* feat: correlate native search outcomes in audit history
Metadata-only audit ledger for agent runs and tool actions in the shared
state DB: stable event identity, closed action/status/error vocabularies,
one-way-hashed tool-call ids, never-inferred terminal outcomes for native
web-search (explicit completed/failed only; otherwise unknown), bounded
retention, audit.list gateway RPC and openclaw audit CLI. Squashed from
the 82-commit audit stack for replay onto current main.
* feat(audit): add audit.enabled config gate (default on)
The metadata-only audit ledger records by default: an audit trail enabled
only after an incident cannot explain the incident, and the rows are
strictly less sensitive than the transcripts every install already
stores. audit.enabled=false stops new writes at the gateway subscription
seam; audit.list and openclaw audit keep serving existing records until
they expire. Documented in the configuration reference, protocol page,
and CLI reference.
* fix: repair full-matrix CI findings after rebase
- break the dynamic-tools/dynamic-tool-execution import cycle by
extracting resolveCodexToolAbortTerminalReason into a leaf module
- restore main's session-worktree protocol exports lost in the
index.ts auto-merge
- register the audit event writer worker as a knip entry point
- docs table formatting; subagent wait-cancellation test scoped to its
audit intent (outcome + timing) and advanced past main's new
lifecycle-timeout retry grace
Centralized managed worktrees under <state-dir>/worktrees/<repo-fingerprint>/<name>
with branch-per-task (openclaw/<name>), .worktreeinclude provisioning, an optional
.openclaw/worktree-setup.sh repo hook, and a SQLite registry in the shared state DB.
Removal always snapshots the tree (untracked included, gitignored excluded) to
refs/openclaw/snapshots/<id>; restore rebuilds the branch at the original commit with
the snapshot content as uncommitted state. Lossless run-end cleanup, 7-day idle GC for
run-owned worktrees (manual exempt), orphan reconciliation, 30-day snapshot retention.
Surfaces: worktrees.* gateway RPC (operator.admin mutations), openclaw worktrees CLI,
Control UI page, plugin-SDK facade + Workboard kind:"worktree" materialization.
E2E-verified on Testbox: full create->work->remove->restore->gc lifecycle.
* feat(crestodian): AI-first conversational onboarding with typed-op guardrails
Interactive `openclaw onboard` (and bare `openclaw` on a fresh install) now
opens the Crestodian conversation: detection-backed first-run proposal
(Claude Code/Codex logins, API keys), persona AI turns for every free-form
message (configless local-runtime fallback, 60s deadline, deterministic
degradation), approval-gated typed operations, chat-hosted channel setup
(`connect <channel>`), config get/schema read ops with secret redaction, and
a post-write validation hook that feeds schema errors back for a self-fix
turn. Adds the additive gateway `crestodian.chat` method so app clients run
the same conversation. Classic wizard stays behind --classic/explicit flags;
non-interactive automation unchanged; `--modern` becomes a deprecated alias
for `openclaw crestodian`.
* feat(macos): Crestodian chat onboarding and importance-ordered permissions
Replace the gateway step-wizard page with a Crestodian chat over the new
crestodian.chat method (works before any model auth exists), sort the
permissions page by importance with no scrolling, drop the redundant manual
refresh, and bump the onboarding version.
* feat(crestodian): run the custodian on the real agent loop with a ring-zero tool
Crestodian conversations now execute through the same embedded agent runner
as regular agents: a persistent agent session with a single construction-gated
`crestodian` tool wrapping the typed operations (read actions free; mutations
require approved=true asserted from explicit user consent, audited, with
post-write config validation fed back into the loop). The engine prefers the
loop (configured models or the Codex app-server fallback) and degrades to the
single-turn planner, then to deterministic commands. Setup approval seeds the
crestodian exec approval so local model harnesses can run; the configless
Codex backend config now enables exec and direct tool loading (it was
dead-on-arrival behind tools.exec.mode=deny and the tool-search index).
* test(crestodian): type the engine mock signatures for the core test lane
* fix(crestodian): map the advertised create_agent tool action
* fix(crestodian): host-verified approval arming and a macOS setup completion gate
Review findings: the model-supplied approved flag alone could authorize
ring-zero mutations (prompt injection / model error), and removing the macOS
wizard gate let users Next past the Crestodian page with nothing configured.
Mutating tool actions now also require host-verified consent (the engine arms
approval only when the user's actual message is an explicit yes), and local
macOS onboarding blocks advancing until setup authored the config, using the
same signal the old step wizard checked.
* fix(crestodian): bind approval to the exact proposed operation and gate dot navigation
A generic yes no longer authorizes arbitrary mutations: denied mutating tool
calls register a canonical operation fingerprint (host-owned, per session),
and an armed turn executes only the identical call, once. The denial message
is arming-aware so the approved turn self-heals in one roundtrip, and the
agent protocol pre-registers proposals. macOS onboarding page dots now honor
the same setup-completion gate as the Next button.
* fix(crestodian): redact sensitive wizard answers, skip logged-out CLIs, gate programmatic advance
Sensitive channel-wizard answers (tokens, passwords) are redacted from the
AI-visible conversation history; setup and the onboarding welcome never pick
or advertise a definitively logged-out CLI as the model; and macOS
handleNext() honors the page gates for programmatic callers (chat handoff)
just like the Next button.
* fix(crestodian): align the onboarding welcome's configured predicate with the app gate
A valid config carrying only a default model (partial/hand-written) now still
gets the first-run proposal instead of the ready guide, so the macOS setup
gate can always be satisfied from the conversation.
* fix(crestodian): armed turns can never mint their own executable proposal
An approval-mismatched call inside an armed turn no longer re-registers and
invites a retry (which let the model swap the approved operation for another
in the same turn); it voids the approval entirely and requires a fresh yes.
Proposals register only in unarmed turns, which the agent protocol already
does when proposing.
* fix(onboard): route any explicit setup flag to the classic wizard
* fix(ci): satisfy new lint rules, tool-display guard, and generated artifacts for crestodian
* chore(i18n): refresh native inventory after permissions copy wrap
* fix(crestodian): harden conversational onboarding
* docs(crestodian): document conversational onboarding
* test(crestodian): type embedded runner mock
* fix(crestodian): close onboarding security gaps
* chore: retrigger ci
* fix(cli): shell completion omitted command aliases like capability, chat, and cron create
* fix(cli): route the dead exec-approvals root alias and single-source alias path expansion
* fix(cli): complete nested aliases in Bash
Co-authored-by: Jack-dev-ops <chen.zegui@xydigit.com>
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Co-authored-by: Jack-dev-ops <chen.zegui@xydigit.com>
* feat: add session thread management
Squash of codex/thread-management (025aefc3ad1) onto origin/main:
pin/archive/rename sessions via sessions.patch, archived-aware
sessions.list, lifecycle fencing, read-only archived chat, SDK +
Swift protocol support, Control UI session management.
* refactor(ui): minimal session rows with hover-revealed management
Chat picker and sidebar recents share session-row primitives: single-line
rows, relative timestamps, rename/archive/pin revealed on hover or focus,
accent pin badge for pinned rows, and an active-run spinner in the trail
slot. Sidebar floats pinned sessions above recency via the shared
comparator and gains archive/pin actions through the unified sessions-view
patch fallback. Archive eligibility is one shared policy
(canArchiveSessionRow); the sidebar/picker active-run tooltip now uses the
real sessionsView.activeRun locale key.
* fix: align session admission with mailbox-era main
Integration fixes after rebasing onto current main: sessions_list mailbox
test expectations learn the archived/pinned row fields and archived:false
list param; gateway agent admission treats a session as deleted only when
both the requested and canonical alias sets miss it (legacy bare-main
stores and exec-approval followups read under different spellings); cron
persist tests keep a consistent store across claim-guarded persist calls;
the ACP abort hook test asserts abort propagation instead of signal
identity; drop dead lifecycle writes flagged by no-useless-assignment and
fix the promise-executor return in the codex compact test.
* fix(qa): align UI e2e and shard fixtures with redesigned session rows
Sidebar session rows are wrapper divs with an inner link now: update the
navigation browser tests and chat-flow Playwright selectors. Seed a real
per-test session store for the auto-fallback admission guard instead of
depending on leftover host files at /tmp/sessions.json. Teach the
test-projects routing fixture about the suites that newly import the
shared temp-dir helper. Document the Codex thread-format contract for
archivedAt/pinnedAt (flag derived from server-stamped timestamp, epoch ms
here vs Codex epoch seconds) at the type and in the session docs.
* test: route auto-fallback suite through temp-dir helper plans
The auto-fallback suite now imports the shared temp-dir helper for its
seeded session store, so the top-level helper routing fixture must list
it in the auto-reply plan.
* feat(cli): openclaw attach — launch Claude Code bound to a gateway session with scoped MCP tools
* fix(cli): use token-only MCP config for attach
---------
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
Merges the Clownfish-repaired contributor branch for #91193. Clownfish preflight cleared security/comments/review, accepted pnpm check:changed, and the PR is clean/mergeable on head a05c170345.
Merges the Clownfish-repaired contributor branch for #93351. The latest repair preserves inline --message whitespace, adds --message-file coverage for gateway and local embedded runs, and the PR is clean/mergeable on head 4897f2fc20.
* feat(cli): add `sessions compact` command and fail loudly on CLI `/compact`
`sessions.compact` was reachable only as an internal Gateway RPC — no CLI
command, no docs — and `openclaw agent --message '/compact'` silently no-opped
with exit 0 because the slash-command handler rejects CLI-originated senders,
so the message fell through to an ordinary agent turn that compacted nothing.
- Add `openclaw sessions compact <key>` wrapping the existing `sessions.compact`
RPC; exit non-zero on a transport error or an `ok:false` payload so automation
never mistakes a silent no-op for success.
- Reject `openclaw agent --message '/compact'` with a redirect to the new
command and exit 1 instead of a silent exit 0. The shared chat-side `/compact`
handler is left untouched (no compatibility / message-delivery blast radius).
- Strictly validate `--max-lines` and `--timeout` (positive integers only).
- Document the command and the `sessions.compact` RPC in docs/cli/sessions.md.
Fixes#90640.
* fix(cli): inherit parent `sessions` options for `compact`
`openclaw sessions compact <key>` did not merge the parent `sessions`
command options the way its sibling subcommands (list/cleanup/info/…) do,
so a parent-level `--agent`/`--json` was silently dropped. In particular
`openclaw sessions --agent work compact <key>` compacted the default
agent's session instead of the work agent's — a wrong-target session-state
mutation.
Merge the parent options in the compact action (parent `--agent`/`--json`,
with the compact-level option taking precedence) and add regression
coverage for parent `--agent`, parent `--json`, and the compact-level
override.
Refs #90640.
* fix(cli): report pending Codex compaction and reject unsupported parent options
Address two ClawSweeper review findings on the `sessions compact` command:
- `sessions-compact.ts`: the Codex app-server `thread/compact/start` path
returns `ok:true / compacted:false` with a pending marker, meaning the
compaction was *started* asynchronously. The formatter collapsed every
non-compacted success into "No compaction needed", so Codex users were told
nothing happened. Report it as a started/pending compaction instead.
- `register.status-health-sessions.ts`: the parent `sessions` command defines
list-only options (`--store`/`--all-agents`/`--active`/`--limit`) that the
compact action previously ignored. Silently dropping a parent `--store` is
dangerous — the gateway resolves the target store itself, so a user could
believe they targeted one store while another is mutated. Reject any
unsupported inherited parent option with a clear error and a non-zero exit.
Add regression tests for the pending-compaction message and the rejected
parent options.
Refs #90640.
* fix(gateway): guard sessions.compact maxLines truncation against active runs
The non-maxLines (LLM) compact branch interrupts an active session run before
compacting, but the maxLines truncate branch read the tail, archived, and
overwrote the transcript in place without that guard. Exposing `--max-lines`
as a documented CLI command (this PR) would make the active-run data-loss mode
tracked by #72765 easy to trigger from ordinary CLI usage.
Run the same interruptSessionRunIfActive guard in the maxLines branch before
reading the tail and truncating, matching the LLM compact path. Add gateway
regression coverage over a real in-process Gateway: with no active run, the
maxLines branch truncates the on-disk transcript 500 -> 50 and preserves the
original 500 lines in the .bak archive; with an active embedded run, the
maxLines branch fires the same interrupt (abort + wait-for-end) before
archiving and truncating.
* docs(cli): move sessions compact section above related links
The new "Compact a session" section was inserted between the cleanup
section's inline "Related:" list and the page's final "## Related"
block, splitting related-link content around the command docs. Move the
compact section above the related-links area and merge the orphaned
"Session config" link into the single final "## Related" block.
* fix(gateway): avoid no-op compact aborts
Signed-off-by: sallyom <somalley@redhat.com>
* fix(gateway): satisfy compact preflight lint
Signed-off-by: sallyom <somalley@redhat.com>
* fix(sessions): preserve compacted transcript structure
---------
Signed-off-by: sallyom <somalley@redhat.com>
Co-authored-by: sallyom <somalley@redhat.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Summary:
- The PR adds descriptor-backed CLI command suggestions for unknown root commands, wires them into Commander parse errors and early unowned-root diagnostics, and covers both paths with focused CLI tests.
- PR surface: Source +104, Tests +71. Total +175 across 5 files.
- Reproducibility: yes. for the behavior gap: current main's formatter and early unowned-root path emit generic diagnostics without closest-command hints, and the PR proof shows the after-fix CLI output.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: suppress suggestions for plugin policy diagnostics
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into fix/83999-cli-command…
- PR branch already contained follow-up commit before automerge: test: align agent model expectations
- PR branch already contained follow-up commit before automerge: test: restore unrelated agent test fixture
Validation:
- ClawSweeper review passed for head b98f5b59e6.
- Required merge gates passed before the squash merge.
Prepared head SHA: b98f5b59e6
Review: https://github.com/openclaw/openclaw/pull/91345#issuecomment-4646215016
Co-authored-by: Glenn-Agent <glenn_agent@163.com>
Archive the canonical legacy database before SQLite sidecars, then detect and finish pending sidecar cleanup on retry without reopening the migrated database.
Reparse nested lazy commands from the Commander root so unknown options keep the original argv and exit non-zero. Adds nested lazy-command coverage for the root rawArgs path. Fixes#92069.
* feat(imessage): always-on inbound recovery, deprecate catchup
Replaces the opt-in catchup subsystem with always-on inbound replay
protection that brings iMessage in line with the other channels, and
fixes#89237 (stale backlog dispatched as fresh after bridge recovery).
- New inbound-dedupe.ts: persistent claimable GUID dedupe (claim/commit/
release) plus a stale-backlog age fence that suppresses live rows whose
send date is materially older than arrival (logged, never silent).
- monitor-provider: claim at ingestion, carry the exact claimed key on the
debouncer entry, commit on successful flush / release on dispatch failure
(per-unit so a coalesced bucket cannot strand a sibling claim). Keeps the
local startup since_rowid watermark so startup-window rows are not skipped.
- Deprecate catchup: delete catchup.ts + catchup-bridge.ts, remove the
channels.imessage.catchup schema, cursor migration, and config-guard nag.
Back-compat: strip the retired key before validation; new imessage doctor
contract reports + removes it on doctor --fix.
- Docs updated for the new recovery model.
Net -947 prod LOC.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(imessage): recover downtime messages via since_rowid replay
Builds downtime recovery on the new inbound dedupe instead of restoring the
old catchup subsystem. On startup the monitor passes the last dispatched rowid
(a persisted per-account cursor) to imsg watch.subscribe as since_rowid, so imsg
replays the messages that landed while the gateway was down, then tails live.
The GUID dedupe drops anything already handled, so no cursor/retry bookkeeping
is needed.
- recovery-cursor.ts: minimal persisted per-account lastDispatchedRowid.
- monitor-provider: since_rowid = cursor (capped to the most recent
IMESSAGE_RECOVERY_MAX_ROWS); split the age fence on the startup rowid boundary
so replayed rows (<= boundary) use the wider recovery window and live rows
(> boundary) keep the tight #89237 fence; advance the cursor on commit.
- Local only: remote SSH cliPath cannot read chat.db, so it tails from the
current rowid (suppress-and-move-on) as before.
Restores missed-message recovery that the catchup removal dropped, with no
config and a fraction of the old LOC.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(imessage): make recovery cursor advance failure- and suppression-safe
Addresses two cursor-state regressions in the downtime-recovery path:
- Failed replay rows could be skipped forever: a released (failed) row keeps
its dedupe claim for retry, but a later successful row in the same flush
advanced the cursor past it, so the next startup's since_rowid skipped it.
Hold a per-session floor at the lowest released rowid and never advance the
cursor past it.
- Suppressed live backlog could be re-delivered after a restart: a live row
suppressed under the tight live fence was not recorded, so after a restart it
fell under the wider recovery window (its rowid now below the new boundary)
and was delivered. Commit its dedupe key on suppression so the recovery
replay treats it as already handled.
Both caught by Codex autoreview. Adds regression tests for the floor and the
suppression record.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(imessage): bound the GUID-less replay key length
Hash the composite fallback key's variable parts (conversation, sender,
created_at, text) so the key is length-bounded regardless of message text.
The persistent dedupe store already hashes keys internally, so this was not a
live overflow, but the bounded key removes the dependency on that and keeps the
fallback fail-open. Flagged by autoreview.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(imessage): recover downtime messages on remote cliPath setups too
The since_rowid replay runs over the imsg RPC client, so driving it from the
persisted recovery cursor (not the local chat.db boundary) makes downtime
recovery work for remote SSH cliPath gateways — the topology the old RPC-based
catchup served and that the rowid-boundary-only version regressed. Local setups
keep the wider, capped recovery window via the chat.db boundary; remote uses the
live age-fence window. Flagged by autoreview.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(imessage): seed recovery cursor from retired catchup cursor on upgrade
A one-time, self-cleaning migration: when the recovery cursor is empty on the
first startup after upgrade, seed it from the retired imessage.catchup-cursors
lastSeenRowid and consume the legacy entry. Without this a user who had catchup
enabled would not replay messages missed across the upgrade restart. Flagged by
autoreview.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(imessage): preserve catchup recovery on upgrade
---------
Co-authored-by: Omar Shahine <10343873+omarshahine@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Fix live model inference edge cases across provider streaming, model switching, outbound delivery, and gateway tool resolution.
Includes live/provider issue fixes and leaves #89100 explicitly partial for the remaining FM-2 group routing case.
* refactor: move imessage monitor state to sqlite
* test: use OpenClaw temp root in iMessage state helper
* test: avoid pending promise lint in chat tests
* test: harden gateway ci flakes
* test: align session list merge expectation
Move Telegram plugin-local state from JSON sidecars into plugin-state SQLite. Keep legacy JSON handling in startup and doctor migration plans, with runtime state now reading and writing SQLite directly. Stabilize the channel Vitest lane by cleaning up typing timers and isolating that lane.
Extract shared normalization/coercion helpers into private @openclaw/normalization-core workspace package while preserving existing plugin SDK helper subpaths.\n\nAlso keeps direct normalization-core imports internal, wires UI/build/loader resolution, and replaces the slow PR network CodeQL lane with a fast added-line boundary scan while retaining full CodeQL for scheduled/manual runs.\n\nVerification: local moved tests, plugin SDK boundary tests, extension loader tests, agents-support shard, UI build/test, build artifacts, lint, workflow guards, autoreview, and GitHub CI passed on PR head 963d893715.
Adds `openclaw sessions tail` as an operator-facing progress view over session trajectory events, with conservative redaction for prompt text, tool arguments, and tool result bodies. The command supports explicit session keys, store/agent scope, follow mode, relocated trajectory pointer files, and cursor-safe follow across bounded trajectory window rewrites.
Documents the new sessions tail CLI surface in `docs/cli/sessions.md`.
Fixes#83441.
Co-authored-by: zhengzuo0-ai <zheng.zuo0@gmail.com>
