* fix(system-agent): keep inference available across routes
Accept provider-owned equivalent response model identities and route every new OpenClaw chat through the configured/authenticated inference fallback ladder. Malformed replies may fall through while provider/model and execution-owner uncertainty remain fail-closed.
Fixes#120711
* fix(system-agent): keep malformed fallback route-scoped
Continue to later configured routes from the same provider after empty or malformed model output. Timeout and unavailable results remain provider-wide, while owner and identity uncertainty remain fail-closed.
Addresses ClawSweeper P1 on #120712.
* fix(codex): pin catalog CODEX_HOME onto terminal resume spawns
The Codex session catalog lists threads through the plugin's supervision
app-server connection, which can run on the agent-scoped Codex home
(homeScope: "agent"). The terminal resume plan spawned a bare
'codex resume <threadId>' under the operator login shell, so the CLI
resolved its default ~/.codex and failed with "No saved session found".
Terminal plans now carry the catalog connection's CODEX_HOME (local and
paired-node paths), the gateway merges plan env into the PTY spawn, and
the triplicated home-scope resolution collapses into one shared
resolveCodexAppServerLocalHomeDir.
* feat(ui): add main-content terminal placement
The terminal panel gains a third dock placement, "main", filling the
content region next to the sidebar like the transcript pane. The panel
header gets a bottom/right/main placement switcher (persisted in the
existing openclaw.terminal.panel.v1 store), and opening a Codex/Claude
session from the session catalog selects main mode so resumed sessions
appear as a full window instead of a bottom strip.
Claim-owned cancellation now stops pre-adoption media hydration, allowing later same-chat messages to proceed. Webhook handling now uses the canonical Telegram adoption stall timeout.
Fixes#120704.
* fix(cloud-workers): honor Crabbox SSH fallback ports
Select a currently reachable advertised SSH endpoint before returning a Crabbox worker lease, while preserving fail-closed teardown. Allow deletion of failed cloud sessions only after the environment record proves the provider lease is gone, and align the Cloud Workers docs with the shipped configuration and Control UI flow.
* fix(cloud-workers): retry advertised SSH endpoints
Persist provider-advertised SSH fallback ports and retry them through the shared pinned transport used by bootstrap, tunnels, reconnects, and workspace transfers. Keep candidate selection provider-neutral, preserve identity and host-key fencing, and add the same-version SQLite column through the existing additive migration path.
* fix(crabbox): recheck SSH readiness after setup
Treat provider setup as a mutating lifecycle phase: refresh authoritative inspect state and wait for SSH readiness again before returning the lease. This prevents bootstrap from racing setup-triggered SSH restarts on fresh and replayed workers while preserving security attestation and fail-closed teardown.
* fix(cloud-workers): retry bootstrap transfers across ports
Use the shared advertised-port candidate runner for bundle transfer, install, and best-effort upload cleanup as well as preflight. This keeps fresh bootstrap connections on pinned identity and host-key semantics when a previously selected SSH port disappears between phases.
Proof passed: 517 focused tests (1 skipped), final autoreview/TruffleHog clean, targeted lint/format. Full check-changed reached the unrelated max-lines baseline drift on current origin/main: this branch's merge base contains ui/src/pages/chat/components/chat-model-controls.ts while current origin/main removed that baseline entry; do not touch the unrelated baseline.
* fix(cloud-workers): persist fallback ports compatibly
Create the fallback-port companion table lazily as an additive surface, preserving downgrade tolerance for binaries that still expect the older shared-state schema.
* fix(cloud-workers): preserve bundle artifact narrowing
Bind the immutable discriminated artifact before the SSH retry callbacks so bundle-only fields remain narrowed across fresh candidate invocations. Use the shared temp-directory owner in the tunnel fallback test for deterministic cleanup.
* fix(cloud-workers): retire deleted placements
Terminal placement rows retire by exact CAS after session deletion, and managed AWS docs now pin the Gateway SSH CIDR.
* fix(crabbox): await pending AWS attestation
missing authoritative metadata is pending only while the lease is non-ready; ready leases still require explicit false.
* fix(cloud-workers): fence remote command retries
require explicit idempotent/never classification; remote worker launch never retries after ambiguous SSH loss.
* fix(cloud-workers): bound SSH fallback operations
resolveMediaMaxBytes treated any number as an explicit cap, so
channels.matrix.mediaMaxMb: 0 became a literal 0-byte limit and every
outbound media send failed before upload, while inbound media on the same
account kept working because monitor/index.ts already floors the same field
with Math.max(1, mediaMaxMb).
Only a positive value is a cap now, matching CommonMediaMaxMbSchema; other
values fall through to the existing unset path (per-kind defaults). matrix
is one of three bundled channels that hand-roll this field without a range
constraint, so the config loads without complaint today.
Validate token response envelopes once in the shared parser used by authorization-code exchange and refresh. Prove null and array responses through both production entry points over real loopback HTTP.
Refs: #120174
Co-authored-by: 毛宇豪0668001457 <mao.yuhao@xydigit.com>
* perf(plugins): declare doctor contract surfaces
* perf(doctor): slim migration import closures
* perf(plugins): narrow doctor declaration record surface and wire owner-test lane
Registry records carry only the doctorContract declaration instead of the whole
parsed manifest, and check:changed now selects the src/plugins-owned declaration
honesty and closure-guard tests for extension module/manifest changes so
cross-lane drift cannot pass PR classification.
* fix(doctor): keep control-plane dist imports require-safe
Keep doctor and channel control-plane chunks off exec-class dependencies, and enforce native require(esm) loading during postbuild.
* chore(plugin-sdk): regenerate API baseline
* chore(plugin-sdk): sync export ordering
* fix(plugins): satisfy doctor contract CI boundaries
* perf(doctor): make qqbot doctor closure dependency-light
qqbot was the last plugin above 5s in doctor state-migration enumeration
(~8s under tsx/jiti). The cost was not the state-key builder (already a
leaf): its doctor closure value-imported the runtime-doctor SDK barrel,
whose plugin-state-store/state-db re-exports pull kysely (~330 modules),
plus security-runtime for one fileExists (~200 modules), all resolved
per-module by jiti during enumeration.
Split the migration-define helpers and light re-exports into a new
private-local plugin-sdk/runtime-doctor-migrations subpath; runtime-doctor
re-exports it so its public surface is byte-identical (API baseline hash
unchanged). qqbot's doctor-contract and state-migrations now import only
the light subpath, swapping fileExists for the equivalent async
legacyStateFileExists already in the closure.
qqbot enumeration: ~8.0s/531 modules -> ~0.25s/18 modules.
* chore(plugin-sdk): drop private-local subpath from API baseline
runtime-doctor-migrations is private-local-only; the baseline tracks public
modules, and the earlier line was generated before the classification.
* fix(plugins): register runtime-doctor-migrations boundary paths
The private-local subpath list feeds the extension package boundary map;
the shared paths config and xai's derived overrides must carry the same
entry or the boundary contract test fails.
listSlackDirectoryPeersLive/listSlackDirectoryGroupsLive hand-rolled
do/while loops with no repeated-cursor detection and no page bound,
while every other users.list/conversations.list consumer goes through
collectSlackCursorPages. A Slack API or proxy edge that keeps
returning the same non-empty next_cursor made directory queries
paginate forever, growing the member/channel arrays without bound.
Both loops now go through collectSlackCursorPages, which throws on a
repeated cursor and caps total pages.
* fix(browser): bound batch action nesting depth in act request normalization
normalizeActRequest recursed over batch nesting with no depth bound, so a
~1MB POST /act body with tens of thousands of nested batch levels parsed
fine and then crashed normalization with RangeError: Maximum call stack
size exceeded before the ACT_MAX_BATCH_ACTIONS count check could run,
surfacing an internal stack overflow as the 400 validation message.
Thread the existing ACT_MAX_BATCH_DEPTH limit through normalizeBatchAction/
normalizeActRequest and reject deeper nesting up front with a clear
'batch nesting exceeds maximum depth of 5' error, matching the bound the
Playwright executor already enforces at dispatch time.
* fix(browser): match batch depth executor boundary
Accept the six wrapper levels supported by the Playwright executor and reject the seventh during request normalization.
Co-authored-by: 万拥 0668000723 <wan.yong@xydigit.com>
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(matrix): ignore out-of-range hex escapes in env account tokens
decodeMatrixEnvAccountToken guarded String.fromCodePoint with
Number.isFinite, which does not bound the Unicode range: a MATRIX_*
env var whose _X<hex>_ escape exceeds 0x10FFFF (e.g.
MATRIX_A_X110000_B_HOMESERVER) threw RangeError out of
listMatrixEnvAccountIds, crashing discovery of every env-backed
Matrix account during startup and doctor checks. Escapes above the
Unicode max are now rejected like any other malformed token.
* chore(matrix): tighten decoder invariant comment
Co-authored-by: 万拥 0668000723 <wan.yong@xydigit.com>
* chore(matrix): clarify decoder invariant
Co-authored-by: 万拥 0668000723 <wan.yong@xydigit.com>
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(ai): preserve Responses server compaction state
Persist opaque Responses compaction items as fenced provider replay state so long stateless sessions can resume authoritative compressed history without exposing it in display or diagnostics. Carry state through worker transcripts and prune replay prefixes without splitting tool pairs.
Release note: Preserve long OpenAI Responses sessions across server-side compaction and worker restarts.
Related: #95788
* test(ai): align long-context fixtures with CI contracts
Make tool-result fixtures type-complete, use the canonical model selector helper, remove unused test-helper exports, and route the paid long-context live probe through the dedicated Gateway profile shard.
* test(ai): type mocked Responses terminal events
Give the mock SSE event collection an explicit open event shape so terminal response events coexist with output-item events under the root test typecheck.
* fix(ai): suppress rejected compaction replay
Persist a route-fenced suppression tombstone when encrypted-content recovery rejects a compaction item, so later turns do not retry the same opaque state. Preserve the tombstone through transcript redaction and cover successful fallback followed by the next turn.
* fix(ai): keep compaction suppression transport-private
Keep the suppression contract local to its sole Responses transport owner and make the regression fixture satisfy root type and lint checks without widening the Plugin SDK surface.
* refactor(ai): remove compaction suppression re-export
* fix(ai): scope compaction suppression to replay route
Keep foreign-route rejection tombstones from hiding the newest compatible Responses compaction while preserving same-route suppression.
* fix(ai): harden Responses replay recovery
Stage encrypted replay recovery so compaction is only suppressed after an attributable rejection. Preserve terminal ordering and keep provider replay within worker frame budgets without truncating opaque state.
* refactor(ai): centralize Responses output indexes
Keep normalized output identity tracking in the stream-slot owner, move response failure state to its diagnostic owner, and remove the obsolete replay clone export so exact-head static gates remain shrink-only.
* fix(ai): retain idless terminal tool identity
Use the canonical empty identity only when a provider supplies neither call nor item id, preventing terminal recovery from duplicating a done-only tool call while preserving stronger identities when available.
* fix(sessions): hide provider replay from public events
* fix(ai): stage encrypted replay recovery
* fix(ai): keep replay attempt kind internal
* fix(ai): route Azure through replay recovery
Use the shared encrypted-content retry owner for Azure Responses so compaction suppression and prompt-observer variants stay coherent across transports.
* fix(ai): harden replay persistence boundaries
Fence Azure replay by the resolved request endpoint, drop invalid replay during transcript sanitization, and surface worker-launch replay omissions through the existing redacted diagnostic path.
* fix(model-fallback): treat empty non-GPT completions as failed candidates (#120132)
Empty and whitespace-only completions from non-GPT models were counted as
candidate_succeeded, silently dropping the turn on visible channels. Apply
the empty/reasoning-only classification to every model; deliberate silent
replies and committed outbound deliveries remain successful.
* fix(model-fallback): classify mixed reasoning-plus-blank completions as failed (#120148)
A completion like [{ isReasoning: true, text: "thinking" }, { text: " " }]
carries no user-visible reply: reasoning text is invisible to the shared
visibility test (includeReasoningPayloads: false), so counting it as visible
made the run look successful and silently ended visible-channel turns.
Filter reasoning payloads out of the empty/whitespace predicate so mixed
reasoning-plus-blank results classify as empty_result (fallback-worthy),
while mixed reasoning-plus-visible-text results stay successful.
Regression tests: mixed reasoning+blank -> empty_result; mixed
reasoning+visible -> success.
* fix(model-fallback): require deliverable assistant results
Use one owner-boundary deliverability predicate for fallback classification, preserve intentional terminal outcomes, and add a mock-channel Gateway scenario for mixed reasoning-plus-blank recovery.\n\nCo-authored-by: 李琪0668001400 <li.qi16@xydigit.com>
* chore: preserve contributor credit
Co-authored-by: 李琪0668001400 <li.qi16@xydigit.com>
* test(qa): cover default model fallback scenario
Make the mixed reasoning-plus-blank fixture recover through both the catalog default alternate and the explicit proof model.
Co-authored-by: 李琪0668001400 <li.qi16@xydigit.com>
---------
Co-authored-by: licheer-zte <licheer-zte@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Resolve reply mode through the selected Telegram account so account overrides and top-level inheritance reach outbound reply context.
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
* fix(subagents): wake the parent when a follow-up finishes a yielded child
A sub-agent that calls sessions_yield on its own behalf parks its run and
correctly withholds the parent's announce. But a later follow-up to that same
child session registered a sibling registry row instead of continuing the paused
one, so the requester defaulted to the child's own main session and the original
parent — itself idle behind sessions_yield — was never woken. The paused row also
stayed an unsettled descendant, deferring the parent's settle batch forever with
nothing recorded explaining the silence.
Follow-up dispatch now adopts the paused row through the existing post-steer
replacement seam, inheriting the requester identity and carrying the settle-wake
credential forward with its frozen batch membership remapped to the new run id.
A follow-up that names its own requester keeps registering separately, since an
explicit requester is a delivery opt-in that adoption would silently drop.
Also stops frozen-result refill from targeting paused rows: a yield clears the
result on purpose, so refilling from the session would attribute a later turn's
text to the paused run.
Closes#120157
* fix(subagents): select the paused owner past a requester-bound sibling
Adoption looked up the newest run for the child session and adopted it only
when that row was itself paused. A requester-bound follow-up deliberately stays
a sibling, but it registers at a higher generation and becomes that newest row,
so any later default follow-up saw an unpaused newest row, declined adoption,
and registered yet another sibling. The original requester stayed parked behind
a paused row that can never announce -- the same silent stall this fix exists to
remove, reached through a valid mixed-delivery sequence.
The latest-run query now takes an optional predicate applied before the
generation comparison, so a caller that owns a specific row class selects the
newest row of that class. Adoption asks for the newest `sessions_yield` row
directly instead of inferring it from generation order.
Docs now state that continuation applies to default delivery, since a follow-up
carrying its own requester runs as a sibling by design.
* test(qa): prove post-yield follow-up delivery through the gateway boundary
The unit and gateway-method tests for paused-run adoption assert on registry
rows, which proves the bookkeeping but not that an operator ever sees the
result. This adds the boundary proof: a real gateway child, the QA mock channel,
and the mock provider driving a subagent that pauses itself and finishes only on
a later follow-up.
A fixture plugin owns both legs. Its `before_dispatch` hook spawns the child with
`completionDelivery: "current-requester"`, so the announce has the operator turn
as its audience. An HTTP route then dispatches the follow-up to that same paused
session using default delivery -- the path adoption is meant to catch. A
requester-bound follow-up would opt into its own audience and run as a sibling
instead, so the two legs must differ here.
The mock provider gains a child that yields on its own behalf. Both of its turns
match on the current prompt rather than the shared transcript, so the yielded
kickoff cannot make the follow-up turn yield a second time.
The scenario asserts both sides of the invariant: no outbound traffic while the
child is paused, and exactly one announce carrying the follow-up marker once it
ends.
Reverting the adoption call site fails this test in the way that matters: the
child still produces its marker and the run still ends with stopReason=stop, but
nothing reaches the requester and the wait times out. The result is computed and
then silently dropped -- which is the failure this repair exists to remove.
* fix(ci): match QA Lab fixture plugin entries as a group in knip
The all-exports pass listed one fixture entry by name, so every new QA Lab
fixture plugin lands as an unused file and turns check-dependencies red until
someone remembers this file. Nothing imports these entries by design: the
Gateway E2E loads them through plugin config paths.
* docs(subagents): scope yield continuation to plugin runtime follow-ups
Adoption is gated on plugin_subagent task tracking, which only
createGatewaySubagentRuntime().run sets, so api.runtime.subagent.run is the
sole route into it. Writing that as one example implied other follow-up paths
to a paused session continue the run too; they are not tracked as sub-agent
runs and announce nobody.
* fix(subagents): reject undurable paused-run adoption
Fail plugin follow-up admission closed when the paused-run ownership swap cannot be persisted, while retaining the existing restart-recovery return-false contract. Trim duplicate tests and keep boundary coverage for requester routing, wake-batch remapping, repeated yield, and persistence rollback.
Co-authored-by: zhou.huanfeng <woundfongv3@163.com>
* docs(subagents): clarify yielded-run steering
Co-authored-by: zhou.huanfeng <woundfongv3@163.com>
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Sarah Fortune