit switch, thresholds, and window. |
BridgeOptions (programmatic bridge embedding)
packages/acp-bridge/src/bridgeOptions.ts defines bridge options. See 03-acp-bridge.md for the full table. Key fields:
| Field | Effect |
|---|---|
boundWorkspace |
Required canonical workspace. |
sessionScope |
'single' (default) vs 'thread'. |
initializeTimeoutMs, sessionRestoreTimeoutMs, maxSessions, eventRingSize, permissionResponseTimeoutMs, maxPendingPermissionsPerSession |
Bounded resource caps. permissionResponseTimeoutMs is shared by ordinary permissions and questions; 0 or omission disables its timer. |
channelFactory |
Pluggable ACP child factory; default is defaultSpawnChannelFactory. |
fileSystem |
BridgeFileSystem adapter. See 07-workspace-filesystem.md. |
permissionPolicy, permissionConsensusQuorum, permissionAudit |
Mediator wiring. |
statusProvider |
Daemon-host preflight cells. |
childEnvOverrides |
Per-handle environment additions or removals. |
externalToolGuard |
Optional daemon-side handler for the private child-to-parent prepare RPC. The bridge validates channel ownership and the active Prompt before and after it calls the handler. |
channelIdleTimeoutMs |
ACP child auto-reap delay after runtime work drains. Plain preheat is preserved for first use; active keepalive windows may extend the delay. |
Web Shell workspace creation deadlines
In the common case, workspace creation makes a capability preflight on a cold or expired cache, followed by session creation. Each request has its own default 30-second timeout, including response-body consumption. Web Shell allows 75 seconds for the combined creation action, covering these two request budgets plus 15 seconds of headroom. A 20-second preflight followed by a 15-second create therefore succeeds without configuration changes. A concurrent capability refresh can supersede the preflight and extend the chain; the action may then time out before creation settles even when each request stays within its own deadline.
The 75-second limit also bounds transports that do not settle after SDK cancellation. It limits the action's wait rather than guaranteeing transport cancellation; successful results arriving after that limit are detached. Both initial workspace creation and creation with an existing session use this limit. SDK standalone creation, other actions, and post-creation callbacks retain their existing deadlines.
Increasing --initialize-timeout-ms does not raise the SDK request timeout for
the capability preflight or the create request. Load/resume follows the separate
restore timeout contract:
automatic SDK derivation requires a cached server restore budget; without one it
falls back to 70 seconds. Explicit request or client timeouts override that
derivation and can shorten the budget. See the
serve protocol reference for the SDK and
Web Shell restore headroom.
Direct SDK consumers can configure
fetchTimeoutMs; Web Shell providers
do not expose this option. See the
Web Shell timeout reference
for creation and callback limits.
The following controlled HTTP test shows the previous 30-second action deadline and the 75-second deadline with identical response delays. It exercises the actual SDK and workspace actions, not a rendered Web Shell or real daemon.
Important defaults
| Constant | File | Value | Meaning |
|---|---|---|---|
DEFAULT_MAX_SESSIONS |
bridge.ts |
32 |
Session cap before SessionLimitExceededError. |
MAX_EVENT_RING_SIZE |
bridge.ts |
1_000_000 |
Soft cap for BridgeOptions.eventRingSize; guards against typos. |
DEFAULT_RING_SIZE |
eventBus.ts |
8000 |
Per-session SSE replay ring depth. |
DEFAULT_MAX_QUEUED |
eventBus.ts |
256 |
Per-subscriber queue cap. |
DEFAULT_MAX_SUBSCRIBERS |
eventBus.ts |
64 |
Per-bus subscriber cap. |
WARN_THRESHOLD_RATIO |
eventBus.ts |
0.75 |
slow_client_warning trigger. |
WARN_RESET_RATIO |
eventBus.ts |
0.375 |
Hysteresis re-arm threshold. |
DEFAULT_INIT_TIMEOUT_MS |
bridge.ts |
10_000 |
ACP initialize handshake timeout. |
MCP_RESTART_TIMEOUT_MS |
bridge.ts |
300_000 |
Bridge timeout for /workspace/mcp/:server/restart. |
DEFAULT_PERMISSION_TIMEOUT_MS |
bridge.ts |
0 |
Shared permission and question wallclock; 0 disables the timer. |
DEFAULT_MAX_PENDING_PER_SESSION |
bridge.ts |
64 |
Aligned with DEFAULT_MAX_SUBSCRIBERS. |
MAX_RESOLVED_PERMISSION_RECORDS |
permissionMediator.ts |
512 |
FIFO for recently resolved permissions. |
KILL_HARD_DEADLINE_MS |
spawnChannel.ts |
10_000 |
Per-channel graceful shutdown window. |
SHUTDOWN_FORCE_CLOSE_MS |
run-qwen-serve.ts |
5_000 |
HTTP server force-close timer. |
MAX_READ_BYTES |
fs/policy.ts |
256 * 1024 |
Full-snapshot and returned-text cap; larger UTF-8 text requires a finite line limit. |
MAX_WRITE_BYTES |
fs/policy.ts |
5 * 1024 * 1024 |
Write cap. |
MAX_DISPLAY_NAME_LENGTH |
bridge.ts |
256 |
Session displayName cap. |
Cross-references
- Auth settings:
12-auth-security.md - Capabilities and protocol version:
11-capabilities-versioning.md - Event ring and backpressure tuning:
10-event-bus.md - MCP pool / budget:
05-mcp-transport-pool.mdand06-mcp-budget-guardrails.md - Permission policy:
04-permission-mediation.md - User operations guide:
../../users/qwen-serve.md
