Adds a generic plugin-declared selectable-context-window surface mirroring thinkingLevels: ModelCatalogEntry.contextWindows + contextWindowDefault through catalog normalization and the gateway protocol, session validation on sessions.create/patch, and a 200K/1M switch inside the Control UI model picker for Claude CLI 5-series models. The Anthropic plugin owns the option mapping: explicit 1m → `[1m]` argv suffix, 200k → bare id + CLAUDE_CODE_DISABLE_1M_CONTEXT=1, omitted → bare id (shipped default argv). Run budgets follow the selection on both CLI and native paths, so a 200K session gets a matching auto-compact window instead of a silent 1M budget.
Review fixes landed in this PR: run-owner prepared-fact plumbing so ordinary replies honor the selection; atomic catalog overlay merge and normalization for the options/default tuple; one-owner tuple reads in the picker; sessions.create key-presence patch semantics; native-run budget capping.
Feature direction and in-picker switch shape by @obviyus (maintainer review).
* fix(opencode): migrate retired free model refs
Repair the shipped beta upgrade path through the provider-owned Doctor contract. Activate the migration from the canonical configured-model selector inventory so every supported selector is covered consistently.
Co-authored-by: samson1357924 <samson1357924@gmail.com>
* fix(opencode): migrate media model preferences
---------
Co-authored-by: samson1357924 <samson1357924@gmail.com>
* docs(agents): standardize canonical record guards
* refactor(model-catalog): use canonical record guard
* refactor(scripts): use canonical record guard
* refactor(ui): use canonical record guard
* refactor(codex): use canonical record guard
* refactor(agents): use canonical record guard
* refactor(sessions): use canonical record guard
* refactor(doctor): use canonical record guard
* refactor(infra): use canonical record guard
* 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
* feat(tools): per-model code-mode capability flags and auto master-switch tier
* feat(anthropic): flag claude-sonnet-4-6 as code-mode preferred
* revert(anthropic): drop claude-sonnet-4-6 from the code-mode preferred set
* test(anthropic): type the manifest compat field in the catalog contract test
* fix(anthropic): carry catalog compat onto hand-built forward-compat model rows
Main already resolves bare opus to Claude Opus 5 but documents nothing about
the rolling behavior. State that bare family aliases follow the current
generation and that pinning is the opt-out, and add regression coverage
separating bare aliases, pinned aliases, and retired-ref upgrades.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* feat(models): add Claude Opus 5 support
* test(models): align Opus 5 setup fixtures
* test(models): update ambient Opus 5 detection
* fix(models): reconcile Opus 5 support with main
* feat(anthropic): add Claude Opus 5 model support
Wire claude-opus-5 through the Claude 5 contract seams: adaptive-by-default
thinking with the full low..max effort range, default-sampling and prefill
stripping, streaming refusal contract, model-bound thinking replay, and 1M/128k
catalog metadata across anthropic, claude-cli, Vertex, Bedrock, and Mantle.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(anthropic-vertex): normalize explicit Vertex Opus 5 model rows
Extend normalizeAnthropicVertexResolvedModel so user-configured Vertex Opus 5
rows regain reasoning, image input, 1M/128k limits, and the native thinking
map; update the live-model priority expectation and regenerate docs_map.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* feat(tooling): add noUncheckedIndexedAccess strict-ratchet lane
* fix(packages): make indexed access explicit across ratchet packages
Burns down all 65 noUncheckedIndexedAccess errors in the seven ratchet
packages with behavior-identical restructuring (iteration, charAt/slice,
regex-group guards, validated hextet tuple). net-policy invariant
violations now throw instead of failing open. Adds
@openclaw/normalization-core/expect (expectDefined/first/last) with
subpath export and tests. memory-host-sdk fixes kept but the package
stays out of the lane: it re-exports core src/** so the flag would apply
transitively to all of core.
* fix(lint): keep .oxlintrc.json strict-JSON parseable for extension lint wrappers
* feat(agents): derive a provider-declared default utility model when unset
When agents.defaults.utilityModel is not set, utility tasks (titles, progress
narration) now use the primary provider's declared small model
(modelCatalog.providers.<id>.defaultUtilityModel: OpenAI -> gpt-5.6-luna,
Anthropic -> claude-haiku-4-5). Auth is inherent because derivation follows
the agent's primary provider. Setting utilityModel to an empty string
disables utility routing entirely; narration turns on automatically when a
default resolves and stays off otherwise.
Formatting/lint/tests verified on Testbox (oxfmt, oxlint, plugins:inventory,
docs:map, import-cycles, check:test-types, 4 test files).
* fix(ai): drop the temperature parameter for models that reject it
The GPT-5.6 family 400s on temperature via the Responses API (live-verified:
gpt-5.6-luna/-terra reject it; gpt-5.5 and gpt-5.4-mini/nano accept it).
supportsOpenAITemperature gates all three OpenAI payload builders, with a
catalog compat override (compat.supportsTemperature) declared for the 5.6
family in the openai manifest. Without this, utility tasks (titles,
narration) would fail once gpt-5.6-luna becomes the derived default.
Gates on Testbox: oxfmt, oxlint, plugins:inventory, import-cycles,
check:test-types, 6 test files. Live proof on Testbox: gpt-5.6-luna and
claude-haiku-4-5 one-shot completions succeed with temperature requested.
* fix(agents): carry the primary model's auth profile onto the derived utility default
A primary like openai/gpt-5.5@work previously reached utility tasks via the
profiled fallback; the derived default shares the provider, so its trailing
auth profile carries over instead of silently switching to default
credentials (Codex review). Gates on Testbox: oxfmt, check:test-types, tests.
* docs: realign the manifest provider-fields table after adding defaultUtilityModel
* feat(openai): add GPT-5.6 series support
* docs: refresh map for GPT-5.6
* fix(openai): preserve GPT-5.6 thinking metadata
* fix(codex): sync managed app server version
* fix(codex): sync managed app server version
* fix(openai): account for GPT-5.6 cache writes
---------
Co-authored-by: Peter Steinberger <steipete@golden-gate.local>
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.
Move model catalog normalization and package-owned catalog schema/types into model-catalog-core while keeping public plugin SDK model catalog declarations on the existing SDK surface. Verified focused tests, package-boundary compile, full build, changed gate, declaration leak grep, CI, and autoreview.
Move model catalog ref helpers into @openclaw/model-catalog-core/model-catalog-refs and update internal callers/package-boundary aliases. Also fix the timestamp predicate typing that blocked prod type checks on current main.
* refactor: extract model catalog core package
* refactor: route model catalog imports through package boundary
* build: include model catalog in plugin sdk package dts
* fix: preserve static fallback model metadata
Peter Steinberger