mirror of
https://github.com/openclaw/openclaw.git
synced 2026-08-26 01:05:36 +00:00
97bbbc2271
* 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 |
||
|---|---|---|
| .. | ||
| active-memory.md | ||
| agent-loop.md | ||
| agent-runtimes.md | ||
| agent-workspace.md | ||
| agent.md | ||
| architecture.md | ||
| channel-docking.md | ||
| commitments.md | ||
| compaction.md | ||
| context-engine.md | ||
| context.md | ||
| delegate-architecture.md | ||
| dreaming.md | ||
| experimental-features.md | ||
| features.md | ||
| managed-worktrees.md | ||
| mantis-slack-desktop-runbook.md | ||
| mantis.md | ||
| markdown-formatting.md | ||
| memory-builtin.md | ||
| memory-honcho.md | ||
| memory-qmd.md | ||
| memory-search.md | ||
| memory.md | ||
| message-lifecycle-refactor.md | ||
| messages.md | ||
| model-failover.md | ||
| model-providers.md | ||
| models.md | ||
| multi-agent.md | ||
| oauth.md | ||
| parallel-specialist-lanes.md | ||
| personal-agent-benchmark-pack.md | ||
| presence.md | ||
| progress-drafts.md | ||
| qa-e2e-automation.md | ||
| qa-matrix.md | ||
| queue-steering.md | ||
| queue.md | ||
| retry.md | ||
| session-pruning.md | ||
| session-tool.md | ||
| session.md | ||
| soul.md | ||
| streaming.md | ||
| system-prompt.md | ||
| timezone.md | ||
| typebox.md | ||
| typing-indicators.md | ||
| usage-tracking.md | ||