* fix(memory-wiki): preserve user edits when rolling back ChatGPT imports
Rollback deleted created pages and overwrote updated pages unconditionally,
destroying content the user added after the import with no recovery copy.
Import runs now record a content hash of each written page after vault
compile, and rollback preserves any page whose current content no longer
matches into the run's recovered directory before deleting or restoring.
Legacy run records without hashes preserve unconditionally.
Fixes#116457
* fix(memory-wiki): move pages aside atomically during rollback
Rollback now renames the live page into the recovery location before
inspecting it, so a concurrent external save cannot land between the
content read and the delete or snapshot restore. Matching pages drop
the moved copy; mismatching pages keep it as the recovery file.
* fix(memory-wiki): make rollback snapshot restore collision-safe
The snapshot restore wrote directly to the page path after the
move-aside, so a page recreated by an editor in that window was
overwritten with no recovery copy. Restore now creates the snapshot
exclusively and on collision moves the recreated page aside and
retries; recovery filenames are uniqued so a second move-aside cannot
clobber an earlier preserved copy.
* fix(memory-wiki): record rollback hashes at write time
* fix(memory-wiki): make ChatGPT rollback retry-safe
* fix(memory-wiki): fence ChatGPT rollback phases
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(voice-call): pin Twilio webhook verification to the configured public path
buildTwilioVerificationUrl overwrote the configured publicUrl path with the
incoming request path, so behind a path-rewriting reverse proxy the
reconstructed verification URL no longer matched the URL Twilio signed and
valid webhooks were rejected. Use the configured public path (keep the request
query), mirroring the Plivo sibling fixed in #112559. Restores callback-path
binding and adds proxy-prefix accept + local-path reject regression tests.
* fix(voice-call): pin Twilio verification to public URL path
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(ui): rename the Memory Palace browser to Memory Wiki and document it
* refactor(memory-wiki): drop the old memory-palace module files
* docs: refresh generated docs map
* test(ui): align dream-diary hub-tab assertion with the wiki sub-tab id
* docs: describe memory wiki clustering behavior accurately
* docs(memory-wiki): record the wiki.overview rename decision at the registration site
* test(ui): query the Agents channels hub tab by tab role after the hub-tabs refactor
* fix(codex): restore connected apps for token-authenticated runs
* fix(codex): keep app inventory protocol types private
* fix(codex): align native runtime with Codex 0.146.0
Co-authored-by: Steven Lee <stevenlee@openai.com>
* fix(codex): clean up latest app-server integration
Co-authored-by: Steven Lee <stevenlee@openai.com>
* fix(codex): keep internal protocol types private
* fix(ci): repair current main Codex landing gates
* fix(ci): format inherited code mode matrix
* fix(codex): reconcile native app-server contracts with main
Prepare a verified GitHub-hosted mainline merge while preserving the reviewed Codex 0.146.0 fixes and canonical OpenAI authentication.
Co-authored-by: Steven Lee <stevenlee@openai.com>
* fix(codex): keep QA evidence in its owning plugin
Resolve the current-main Code Mode test rename without resurrecting the retired core test path.
Co-authored-by: Steven Lee <stevenlee@openai.com>
* fix(codex): enforce canonical OpenAI app-server auth
Reject retired provider aliases without runtime compatibility, direct operators to the doctor migration, and remove the redundant OpenAI API-key predicate.
Co-authored-by: Steven Lee <stevenlee@openai.com>
* chore(codex): reconcile latest main dependency graph
Preserve current main dependency changes while preparing the original Codex PR for an ancestry-preserving signed mainline merge.
Co-authored-by: Steven Lee <stevenlee@openai.com>
* fix(codex): unify bundled Codex 0.146 runtimes
Keep the ACP adapter on the same 0.146.0 Codex release as the managed runtime, remove obsolete 0.145.0 platform artifacts and unused semver compatibility, and preserve the latest main dependency upgrades.
Co-authored-by: Steven Lee <stevenlee@openai.com>
---------
Co-authored-by: Peter Steinberger <peter@steipete.me>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Allow before_agent_reply plugins to declare host-enforced trigger eligibility so scheduled-only hooks do not block interrupted user-turn recovery. Keep omitted and malformed scopes fail-closed, scope both memory-core maintenance hooks, and cover three runner reload cycles through the public registration contract.
Refs: #111442
Source: #114836
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* feat(gateway): share the canonical browser-origin policy with plugins
Export resolveAcceptedBrowserOrigin through openclaw/plugin-sdk/webhook-request-guards
so browser-facing plugin routes reuse the Gateway's real origin contract instead of a
narrow allowedOrigins array check. Private LAN/Tailnet Control UI loads and the
Host-header fallback were previously rejected with 403 by plugin offer routes while the
Control UI itself worked.
Moves the loopback/forwarded-header helpers to net.ts (re-exported from auth.ts) so the
guard can delegate without importing gateway auth, and migrates the Codex realtime
broker onto the shared seam.
* feat(talk): let providers own agent delegation for realtime voice
Adds an optional runAgentConsult callback to the browser-session create request and
injects the existing embedded consult runtime from talk-client, bound to the same agent
and session key the GA tool path uses. Providers whose realtime protocol delegates work
through their own control channel (rather than GA function calls) can now reach the
OpenClaw agent without a client round-trip.
Threads the effective per-session model into browser-session capability resolution so a
request-level model override selects the right capability set, and propagates a caller
abort signal into consultRealtimeVoiceAgent so a superseded delegation stops its run.
* feat(openai): support GPT-Live realtime voice over ChatGPT OAuth
Implements OpenAI's quicksilver/frameless session natively for Talk browser sessions.
The Gateway creates the WebRTC call (multipart sdp+session to https://api.openai.com/v1/live)
and owns the sideband control socket, so the browser never holds upstream credentials;
delegation.created events run through the OpenClaw agent and stream back as speakable
context appends.
Verified end-to-end on 2026-07-28 against a ChatGPT Pro OAuth profile: call create 201
with an rtc_* id and answer SDP, sideband session.started, session.close teardown.
ChatGPT OAuth is preferred over a Platform API key because /v1/live access for platform
keys is waitlist-gated; the legacy chatgpt.com backend route returns 403 for every model
and protocol version and is not used.
Accepted models are gpt-live-1-codex and gpt-live-1-boulder-alpha; the voice allowlist is
the ten values the route actually accepts, since an invalid voice is rejected at call
creation and cannot be repaired afterwards (session.update reports immutable_field_update).
* docs: document GPT-Live Talk support and its route gotchas
Records the working route and auth, the accepted models and voices, the browser-only
scope, and the two traps that cost the most time: the chatgpt.com backend route returns
403 Voice session access denied for every model, and that same 403 is also what an
invalid voice returns, so it must not be read as an account entitlement block.
* fix(openai): resolve GPT-Live CI failures
* refactor(openai): own zod runtime dependency
* fix(openai): satisfy lint and live-shard gates for GPT-Live
Types the retry-delay finish callback as Error so the rejection reason is provably an
Error at the call site; the abort path already normalized a non-Error AbortSignal reason,
but the unknown parameter type hid that from static analysis.
Registers the new GPT-Live live test in the native-live-extensions-openai shard
expectation. The shard selector already picked the file up from the real tree; only the
hardcoded list in the tooling test lagged.
* fix(openai): clean up post-rebase capability resolver
* fix(openai): preserve GPT-Live delegation fragments
* fix(openai): close GPT-Live sideband handoff race
* fix(openai): accept UUID GPT-Live call ids
* style: apply oxfmt to GPT-Live sources and Talk docs
* style: format Talk docs after rebase
* fix(openai): keep GPT-Live transcript context across ignored delegations
Aggregators republish first-party models under a namespaced id and varying
case, so the shared-model check could not group novita/moonshotai/kimi-k3 with
moonshot/kimi-k3. Matching now ignores one leading namespace segment and case,
which catches that whole class automatically instead of needing an
upstreamModel marker per row.
Declares the tier on the 18 rows this surfaces across baseten, deepinfra, gmi,
novita, nvidia, and together. All are "capable", matching what the runtime
already applied for an absent flag, so behavior is unchanged.
* refactor(agents): share one tool-surface resolver across runner and harness
The code-mode vs tool-search gate decision and the three-way catalog
application were duplicated across the embedded runner and the native
harness bridge, and had already drifted: the harness copy was missing the
skillWorkshopProposalOnly condition and its params object had no field to
express it.
Both surfaces now consume resolveAgentToolSurfacePlan and
applyAgentToolSurfaceCatalog, so the gates and the catalog branch exist
once. Both gate booleans derive from a single shared toolsAvailable
intermediate.
Behavior change: the harness path now honors skillWorkshopProposalOnly.
Proposal-only skill-workshop runs are deliberately narrow single-tool runs,
so code-mode indirection and tool-search catalogs are pure overhead — a
harness-independent reason. Both callers currently pin
agentHarnessRuntimeOverride "openclaw", so this closes a latent fail-open
rather than fixing a live bug.
* fix(agents): let the shared catalog params carry a config-less run
resolveAgentToolSearchRuntimeConfig returns OpenClawConfig | undefined, so
requiring a non-null toolSearchRuntimeConfig broke tsgo:core at both call
sites. Keep the key required so it cannot be silently omitted, but let the
value be undefined as the pre-refactor code already allowed.
* fix(agents): keep the tool-surface module free of dead exports
Importing isCodeModeEngagedForModel and applyToolSchemaDirectoryCatalog from
their defining modules left the code-mode.ts and tool-search.ts re-exports with
no production consumer, which knip rejects. Go back through the barrels, which
is also what both call sites did before this refactor.
The two params types were exported only for the test, so knip's production scan
saw them as dead. Keep them module-local and derive the type in the test.
* feat(plugins): catch code-mode drift between catalogs sharing one model
Adds a contract test that groups bundled catalog rows by shared upstream
model and requires every row in a group to declare compat.codeMode once any
sibling does. Rows sharing a model id group automatically; rows under
different ids opt in with the new manifest-only `upstreamModel` marker.
Moves the kimi catalog into its manifest so the scan can see it, and records
the tier reseller catalogs were silently missing as explicit "capable".
* docs: regenerate docs map for the shared-model code-mode section
