* feat(hooks): add trigger and channelId to plugin hook agent context
Adds `trigger` and `channelId` fields to `PluginHookAgentContext` so
plugins can determine what initiated the agent run and which channel
it originated from, without session-key parsing or Redis bridging.
trigger values: "user", "heartbeat", "cron", "memory"
channelId values: "telegram", "discord", "whatsapp", etc.
Both fields are threaded through run.ts and attempt.ts hookCtx so all
hook phases receive them (before_model_resolve, before_prompt_build,
before_agent_start, llm_input, llm_output, agent_end).
channelId falls back from messageChannel to messageProvider when the
former is not set. followup-runner passes originatingChannel so queued
followup runs also carry channel context.
* docs(changelog): note hook context parity fix for #28623
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(plugins): expose ephemeral sessionId in tool contexts for per-conversation isolation
The plugin tool context (`OpenClawPluginToolContext`) and tool hook
context (`PluginHookToolContext`) only provided `sessionKey`, which
is a durable channel identifier that survives /new and /reset.
Plugins like mem0 that need per-conversation isolation (e.g. mapping
Mem0 `run_id`) had no way to distinguish between conversations,
causing session-scoped memories to persist unbounded across resets.
Add `sessionId` (ephemeral UUID regenerated on /new and /reset) to:
- `OpenClawPluginToolContext` (factory context for plugin tools)
- `PluginHookToolContext` (before_tool_call / after_tool_call hooks)
- Internal `HookContext` for tool call wrappers
Thread the value from the run attempt through createOpenClawCodingTools
→ createOpenClawTools → resolvePluginTools and through the tool hook
wrapper.
Closes#31253
Made-with: Cursor
* fix(agents): propagate embedded sessionId through tool hook context
* test(hooks): cover sessionId in embedded tool hook contexts
* docs(changelog): add sessionId hook context follow-up note
* test(hooks): avoid toolCallId collision in after_tool_call e2e
---------
Co-authored-by: SidQin-cyber <sidqin0410@gmail.com>
* fix(hooks): deduplicate after_tool_call hook in embedded runs
(cherry picked from commit c129a1a74b)
* fix(hooks): propagate sessionKey in after_tool_call context
The after_tool_call hook in handleToolExecutionEnd was passing
`sessionKey: undefined` in the ToolContext, even though the value is
available on ctx.params. This broke plugins that need session context
in after_tool_call handlers (e.g., for per-session audit trails or
security logging).
- Add `sessionKey` to the `ToolHandlerParams` Pick type
- Pass `ctx.params.sessionKey` through to the hook context
- Add test assertion to prevent regression
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
(cherry picked from commit b7117384fc)
* fix(hooks): thread agentId through to after_tool_call hook context
Follow-up to #30511 — the after_tool_call hook context was passing
`agentId: undefined` because SubscribeEmbeddedPiSessionParams did not
carry the agent identity. This threads sessionAgentId (resolved in
attempt.ts) through the session params into the tool handler context,
giving plugins accurate agent-scoped context for both before_tool_call
and after_tool_call hooks.
Changes:
- Add `agentId?: string` to SubscribeEmbeddedPiSessionParams
- Add "agentId" to ToolHandlerParams Pick type
- Pass `agentId: sessionAgentId` at the subscribeEmbeddedPiSession()
call site in attempt.ts
- Wire ctx.params.agentId into the after_tool_call hook context
- Update tests to assert agentId propagation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
(cherry picked from commit aad01edd3e)
* changelog: credit after_tool_call hook contributors
* Update CHANGELOG.md
* agents: preserve adjusted params until tool end
* agents: emit after_tool_call with adjusted args
* tests: cover adjusted after_tool_call params
* tests: align adapter after_tool_call expectation
---------
Co-authored-by: jbeno <jim@jimbeno.net>
Co-authored-by: scoootscooob <zhentongfan@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
x-ai/grok models on OpenRouter do not support the reasoning.effort
parameter and reject payloads containing it with "Invalid arguments
passed to the model." Skip reasoning injection for these models, the
same way we already skip it for the dynamic "auto" routing model.
Closes#32039
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(agents): support `thinkingDefault: "adaptive"` for Anthropic models
Anthropic's Opus 4.6 and Sonnet 4.6 support adaptive thinking where the
model dynamically decides when and how much to think. This is now
Anthropic's recommended mode and `budget_tokens` is deprecated on these
models.
Add "adaptive" as a valid thinking level:
- Config: `agents.defaults.thinkingDefault: "adaptive"`
- CLI: `/think adaptive` or `/think auto`
- Pi SDK mapping: "adaptive" → "medium" effort at the pi-agent-core
layer, which the Anthropic provider translates to
`thinking.type: "adaptive"` with `output_config.effort: "medium"`
- Provider fallbacks: OpenRouter and Google map "adaptive" to their
respective "medium" equivalents
Closes#30880
Made-with: Cursor
* style(changelog): format changelog with oxfmt
* test(types): fix strict typing in runtime/plugin-context tests
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
GitHub Copilot API tokens expire after ~30 minutes. When OpenClaw spawns
a long-running subagent using Copilot as the provider, the token would
expire mid-session with no recovery mechanism, causing 401 auth errors.
This commit adds:
- Periodic token refresh scheduled 5 minutes before expiry
- Auth error detection with automatic token refresh and single retry
- Proper timer cleanup on session shutdown to prevent leaks
The implementation uses a per-attempt retry flag to ensure each auth
error can trigger one refresh+retry cycle without creating infinite
retry loops.
🤖 AI-assisted: This fix was developed with GitHub Copilot CLI assistance.
Testing: Fully tested with 3 new unit tests covering auth retry, retry
reset, and timer cleanup scenarios. All 11 auth rotation tests pass.
Fix tool-call lookup failures when models emit whitespace-padded names by normalizing
both transcript history and live streamed embedded-runner tool calls before dispatch.
Co-authored-by: wangchunyue <80630709+openperf@users.noreply.github.com>
Co-authored-by: Sid <sidqin0410@gmail.com>
Co-authored-by: Philipp Spiess <hello@philippspiess.com>
* fix(agents): add "google" provider to isReasoningTagProvider to prevent reasoning leak
The gemini-api-key auth flow creates a profile with provider "google"
(e.g. google/gemini-3-pro-preview), but isReasoningTagProvider only
matched "google-gemini-cli" (OAuth) and "google-generative-ai". As a
result:
- reasoningTagHint was false → system prompt omitted <think>/<final>
formatting instructions
- enforceFinalTag was false → <final> tag filtering was skipped
Raw <think> reasoning output was delivered to the end user.
Fix: add the bare "google" provider string to the match list and cover
it with two new test cases (exact match + case-insensitive).
Fixes#26551
* fix(agents): add forward-compat fallback for google-gemini-cli gemini-3.1-pro/flash-preview
gemini-3.1-pro-preview and gemini-3.1-flash-preview are not yet present in
pi-ai's built-in google-gemini-cli model catalog (only gemini-3-pro-preview
and gemini-3-flash-preview are registered). When users configure these models
they get "Unknown model" errors even though Gemini CLI OAuth supports them.
The codebase already has isGemini31Model() in extra-params.ts, which proves
intent to support these models. Add a resolveGoogleGeminiCli31ForwardCompatModel
entry to resolveForwardCompatModel following the same clone-template pattern
used for zai/glm-5 and anthropic 4.6 models.
- gemini-3.1-pro-* clones gemini-3-pro-preview (with reasoning: true)
- gemini-3.1-flash-* clones gemini-3-flash-preview (with reasoning: true)
Also add test helpers and three test cases to model.forward-compat.test.ts.
Fixes#26524
* Changelog: credit Google Gemini provider fallback fixes
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
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 185f3814e9)
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 aa55439798)
