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 preview test mocked codex-route-warnings wholesale; the consolidated
blocked-merge warning now flows through it, so the auto-merge case runs the
actual implementation once. Migration identity helpers stay module-local;
codex-route-model-ref formatting fixed.
- codex media substitution keys on the registered media-understanding
provider (image capability + default model) instead of the deleted text
provider's synthetic auth probe; deterministic injected route in tests
- migration helper exports without production consumers are module-local;
the blocked-provider warning assertion goes through the plan export
- null-vs-undefined runtime record type at the provider-move helper
- gateway models.list fixtures expect the new agentRuntime intent field
(codex/implicit for policy-backed OpenAI routes, openclaw/implicit for
synthetic routes without provider policy)
- split doctor cron legacy-repair into its own module to satisfy the
max-lines gate without suppressions; callers import directly
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
* refactor(qa): route live channel selectors through suite host
* fix(qa): repair live selector CI
* fix(qa): remove retired runner exports
* fix(qa): remove obsolete live evidence
* 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>
* fix(process): report actual UTF-8 byte count in stdin write message
Replace string.length (UTF-16 code units) with Buffer.byteLength(content, 'utf8')
so the reported byte count matches the actual bytes written to process stdin.
For ASCII content the values are identical. For non-ASCII content (CJK, emoji),
string.length underreports the actual UTF-8 byte count.
* test(process): cover UTF-8 stdin write byte count
Co-authored-by: 陈志强0668000989 <chen.zhiqiang1@xydigit.com>
* style(test): keep UTF-8 regression compact
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(process): report actual UTF-8 byte count in send-keys message
Replace string.length (UTF-16 code units) with Buffer.byteLength(data, 'utf8')
so the reported byte count matches the actual bytes sent to process stdin.
For ASCII key sequences the values are identical. For non-ASCII text
sent via literal key data, string.length underreports the actual UTF-8
byte count.
* test(process): cover UTF-8 send-keys byte count
Co-authored-by: 陈志强0668000989 <chen.zhiqiang1@xydigit.com>
* ci: prune stale max-lines baseline
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(agents): reject synchronous sessions_send self-targets, break down missing-cost entries, dedup usage merges
- sessions_send fails fast with a clear error when a synchronous send resolves
to the calling session's own key, instead of enqueueing behind the sender's
own lane until timeout and falling back to an empty reply; fire-and-forget
(timeoutSeconds: 0) self-delivery keeps working (#107172)
- missingCostEntries now carries a provider/model breakdown surfaced on the
status runtime line and gateway CLI cost line, so zero-priced usage (e.g.
openai-codex/*) is attributable instead of an opaque counter (#98348)
- codex-synthetic-usage merge helpers share one precedence helper; behavior
unchanged, duplicate ranking logic deleted (#107497)
* test: use a valid billing type in synthetic-usage precedence case
* test: fix billing expectation to match valid type
* fix(plugins): keep official plugin config across bundled-to-external moves, harden npm metadata parsing
- doctor --fix and plugin auto-enable treat official-catalog plugin ids as
known configuration even when the external package is not installed yet, so
a bundled-to-external transition (codex) no longer silently drops the
plugins.allow entry and unregisters the agent harness; garbage ids are still
pruned, and the codex-specific diagnostic suppression in the doctor scan is
replaced by the generic official-catalog rule (#107226)
- npm view metadata normalization handles object and multi-version array
output, flat dist.* keys and nested dist objects, absent openclaw blocks,
selects the maximum satisfying semver (publication order is not semver
order), fails closed when a recognized range has no satisfying entry, and
names the missing fields in the error (#107842)
The #107219 register-crash fix (lazy binding-store opening so plugin
registration never touches runtime.state under the base runtime) landed with
#108311 alongside its regression test.
* style: format install-source-utils imports
* fix(plugins): align hook and tool registrations
Reuse gateway-owned plugin registrations for matching hooks and tools while loading only missing tool owners from narrower runtime scopes.\n\nCo-authored-by: w33d <w33d@steadholme.local>
* test(plugins): cover mixed registry tool owners
Verify gateway-pinned and compatible active registrations compose without another plugin load.
Co-authored-by: w33d <w33d@steadholme.local>
* refactor(plugins): keep pinned registry lookup internal
Reuse the existing runtime-state contract so hook and tool ownership does not expand the Plugin SDK surface or treat unpinned active registries as Gateway owners.
* test(plugins): complete hook context fixture
Supply the required tool name in the stateful hook ownership regression context.
* chore: leave contributor release note in PR
Normal contributor PRs do not modify the release-owned changelog; the PR body retains the release note and attribution.
* fix(plugins): align partial registry owners
* fix(plugins): preserve scoped tool diagnostics
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: w33d <w33d@steadholme.local>
Peter Steinberger