* fix(plugins): canonicalize manifest plugin ids to lowercase
Plugin config policy lists (plugins.deny, plugins.allow, plugins.entries)
are lowercase-normalized through normalizePluginId, but a plugin's
self-declared manifest id was only trimmed, never lowercased. A plugin
publishing "id": "Malicious-Scraper" therefore never matched an operator
denylist entry of "malicious-scraper" and fell through to default
activation, loading its hooks, channels, secret integrations, and tools.
The same gap let a mixed-case spelling evade the core reserved-id check.
Canonicalize the id at the manifest parse boundary where
PluginManifestRecord.id is minted, so every downstream policy consumer
compares against the same canonical form.
* test(plugins): prove mixed-case deny at gateway startup
* test(plugins): assert denied gateway record is absent
* test(plugins): materialize allowed secret fixture
* fix(plugins): compare a derived policy key instead of rewriting manifest identity
Manifest ids stay exactly as declared. Deny, allow, and per-entry checks now
compare a lowercase policy key derived at each enforcement boundary, matching
the lowercase-normalized config lists.
The previous approach lowercased PluginManifestRecord.id at the parse boundary.
That id is also matched against the plugin runtime export id, and a mismatch is
a hard load failure, so an existing plugin declaring the same mixed-case id in
both its manifest and its runtime export would stop loading after upgrade.
The Gateway fixture now declares a mixed-case manifest id with a matching
mixed-case runtime export, covering that upgrade case, and drops the allowlist
that previously scoped discovery by a lowercase id and masked the denylist
behavior under test.
* fix(plugins): close mixed-case policy gaps
* test(plugins): use tracked policy fixture temp dir
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Replace the bare onTurnAdopted callback and queuedFollowupLifecycle with one
turnAdoptionLifecycle surface (onSettled guaranteed via finally; adoption-loss
aborts queued steering turns without transcript replay), threaded through the
turn kernel and agent runner, exposed to plugins via
runtime.state.openChannelIngressDrain and the channel-outbound SDK barrel,
with surface budgets re-measured against the narrowed baselines (#108656).
* feat: consume live featured catalog state
* fix(plugins): honor hosted curation for published bundled plugins
* fix(plugins): accept package-less trusted ClawHub provenance
Embedded runs targeting a CLI runtime provider fall through to the openclaw
harness and call the provider API directly with the runtime's credentials
(cli_runtime_passthrough_openclaw). Anthropic routes direct anthropic-messages
calls on subscription OAuth tokens to metered extra-usage billing — this is
long-standing behavior, not a recent change. Without extra-usage balance,
every such run (e.g. active-memory recall) fails with a billing error; with
extra-usage enabled, the run silently draws paid metered usage instead of the
plan limits the CLI runtime was configured for. Only CLI-backed execution
runs on plan limits for those credentials.
Add an opt-in RunEmbeddedAgentParams.cliBackendDispatch: "subscription-auth"
that dispatches the run through runCliAgent as a one-shot turn when the
provider is claude-cli, a CLI backend is registered, and the ordered auth
profile selection for the passthrough resolves to a subscription (oauth/token)
credential or nothing rather than an API key; resolution stays on stored
credential metadata, with no credential materialization or refresh on the
per-turn path. The dispatch translates toolsAllow into the selectable-backend
surface (native: [], allowlisted loopback MCP tools; wildcard allowlists stay
MCP-only), runs with a fresh CLI process (no live-session reuse; session-
scoped bundle-MCP retirement on run end rather than the process-wide loopback
close), bridges CLI tool result events to onAgentToolResult with native-path
semantics (normalizeToolName + isToolResultError), and drops CLI session
bindings from the result.
The selectable-backend MCP list now also bounds the loopback MCP grant
server-side: the grant carries a per-run gateway tool allowlist enforced in
scoped tool resolution, so tools outside the run's allowlist can be neither
listed nor called even under CLI bypass permission modes where
--allowedTools is advisory.
active-memory recall opts in so recall works on claude-cli subscription-only
instances and stops drawing metered extra usage where it previously could.
Scoped to claude-cli; other CLI runtimes keep the passthrough until their
direct-API contract is verified.
The dispatch also mirrors the run into the run's session transcript through the session
accessor (user turn, tool call/result records as they stream, final assistant
snapshot at run end) so transcript consumers keep parity with embedded runs:
active-memory's persistTranscripts, timeout partial-text salvage, and the
live terminal-search watcher that polls the session file mid-run.
Post-review hardening: canonical anthropic/<model> refs whose configured
agentRuntime is claude-cli resolve through the runtime policy before the
dispatch gate (they previously stayed on the failing passthrough); restricted
dispatches serve an exclusive loopback-only MCP bundle so user/plugin MCP
servers stay outside the run's tool universe; and the transcript recorder
flushes the latest assistant snapshot the moment the run aborts, so timeout
salvage sees partial text even while the killed CLI child is still settling.
Recalls routed to the claude-cli runtime default to a 45s budget (measured
CLI-dispatched runs take 14-20s, over the plain 15s default); explicit
timeoutMs config always wins.
Transcript mirror keeps bare-array tool_result content (claude stream-json
echoes MCP results without a {content} wrapper); dropping it classified every
successful recall as no_relevant_memory.
CLI dispatch resolves inside session/global lane admission so dispatched
runs obey the same lifecycle, placement, and concurrency gates as native
embedded runs.
LOC-ratchet offsets move the loopback grant-context builders to
cli-runner/mcp-grant-context.ts and dedupe the run/prep stage-summary
emitters into attempt-stage-timing.ts; unused type exports dropped and the
now-used stream-message baseline entry removed.
The recall timeout default now consumes the runner's own dispatch
eligibility through a new plugin-runtime seam
(agent.resolveCliBackendDispatchEligibility): API-key and missing-backend
routes keep the passthrough and its plain 15s default.
Eligibility honors an explicitly pinned authProfileId (the credential the
run executes on) before ordered profile selection, in both directions.
Transcript mirror composes buildAssistantMessage + buildUsageWithNoCost
directly; main trimmed the zero-usage wrapper export (ab0ccc244b) before
this branch's usage landed.
Dispatch eligibility is provider-owned: the anthropic plugin's claude-cli
backend declares CliBackendPlugin.subscriptionAuthDispatch and core reads
the registered descriptor instead of a core provider allowlist.
Dispatch fails closed on tool policy (only non-empty named allowlists are
expressible on the CLI surface; deny-all, wildcards, absent allowlists, and
disableTools/modelRun keep the passthrough), threads the pinned
authProfileId into CLI runtime resolution, and emits onExecutionStarted at
the admitted dispatch boundary.
* fix(workboard): record resolved runtime metadata instead of hardcoded codex engine
Workboard executions labeled every dispatched run engine=codex, model=default,
and id suffix :codex even for Claude/other harness agents. The gateway agent
admission phase now returns the resolved {harness, provider, model} for plugin
subagent runs; the dispatcher records it verbatim and omits engine/model when
unresolved. Engine becomes an open runtime identifier in the workboard
contract (built-in launch choices stay a closed list), store/UI normalizers
preserve historical labels as written instead of inventing codex, and new
execution ids use an :agent-session suffix. Fixes#108362
* fix(workboard): accept undefined engine in ui engineModel helper
* refactor(channels): generalize channel retry runner and retry-after parsing; drop dead configured-state probes
* fix(channels): align retry and metadata contracts
* fix(plugins): handle ENOTDIR gracefully in npm-project-roots
The listManagedPluginNpmProjectRootsSync and listManagedPluginNpmProjectRoots
functions only caught ENOENT errors when reading the projects directory,
but an ENOTDIR error (when a file path is mistakenly used as a directory)
would propagate unhandled and crash the CLI.
Replace the local isMissing helper with the shared isNotFoundPathError from
infra/path-guards.ts, which already covers both ENOENT and ENOTDIR.
Fixes#107467
* test(plugins): use managed temp directory fixture
* chore: keep release notes out of contributor PR
* fix(plugins): restore not-found path guard export
* fix(plugins): normalize Windows managed install paths
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: Peter Steinberger <peter@steipete.me>
* refactor(plugin-sdk): narrow wildcard barrels to explicit used exports
* refactor(tools): delete dead tool-planning module exposed by barrel narrowing
* fix(plugin-sdk): restore deprecation tag on OpenClawSchemaType alias
* test(agents): drop test for deleted runtime proxy module
* refactor(tools): trim descriptor types to cache consumers
* refactor(deadcode): harvest exports orphaned by barrel narrowing
* refactor(deadcode): harvest exports orphaned by barrel narrowing (rest)
* fix(agents): restore sdk imports and test markers via public predicate
* fix(plugin-sdk): named type re-exports in plugin-entry; trim types barrel precisely
* chore(plugin-sdk): account unmasked deprecated provider types in budgets
* fix(plugins): name star-only type rows for dts bundling
* fix(plugins): restore host-hook surface; unexport internal api compositions
* fix(plugins): named type imports for api composition; restore needed source exports
* fix(plugins): knip-visible type imports for registry surfaces
* test: adapt tests to privatized media and command internals
* fix(qa-lab): re-export snapshot conversation type
* style: format sessions sdk imports
* fix(plugins): restore smoke entry export; pin budgets to exact actuals
* fix(plugins): canonical smoke-entry import; drop orphaned root shims
* fix(plugins): allowlist manifest probe, repoint qa web import, drop dead browser barrels
* fix(plugin-sdk): pin codex auth marker and scaffold provider type
* fix(qa-lab): keep web-facing model-selection shim within boundary rules
* fix(plugin-sdk): preserve merged contracts through narrowed barrels
* chore(plugin-sdk): pin post-rebase surface budgets
On git-channel installs where both extensions/<id>/index.ts and
dist/extensions/<id>/index.js exist, two registry assemblies resolved the same
plugin id to different physical files (preferBuiltPluginArtifacts drives both the
artifact choice and the load-cache key), so the path-keyed module cache
evaluated the entry twice — two live plugin instances with separate state,
binding hooks to one and registerTool to the other. Memoize the first resolved
runtime entry path per plugin-id + real root + entry-kind so both assemblies
converge on one module instance; clear the memo on activated-runtime-state and
registry-load-cache resets so reload/install/doctor re-resolve. No-op on
dist-only installs.
Closes#107933
The deleted text provider's usage hook was the only source for the /status
Codex subscription usage line. Harnesses can now contribute an optional
usage snapshot (provider hooks keep priority; only distinct synthetic hook
owners fall through), and the codex harness reports app-server rate limits
via account/rateLimits/read with the same conversion and account identity
as before. No text provider resurrected; deadcode and SDK surface gates
clean.
The live codex text provider was a redundant projection of the openai
catalog (exclusive provider ownership; the openai plugin's ChatGPT OAuth
discovery already serves gpt-5.6-* route-aware). Folding it:
- extensions/codex no longer registers a text provider, catalog entry, or
synthetic text auth; provider.ts/provider-catalog.ts/provider-discovery.ts
and the route-blind model-name heuristics are deleted; the narrow
post-harness reasoning fallback moves to an app-server-owned module
- openai thinking policy keys on explicit selected-route provenance
(api === openai-chatgpt-responses) instead of value-shape inference
- models.list gains an optional additive agentRuntime field (configured
intent); session agentHarnessId remains the execution proof
- doctor --fix migrates the shipped codex/* config shape end to end:
every model slot, provider-config merge with blocker-aware conflict
handling, sessions, cron payloads (two-phase: runtime policy persists
before cron refs rewrite), transcripts; migrated refs carry model-scoped
agentRuntime.id=codex preserving the shipped wizard semantics; auto
runtime policies normalize to codex with sibling fields preserved;
blocked provider conflicts retain the whole legacy namespace fail-closed
with an actionable warning
- the stale openai:default profile cleanup (#91352) was deliberately
deferred to a follow-up after review showed it needs per-agent identity
proofs; doctor keeps warning about unusable profiles
Fixes#105561Fixes#84637Fixes#90420
* fix(agents): wake owning session after generated-media direct delivery
When a background media generation (image/music/video) completes but the
requester's agent turn cannot be woken, delivery falls back to sending the
media straight to the channel. The owning session never learned about it,
leaving the attachment orphaned with no agent follow-up.
Queue a system event plus a scoped heartbeat wake after both direct
fallback paths (announce delivery and the shared background lifecycle) so
the agent continues the conversation in its own voice. Subagent requester
sessions skip the heartbeat since their completions route via announce.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(agents): persist generated media session handoffs
Co-authored-by: Molty <steipete@gmail.com>
* chore: prune max-lines baseline
* fix(agents): harden durable media handoffs
* fix(agents): charge media retries once
* chore: refresh max-lines baseline
* fix(agents): persist delivery settlement cleanup
* fix(agents): fence interrupted media delivery
* fix(agents): fence durable handoff admission
* fix(agents): reconcile terminal handoffs at retry limit
* fix(agents): align durable handoff types
* test(agents): type durable handoff fixtures
* fix: satisfy session delivery lint
* fix: avoid payload map spreads
* fix: satisfy durable handoff gates
* test: align generated media handoff expectations
* fix: avoid serializing session recovery state during load
---------
Co-authored-by: Molty <steipete@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
