Azure OpenAI endpoints were not recognized by shouldForceResponsesStore(),
causing store=false to be sent with all Azure Responses API requests.
This broke multi-turn conversations because previous_response_id referenced
responses that Azure never stored.
Add "azure-openai-responses" to the provider whitelist and
*.openai.azure.com to the URL check in isDirectOpenAIBaseUrl().
Fixes#27497
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
(cherry picked from commit 185f3814e94cf50bf04838994af1944389a4b6c0)
When reasoningLevel is 'on', reasoning content was being sent as a
visible message to WhatsApp and other non-Telegram channels via two
paths:
1. Block reply: emitted via onBlockReply in handleMessageEnd
2. Final payloads: added to replyItems in buildEmbeddedRunPayloads
Telegram has its own dispatch path (bot-message-dispatch.ts) that
splits reasoning into a dedicated lane and handles suppression.
The generic dispatch-from-config.ts path used by WhatsApp, web, etc.
had no such filtering.
Fix:
- Add isReasoning?: boolean flag to ReplyPayload
- Tag reasoning payloads at both emission points
- Filter isReasoning payloads in dispatch-from-config.ts for both
block reply and final reply paths
Telegram is unaffected: it uses its own deliver callback that detects
reasoning via the 'Reasoning:\n' prefix and routes to a separate lane.
Fixes#24954
The 'auto' model on OpenRouter dynamically routes to any underlying model
OpenRouter selects, including reasoning-required endpoints. Previously,
OpenClaw would unconditionally inject `reasoning.effort: "none"` into
every request when the thinking level was "off", which causes a 400 error
on models where reasoning is mandatory and cannot be disabled.
Root cause:
- openrouter/auto has reasoning: false in the built-in catalog
- With thinking level "off", createOpenRouterWrapper injects
`reasoning: { effort: "none" }` via mapThinkingLevelToOpenRouterReasoningEffort
- For any OpenRouter-routed model that requires reasoning this results in:
"400 Reasoning is mandatory for this endpoint and cannot be disabled"
- The reasoning: false is then persisted back to models.json on every
ensureOpenClawModelsJson call, so manually removing it has no lasting effect
Fix:
- In applyExtraParamsToAgent, when provider is "openrouter" and the model
id is "auto", pass undefined as thinkingLevel to createOpenRouterWrapper
so no reasoning.effort is injected at all, letting OpenRouter's upstream
model handle it natively
- Add an explanatory comment in buildOpenrouterProvider clarifying that the
reasoning: false catalog value does NOT cause effort injection for "auto"
Users who need explicit reasoning control should target a specific model
id (e.g. openrouter/deepseek/deepseek-r1) rather than the auto router.
Fixes#24851
(cherry picked from commit aa554397980972d917dece09ab03c4cc15f5d100)
"off" is a truthy string, so the existing guard `if (thinkingLevel && ...)`
was always entering the injection block and sending `reasoning: { effort: "none" }`
to every OpenRouter request — even when thinking wasn't enabled. Models that
require reasoning (e.g. deepseek/deepseek-r1) reject this with:
400 Reasoning is mandatory for this endpoint and cannot be disabled.
Fix: skip the reasoning injection entirely when thinkingLevel is "off".
The reasoning_effort flat-field cleanup still runs. Omitting the reasoning
field lets each model use its own default behavior.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
sessions_send timeout/error results were being surfaced as raw warning
messages in Telegram chats because the tool is classified as mutating,
which forces error warnings to always be shown. However, sessions_send
failures are transient inter-session communication issues where the
message may still have been delivered, so they should not leak to users.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Isolated cron sessions (agentTurn) were grouped with subagent sessions
under the "minimal" prompt mode, which causes buildSkillsSection to
return an empty array. This meant <available_skills> was never included
in the system prompt for isolated cron runs.
Subagent sessions legitimately need minimal prompts (reduced context),
but isolated cron sessions are full agent turns that should have access
to all configured skills, matching the behavior of normal chat sessions
and non-isolated cron runs.
Remove isCronSessionKey from the minimal prompt condition so only
subagent sessions use "minimal" mode.
Fixes openclaw#24888
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: Add Kilo Gateway provider
Add support for Kilo Gateway as a model provider, similar to OpenRouter.
Kilo Gateway provides a unified API that routes requests to many models
behind a single endpoint and API key.
Changes:
- Add kilocode provider option to auth-choice and onboarding flows
- Add KILOCODE_API_KEY environment variable support
- Add kilocode/ model prefix handling in model-auth and extra-params
- Add provider documentation in docs/providers/kilocode.md
- Update model-providers.md with Kilo Gateway section
- Add design doc for the integration
* kilocode: add provider tests and normalize onboard auth-choice registration
* kilocode: register in resolveImplicitProviders so models appear in provider filter
* kilocode: update base URL from /api/openrouter/ to /api/gateway/
* docs: fix formatting in kilocode docs
* fix: address PR review — remove kilocode from cacheRetention, fix stale model refs and CLI name in docs, fix TS2742
* docs: fix stale refs in design doc — Moltbot to OpenClaw, MoltbotConfig to OpenClawConfig, remove extra-params section, fix doc path
* fix: use resolveAgentModelPrimaryValue for AgentModelConfig union type
---------
Co-authored-by: Mark IJbema <mark@kilocode.ai>
* Telegram: soft-fail reactions and fallback to inbound message id
* Telegram: soft-fail missing reaction message id
* Update CHANGELOG.md
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(compaction): pass model through runtime to fix ctx.model undefined
Fixes#3479
Root cause: extensionRunner.initialize() is never called in compact.ts workflow,
leaving ctx.model undefined. Compaction safeguard checks ctx.model and returns
fallback summary immediately without attempting LLM summarization.
Changes:
1. Pass model through compaction safeguard runtime registry (same pattern as maxHistoryShare)
2. Fall back to runtime.model when ctx.model is undefined
3. Add once-per-session warning when both models are missing (prevents log spam)
4. Add regression test for runtime.model fallback
This follows the established runtime registry pattern rather than attempting to call
extensionRunner.initialize() (which is SDK-internal and not meant for direct access).
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* test: add comprehensive tests for compaction-safeguard model fallback
Add integration tests to verify the model fallback behavior:
- Test runtime.model fallback when ctx.model is undefined (compact.ts workflow)
- Test fallback summary when both ctx.model and runtime.model are undefined
- Test contextWindowTokens runtime storage/retrieval
- Test combined runtime values (maxHistoryShare + contextWindowTokens + model)
These tests verify the fix for issue #3479 where compaction fails due to
ctx.model being undefined in the compact.ts workflow. The runtime registry
pattern allows model to be passed when extensionRunner.initialize() is not
called, ensuring summarization works in all code paths.
Related: PR #17864
* fix(test): adapt compaction-safeguard tests to upstream type changes
- Add baseUrl to Model mock objects (now required by Model<Api>)
- Add explicit Model<Api> annotation to prevent provider string widening
- Cast modelRegistry mock through unknown (ModelRegistry expanded)
- Use non-null assertion for compactionHandler (TypeScript strict)
- Type compaction result explicitly
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Compaction: add changelog credit for model fallback fix
* Update CHANGELOG.md
* Update CHANGELOG.md
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix: sanitize tool call IDs in agent loop for Mistral strict9 format (#23595)
Mistral requires tool call IDs to be exactly 9 alphanumeric characters
([a-zA-Z0-9]{9}). The existing sanitizeToolCallIdsForCloudCodeAssist
mechanism only ran on historical messages at attempt start via
sanitizeSessionHistory, but the pi-agent-core agent loop's internal
tool call → tool result cycles bypassed that path entirely.
Changes:
- Wrap streamFn (like dropThinkingBlocks) so every outbound request
sees sanitized tool call IDs when the transcript policy requires it
- Replace call_${Date.now()} in pendingToolCalls with a 9-char hex ID
generated from crypto.randomBytes
- Add Mistral tool call ID error pattern to ERROR_PATTERNS.format so
the error is correctly classified for retry/rotation
* Changelog: document Mistral strict9 tool-call ID fix
---------
Co-authored-by: echoVic <AkiraVic@outlook.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(cache): inject cache_control into system prompt for OpenRouter Anthropic
Add onPayload wrapper that injects cache_control: { type: "ephemeral" }
into the system/developer message content for OpenRouter requests routed
to Anthropic models. The system prompt is typically ~18k tokens and was
being re-processed on every request without caching.
Fixes#15151
* Changelog: add OpenRouter note for #17473
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* OpenRouter: allow any model ID instead of restricting to static catalog
OpenRouter models were restricted to a hardcoded prefix list in the internal model catalog, preventing use of newly added or less common models. This change makes OpenRouter work as the pass-through proxy it is -- any valid OpenRouter model ID now resolves dynamically.
Fixes https://github.com/openclaw/openclaw/issues/5241
Changes:
- Add OpenRouter as an implicit provider in resolveImplicitProviders so models.json is populated when an API key is detected (models-config.providers.ts)
- Add a pass-through fallback in resolveModel that creates OpenRouter models on-the-fly when they aren't pre-registered in the local catalog (
model.ts
)
- Remove the static prefix filter for OpenRouter/opencode in isModernModelRef (live-model-filter.ts)
* Apply requested change for maxTokens
* Agents: remove dead helper in live model filter
* Changelog: note Joly0/main OpenRouter fix
* Changelog: fix OpenRouter entry text
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
extraParams.provider was silently dropped by createStreamFnWithExtraParams().
This change injects it into model.compat.openRouterRouting so pi-ai's
buildParams includes params.provider in the API request body.
Enables OpenRouter provider routing options (only, order, allow_fallbacks,
data_collection, ignore, sort, quantizations) via model config:
```jsonc
"openrouter/model-name": {
"params": {
"provider": {
"only": ["deepinfra", "fireworks"],
"allow_fallbacks": false
}
}
}
```
Closes#10869✍️ Author: Claude Code with @carrotRakko (AI-written, human-approved)
