mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 10:40:43 +00:00
fix: hide adaptive think option for GPT models
This commit is contained in:
Peter Steinberger
@@ -43,6 +43,7 @@ For model selection rules, see [/concepts/models](/concepts/models).
|
||||
`matchesContextOverflowError`, `classifyFailoverReason`,
|
||||
`isCacheTtlEligible`, `buildMissingAuthMessage`, `suppressBuiltInModel`,
|
||||
`augmentModelCatalog`, `isBinaryThinking`, `supportsXHighThinking`,
|
||||
`supportsAdaptiveThinking`,
|
||||
`resolveDefaultThinkingLevel`, `applyConfigDefaults`, `isModernModelRef`,
|
||||
`prepareRuntimeAuth`, `resolveUsageAuth`, `fetchUsageSnapshot`, and
|
||||
`onModelSelected`.
|
||||
@@ -133,6 +134,7 @@ Typical split:
|
||||
discovery and config merging
|
||||
- `isBinaryThinking`: provider owns binary on/off thinking UX
|
||||
- `supportsXHighThinking`: provider opts selected models into `xhigh`
|
||||
- `supportsAdaptiveThinking`: provider opts selected models into `adaptive`
|
||||
- `resolveDefaultThinkingLevel`: provider owns default `/think` policy for a
|
||||
model family
|
||||
- `applyConfigDefaults`: provider applies provider-specific global defaults
|
||||
|
||||
@@ -658,7 +658,7 @@ Provider plugins now have two layers:
|
||||
`buildAuthDoctorHint`, `matchesContextOverflowError`,
|
||||
`classifyFailoverReason`, `isCacheTtlEligible`,
|
||||
`buildMissingAuthMessage`, `suppressBuiltInModel`, `augmentModelCatalog`,
|
||||
`isBinaryThinking`, `supportsXHighThinking`,
|
||||
`isBinaryThinking`, `supportsXHighThinking`, `supportsAdaptiveThinking`,
|
||||
`resolveDefaultThinkingLevel`, `isModernModelRef`, `prepareRuntimeAuth`,
|
||||
`resolveUsageAuth`, `fetchUsageSnapshot`, `createEmbeddingProvider`,
|
||||
`buildReplayPolicy`,
|
||||
@@ -724,16 +724,17 @@ The "When to use" column is the quick decision guide.
|
||||
| 32 | `augmentModelCatalog` | Synthetic/final catalog rows appended after discovery | Provider needs synthetic forward-compat rows in `models list` and pickers |
|
||||
| 33 | `isBinaryThinking` | On/off reasoning toggle for binary-thinking providers | Provider exposes only binary thinking on/off |
|
||||
| 34 | `supportsXHighThinking` | `xhigh` reasoning support for selected models | Provider wants `xhigh` on only a subset of models |
|
||||
| 35 | `resolveDefaultThinkingLevel` | Default `/think` level for a specific model family | Provider owns default `/think` policy for a model family |
|
||||
| 36 | `isModernModelRef` | Modern-model matcher for live profile filters and smoke selection | Provider owns live/smoke preferred-model matching |
|
||||
| 37 | `prepareRuntimeAuth` | Exchange a configured credential into the actual runtime token/key just before inference | Provider needs a token exchange or short-lived request credential |
|
||||
| 38 | `resolveUsageAuth` | Resolve usage/billing credentials for `/usage` and related status surfaces | Provider needs custom usage/quota token parsing or a different usage credential |
|
||||
| 39 | `fetchUsageSnapshot` | Fetch and normalize provider-specific usage/quota snapshots after auth is resolved | Provider needs a provider-specific usage endpoint or payload parser |
|
||||
| 40 | `createEmbeddingProvider` | Build a provider-owned embedding adapter for memory/search | Memory embedding behavior belongs with the provider plugin |
|
||||
| 41 | `buildReplayPolicy` | Return a replay policy controlling transcript handling for the provider | Provider needs custom transcript policy (for example, thinking-block stripping) |
|
||||
| 42 | `sanitizeReplayHistory` | Rewrite replay history after generic transcript cleanup | Provider needs provider-specific replay rewrites beyond shared compaction helpers |
|
||||
| 43 | `validateReplayTurns` | Final replay-turn validation or reshaping before the embedded runner | Provider transport needs stricter turn validation after generic sanitation |
|
||||
| 44 | `onModelSelected` | Run provider-owned post-selection side effects | Provider needs telemetry or provider-owned state when a model becomes active |
|
||||
| 35 | `supportsAdaptiveThinking` | `adaptive` thinking support for selected models | Provider wants `adaptive` shown only for models with provider-managed adaptive thinking |
|
||||
| 36 | `resolveDefaultThinkingLevel` | Default `/think` level for a specific model family | Provider owns default `/think` policy for a model family |
|
||||
| 37 | `isModernModelRef` | Modern-model matcher for live profile filters and smoke selection | Provider owns live/smoke preferred-model matching |
|
||||
| 38 | `prepareRuntimeAuth` | Exchange a configured credential into the actual runtime token/key just before inference | Provider needs a token exchange or short-lived request credential |
|
||||
| 39 | `resolveUsageAuth` | Resolve usage/billing credentials for `/usage` and related status surfaces | Provider needs custom usage/quota token parsing or a different usage credential |
|
||||
| 40 | `fetchUsageSnapshot` | Fetch and normalize provider-specific usage/quota snapshots after auth is resolved | Provider needs a provider-specific usage endpoint or payload parser |
|
||||
| 41 | `createEmbeddingProvider` | Build a provider-owned embedding adapter for memory/search | Memory embedding behavior belongs with the provider plugin |
|
||||
| 42 | `buildReplayPolicy` | Return a replay policy controlling transcript handling for the provider | Provider needs custom transcript policy (for example, thinking-block stripping) |
|
||||
| 43 | `sanitizeReplayHistory` | Rewrite replay history after generic transcript cleanup | Provider needs provider-specific replay rewrites beyond shared compaction helpers |
|
||||
| 44 | `validateReplayTurns` | Final replay-turn validation or reshaping before the embedded runner | Provider transport needs stricter turn validation after generic sanitation |
|
||||
| 45 | `onModelSelected` | Run provider-owned post-selection side effects | Provider needs telemetry or provider-owned state when a model becomes active |
|
||||
|
||||
`normalizeModelId`, `normalizeTransport`, and `normalizeConfig` first check the
|
||||
matched provider plugin, then fall through other hook-capable provider plugins
|
||||
@@ -805,7 +806,7 @@ api.registerProvider({
|
||||
|
||||
- Anthropic uses `resolveDynamicModel`, `capabilities`, `buildAuthDoctorHint`,
|
||||
`resolveUsageAuth`, `fetchUsageSnapshot`, `isCacheTtlEligible`,
|
||||
`resolveDefaultThinkingLevel`, `applyConfigDefaults`, `isModernModelRef`,
|
||||
`supportsAdaptiveThinking`, `resolveDefaultThinkingLevel`, `applyConfigDefaults`, `isModernModelRef`,
|
||||
and `wrapStreamFn` because it owns Claude 4.6 forward-compat,
|
||||
provider-family hints, auth repair guidance, usage endpoint integration,
|
||||
prompt-cache eligibility, auth-aware config defaults, Claude
|
||||
|
||||
@@ -535,16 +535,17 @@ API key auth, and dynamic model resolution.
|
||||
| 31 | `augmentModelCatalog` | Synthetic forward-compat rows |
|
||||
| 32 | `isBinaryThinking` | Binary thinking on/off |
|
||||
| 33 | `supportsXHighThinking` | `xhigh` reasoning support |
|
||||
| 34 | `resolveDefaultThinkingLevel` | Default `/think` policy |
|
||||
| 35 | `isModernModelRef` | Live/smoke model matching |
|
||||
| 36 | `prepareRuntimeAuth` | Token exchange before inference |
|
||||
| 37 | `resolveUsageAuth` | Custom usage credential parsing |
|
||||
| 38 | `fetchUsageSnapshot` | Custom usage endpoint |
|
||||
| 39 | `createEmbeddingProvider` | Provider-owned embedding adapter for memory/search |
|
||||
| 40 | `buildReplayPolicy` | Custom transcript replay/compaction policy |
|
||||
| 41 | `sanitizeReplayHistory` | Provider-specific replay rewrites after generic cleanup |
|
||||
| 42 | `validateReplayTurns` | Strict replay-turn validation before the embedded runner |
|
||||
| 43 | `onModelSelected` | Post-selection callback (e.g. telemetry) |
|
||||
| 34 | `supportsAdaptiveThinking` | Adaptive thinking support |
|
||||
| 35 | `resolveDefaultThinkingLevel` | Default `/think` policy |
|
||||
| 36 | `isModernModelRef` | Live/smoke model matching |
|
||||
| 37 | `prepareRuntimeAuth` | Token exchange before inference |
|
||||
| 38 | `resolveUsageAuth` | Custom usage credential parsing |
|
||||
| 39 | `fetchUsageSnapshot` | Custom usage endpoint |
|
||||
| 40 | `createEmbeddingProvider` | Provider-owned embedding adapter for memory/search |
|
||||
| 41 | `buildReplayPolicy` | Custom transcript replay/compaction policy |
|
||||
| 42 | `sanitizeReplayHistory` | Provider-specific replay rewrites after generic cleanup |
|
||||
| 43 | `validateReplayTurns` | Strict replay-turn validation before the embedded runner |
|
||||
| 44 | `onModelSelected` | Post-selection callback (e.g. telemetry) |
|
||||
|
||||
Prompt tuning note:
|
||||
|
||||
|
||||
@@ -16,10 +16,11 @@ title: "Thinking Levels"
|
||||
- medium → “think harder”
|
||||
- high → “ultrathink” (max budget)
|
||||
- xhigh → “ultrathink+” (GPT-5.2 + Codex models and Anthropic Claude Opus 4.7 effort)
|
||||
- adaptive → provider-managed adaptive thinking (supported for Anthropic Claude 4.6 and Opus 4.7)
|
||||
- adaptive → provider-managed adaptive thinking (supported for Claude 4.6 on Anthropic/Bedrock and Anthropic Claude Opus 4.7)
|
||||
- `x-high`, `x_high`, `extra-high`, `extra high`, and `extra_high` map to `xhigh`.
|
||||
- `highest`, `max` map to `high`.
|
||||
- Provider notes:
|
||||
- `adaptive` is only advertised in native command menus and pickers for providers/models that declare adaptive thinking support. It remains accepted as a typed directive for compatibility with existing configs and aliases.
|
||||
- Anthropic Claude 4.6 models default to `adaptive` when no explicit thinking level is set.
|
||||
- Anthropic Claude Opus 4.7 does not default to adaptive thinking. Its API effort default remains provider-owned unless you explicitly set a thinking level.
|
||||
- Anthropic Claude Opus 4.7 maps `/think xhigh` to adaptive thinking plus `output_config.effort: "xhigh"`, because `/think` is a thinking directive and `xhigh` is the Opus 4.7 effort setting.
|
||||
@@ -109,7 +110,8 @@ title: "Thinking Levels"
|
||||
- Picking another level writes the session override immediately via `sessions.patch`; it does not wait for the next send and it is not a one-shot `thinkingOnce` override.
|
||||
- The first option is always `Default (<resolved level>)`, where the resolved default comes from the active session model: `adaptive` for Claude 4.6 on Anthropic, `off` for Anthropic Claude Opus 4.7 unless configured, `low` for other reasoning-capable models, `off` otherwise.
|
||||
- The picker stays provider-aware:
|
||||
- most providers show `off | minimal | low | medium | high | adaptive`
|
||||
- most providers show `off | minimal | low | medium | high`
|
||||
- Anthropic/Bedrock Claude 4.6 shows `off | minimal | low | medium | high | adaptive`
|
||||
- Anthropic Claude Opus 4.7 shows `off | minimal | low | medium | high | xhigh | adaptive`
|
||||
- Z.AI shows binary `off | on`
|
||||
- `/think:<level>` still works and updates the same stored session level, so chat directives and the picker stay in sync.
|
||||
|
||||
Reference in New Issue
Block a user