* fix(ollama): carry real Ollama Cloud context windows and capabilities
The ollama-cloud catalog still described three models (minimax-m2.7, glm-5.1,
glm-5.2) plus a retired kimi-k2.5. Every other cloud model — including kimi-k3,
the current flagship — was absent, so core synthesized it at the generic
DEFAULT_CONTEXT_TOKENS of 200k. A kimi-k3 session therefore ran with 200,000 of
its real 1,048,576 token window: 80% of the context silently discarded, with no
warning anywhere in the product.
Describe the full current cloud lineup with context windows, input modalities
and reasoning support verified against live /api/show and the ollama.com model
pages. Only mistral-large-3 lacks thinking (vision + tools + cloud only).
Suffixed refs shared the same defect from the other side: the default lookup is
keyed bare, so `kimi-k3:cloud` missed it and fell to the 128k plugin default.
A hardcoded glm-5.2 literal in buildOllamaModelDefinition had been papering over
that for exactly one model; replace it with a lookup through the canonical
cloud-id normalizer, which model-reasoning.ts already owned, and drop the
duplicate spelling of that helper.
* fix(ollama): cover exact cloud catalog variants
* fix(ollama): remove invalid cloud aliases
* fix(ollama): default Ollama Cloud onboarding to minimax-m3
Cloud onboarding derives `defaultModel` from the first entry of
OLLAMA_CLOUD_DEFAULT_MODELS, so array order silently owned the out-of-box
model choice. Put minimax-m3 (524,288 ctx, thinking + tools + vision) at
index 0, add it to the bundled rows it was missing from, and document the
ordering contract at the declaration.
Pin the resolved default id in the cloud setup tests so a reorder cannot
move it unnoticed, and align the provider doc's onboarding default and
fallback row list.
Claude-Session: https://claude.ai/code/session_01QXUQuDVataA5o16kxNnmoX
* fix(ollama): preserve default and shared model contracts
* test(ollama): consolidate cloud setup capability expectations
---------
Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Recheck the request signal after an async response hook settles so a concurrent abort cannot reach response body handling. Related to #125802 and #125834.
Co-authored-by: Onur Solmaz <2453968+osolmaz@users.noreply.github.com>
* perf(doctor): keep bundled doctor contract closures dependency-light
Doctor contract enumeration cold-loads each plugin's doctor-contract-api
closure via jiti, so a static value import of openclaw/plugin-sdk/runtime-doctor
pulled the state-db/kysely graph (~4.3s per closure) into
listPluginDoctorLegacyConfigRules / listPluginDoctorStateMigrationEntries.
- migrate all light doctor-contract closures (66 files) to the
dependency-light openclaw/plugin-sdk/runtime-doctor-migrations subpath
- voice-call: load detect/repairOpenClawStateDatabaseSchema* lazily inside
the migration bodies; keep only a type-only static runtime-doctor import
- matrix: split pure credential record shapes/normalizers into
credentials-state.ts so the doctor closure no longer imports the sync
plugin-state store through credentials-read
- guard: doctor-contract-closure-guard.test.ts now forbids static value
imports of runtime-doctor in closures alongside agent-runtime
* fix(matrix): keep credential revocation record type module-local
Knip production scan flags the export as consumer-less; the type is only
referenced by the exported union and revocation guard signature.
* 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.
* fix(ollama): resolve web search secret refs
* fix(ollama): preserve blocked search secret refs
* fix(ollama): share web search credential policy
* fix(ollama): resolve web search secret refs via shared resolver
Route configured models.providers.ollama.apiKey resolution through the
existing shared resolveWebSearchProviderCredential helper so env-backed
SecretRefs resolve for web search, and resolve the ambient OLLAMA_API_KEY
independently of the configured selected-host key so mixed setups still
reach the Ollama Cloud fallback after both selected-host attempts fail
(regression fixed at web-search-provider.ts:195).
Drop the two optional plugin-SDK resolver hooks (provider normalization
and unavailable-configured-ref callback) added earlier: the fix does not
depend on them, so the shared resolver and its generated plugin-SDK
baseline stay identical to main and no new plugin-SDK contract surface is
introduced. Ollama applies its own non-secret-marker filter locally on
the resolver output instead.
Add a mixed-credential regression test (configured host key plus a
distinct ambient OLLAMA_API_KEY reaching the cloud fallback) and drop the
tests for the removed fail-closed-throw behavior.
* fix(ollama): fail closed on unavailable web search refs
* fix(web-search): resolve env shorthand secret refs
* docs(changelog): note Ollama web-search SecretRef fix
* chore(changelog): remove release-owned entry
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Peter Steinberger