* feat(context-engine): add ContextEngine interface and registry
Introduce the pluggable ContextEngine abstraction that allows external
plugins to register custom context management strategies.
- ContextEngine interface with lifecycle methods: bootstrap, ingest,
ingestBatch, afterTurn, assemble, compact, prepareSubagentSpawn,
onSubagentEnded, dispose
- Module-level singleton registry with registerContextEngine() and
resolveContextEngine() (config-driven slot selection)
- LegacyContextEngine: pass-through implementation wrapping existing
compaction behavior for 100% backward compatibility
- ensureContextEnginesInitialized() guard for safe one-time registration
- 19 tests covering contract, registry, resolution, and legacy parity
* feat(plugins): add context-engine slot and registerContextEngine API
Wire the ContextEngine abstraction into the plugin system so external
plugins can register context engines via the standard plugin API.
- Add 'context-engine' to PluginKind union type
- Add 'contextEngine' slot to PluginSlotsConfig (default: 'legacy')
- Wire registerContextEngine() through OpenClawPluginApi
- Export ContextEngine types from plugin-sdk for external consumers
- Restore proper slot-based resolution in registry
* feat(context-engine): wire ContextEngine into agent run lifecycle
Integrate the ContextEngine abstraction into the core agent run path:
- Resolve context engine once per run (reused across retries)
- Bootstrap: hydrate canonical store from session file on first run
- Assemble: route context assembly through pluggable engine
- Auto-compaction guard: disable built-in auto-compaction when
the engine declares ownsCompaction (prevents double-compaction)
- AfterTurn: post-turn lifecycle hook for ingest + background
compaction decisions
- Overflow compaction: route through contextEngine.compact()
- Dispose: clean up engine resources in finally block
- Notify context engine on subagent lifecycle events
Legacy engine: all lifecycle methods are pass-through/no-op, preserving
100% backward compatibility for users without a context engine plugin.
* feat(plugins): add scoped subagent methods and gateway request scope
Expose runtime.subagent.{run, waitForRun, getSession, deleteSession}
so external plugins can spawn sub-agent sessions without raw gateway
dispatch access.
Uses AsyncLocalStorage request-scope bridge to dispatch internally via
handleGatewayRequest with a synthetic operator client. Methods are only
available during gateway request handling.
- Symbol.for-backed global singleton for cross-module-reload safety
- Fallback gateway context for non-WS dispatch paths (Telegram/WhatsApp)
- Set gateway request scope for all handlers, not just plugin handlers
- 3 staleness tests for fallback context hardening
* feat(context-engine): route /compact and sessions.get through context engine
Wire the /compact command and sessions.get handler through the pluggable
ContextEngine interface.
- Thread tokenBudget and force parameters to context engine compact
- Route /compact through contextEngine.compact() when registered
- Wire sessions.get as runtime alias for plugin subagent dispatch
- Add .pebbles/ to .gitignore
* style: format with oxfmt 0.33.0
Fix duplicate import (ControlUiRootState in server.impl.ts) and
import ordering across all changed files.
* fix: update extension test mocks for context-engine types
Add missing subagent property to bluebubbles PluginRuntime mock.
Add missing registerContextEngine to lobster OpenClawPluginApi mock.
* fix(subagents): keep deferred delete cleanup retryable
* style: format run attempt for CI
* fix(rebase): remove duplicate embedded-run imports
* test: add missing gateway context mock export
* fix: pass resolved auth profile into afterTurn compaction
Ensure the embedded runner forwards resolved auth profile context into
legacy context-engine compaction params on the normal afterTurn path,
matching overflow compaction behavior. This allows downstream LCM
summarization to use the intended provider auth/profile consistently.
Also fix strict TS typing in external-link token dedupe and align an
attempt unit test reasoningLevel value with the current ReasoningLevel
enum.
Regeneration-Prompt: |
We were debugging context-engine compaction where downstream summary
calls were missing the right auth/profile context in normal afterTurn
flow, while overflow compaction already propagated it. Preserve current
behavior and keep changes additive: thread the resolved authProfileId
through run -> attempt -> legacy compaction param builder without
broad refactors.
Add tests that prove the auth profile is included in afterTurn legacy
params and that overflow compaction still passes it through run
attempts. Keep existing APIs stable, and only adjust small type issues
needed for strict compilation.
* fix: remove duplicate imports from rebase
* feat: add context-engine system prompt additions
* fix(rebase): dedupe attempt import declarations
* test: fix fetch mock typing in ollama autodiscovery
* fix(test): add registerContextEngine to diffs extension mock APIs
* test(windows): use path.delimiter in ios-team-id fixture PATH
* test(cron): add model formatting and precedence edge case tests
Covers:
- Provider/model string splitting (whitespace, nested paths, empty segments)
- Provider normalization (casing, aliases like bedrock→amazon-bedrock)
- Anthropic model alias normalization (opus-4.5→claude-opus-4-5)
- Precedence: job payload > session override > config default
- Sequential runs with different providers (CI flake regression pattern)
- forceNew session preserving stored model overrides
- Whitespace/empty model string edge cases
- Config model as string vs object format
* test(cron): fix model formatting test config types
* test(phone-control): add registerContextEngine to mock API
* fix: re-export ChannelKind from config-reload-plan
* fix: add subagent mock to plugin-runtime-mock test util
* docs: add changelog fragment for context engine PR #22201
* fix(gateway): flush throttled delta before emitChatFinal
The 150ms throttle in emitChatDelta can suppress the last text chunk
before emitChatFinal fires, causing streaming clients (e.g. ACP) to
receive truncated responses. The final event carries the complete text,
but clients that build responses incrementally from deltas miss the
tail end.
Flush one last unthrottled delta with the complete buffered text
immediately before sending the final event. This ensures all streaming
consumers have the full response without needing to reconcile deltas
against the final payload.
* fix(gateway): avoid duplicate delta flush when buffer unchanged
Track the text length at the time of the last broadcast. The flush in
emitChatFinal now only sends a delta if the buffer has grown since the
last broadcast, preventing duplicate sends when the final delta passed
the 150ms throttle and was already broadcast.
* fix(gateway): honor heartbeat suppression in final delta flush
* test(gateway): add final delta flush and dedupe coverage
* fix(gateway): skip final flush for silent lead fragments
* docs(changelog): note gateway final-delta flush fix credits
---------
Co-authored-by: Jonathan Taylor <visionik@pobox.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* 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>
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.
* 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: 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>
A timeout is model/network-specific, not an auth issue. Marking the
auth profile as failed on timeout poisons fallback models on the same
provider (e.g. gpt-5.3 timeout would block gpt-5.2 via shared profile
cooldown). The prompt-phase path already guards against this; this
aligns the post-response timeout path to match.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove the `overflowCompactionAttempts = 0` reset inside the inner loop's
tool-result-truncation branch. The counter was being zeroed on each truncation
cycle, allowing prompt-injection attacks to bypass the MAX_OVERFLOW_COMPACTION_ATTEMPTS
guard and trigger unbounded auto-compaction, exhausting context window resources (DoS).
CWE-400 / GHSA-x2g4-7mj7-2hhj
recordAssistantUsage accumulated cacheRead across the entire multi-turn
run, and totalTokens was clamped to contextTokens. This caused
session_status to report 100% context usage regardless of actual load.
Changes:
- run.ts: capture lastTurnTotal from the most recent model call and
inject it into the normalized usage before it reaches agentMeta.
- usage-reporting.test.ts: verify usage.total reflects current turn,
not accumulated total.
Fixes#17016
Wire media URL tracking through the embedded agent pipeline so that
media already sent via messaging tools is not delivered again by the
reply dispatcher.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enable plugins to override the model and provider for agent runs by
returning modelOverride/providerOverride from the before_agent_start
hook. The hook is now invoked early in run.ts (before resolveModel)
so overrides take effect. The result is passed to attempt.ts via
earlyHookResult to prevent double-firing.
This enables security-critical use cases like routing PII-containing
prompts to local models instead of cloud providers.
* Agents: add subagent orchestration controls
* Agents: add subagent orchestration controls (WIP uncommitted changes)
* feat(subagents): add depth-based spawn gating for sub-sub-agents
* feat(subagents): tool policy, registry, and announce chain for nested agents
* feat(subagents): system prompt, docs, changelog for nested sub-agents
* fix(subagents): prevent model fallback override, show model during active runs, and block context overflow fallback
Bug 1: When a session has an explicit model override (e.g., gpt/openai-codex),
the fallback candidate logic in resolveFallbackCandidates silently appended the
global primary model (opus) as a backstop. On reinjection/steer with a transient
error, the session could fall back to opus which has a smaller context window
and crash. Fix: when storedModelOverride is set, pass fallbacksOverride ?? []
instead of undefined, preventing the implicit primary backstop.
Bug 2: Active subagents showed 'model n/a' in /subagents list because
resolveModelDisplay only read entry.model/modelProvider (populated after run
completes). Fix: fall back to modelOverride/providerOverride fields which are
populated at spawn time via sessions.patch.
Bug 3: Context overflow errors (prompt too long, context_length_exceeded) could
theoretically escape runEmbeddedPiAgent and be treated as failover candidates
in runWithModelFallback, causing a switch to a model with a smaller context
window. Fix: in runWithModelFallback, detect context overflow errors via
isLikelyContextOverflowError and rethrow them immediately instead of trying the
next model candidate.
* fix(subagents): track spawn depth in session store and fix announce routing for nested agents
* Fix compaction status tracking and dedupe overflow compaction triggers
* fix(subagents): enforce depth block via session store and implement cascade kill
* fix: inject group chat context into system prompt
* fix(subagents): always write model to session store at spawn time
* Preserve spawnDepth when agent handler rewrites session entry
* fix(subagents): suppress announce on steer-restart
* fix(subagents): fallback spawned session model to runtime default
* fix(subagents): enforce spawn depth when caller key resolves by sessionId
* feat(subagents): implement active-first ordering for numeric targets and enhance task display
- Added a test to verify that subagents with numeric targets follow an active-first list ordering.
- Updated `resolveSubagentTarget` to sort subagent runs based on active status and recent activity.
- Enhanced task display in command responses to prevent truncation of long task descriptions.
- Introduced new utility functions for compacting task text and managing subagent run states.
* fix(subagents): show model for active runs via run record fallback
When the spawned model matches the agent's default model, the session
store's override fields are intentionally cleared (isDefault: true).
The model/modelProvider fields are only populated after the run
completes. This left active subagents showing 'model n/a'.
Fix: store the resolved model on SubagentRunRecord at registration
time, and use it as a fallback in both display paths (subagents tool
and /subagents command) when the session store entry has no model info.
Changes:
- SubagentRunRecord: add optional model field
- registerSubagentRun: accept and persist model param
- sessions-spawn-tool: pass resolvedModel to registerSubagentRun
- subagents-tool: pass run record model as fallback to resolveModelDisplay
- commands-subagents: pass run record model as fallback to resolveModelDisplay
* feat(chat): implement session key resolution and reset on sidebar navigation
- Added functions to resolve the main session key and reset chat state when switching sessions from the sidebar.
- Updated the `renderTab` function to handle session key changes when navigating to the chat tab.
- Introduced a test to verify that the session resets to "main" when opening chat from the sidebar navigation.
* fix: subagent timeout=0 passthrough and fallback prompt duplication
Bug 1: runTimeoutSeconds=0 now means 'no timeout' instead of applying 600s default
- sessions-spawn-tool: default to undefined (not 0) when neither timeout param
is provided; use != null check so explicit 0 passes through to gateway
- agent.ts: accept 0 as valid timeout (resolveAgentTimeoutMs already handles
0 → MAX_SAFE_TIMEOUT_MS)
Bug 2: model fallback no longer re-injects the original prompt as a duplicate
- agent.ts: track fallback attempt index; on retries use a short continuation
message instead of the full original prompt since the session file already
contains it from the first attempt
- Also skip re-sending images on fallback retries (already in session)
* feat(subagents): truncate long task descriptions in subagents command output
- Introduced a new utility function to format task previews, limiting their length to improve readability.
- Updated the command handler to use the new formatting function, ensuring task descriptions are truncated appropriately.
- Adjusted related tests to verify that long task descriptions are now truncated in the output.
* refactor(subagents): update subagent registry path resolution and improve command output formatting
- Replaced direct import of STATE_DIR with a utility function to resolve the state directory dynamically.
- Enhanced the formatting of command output for active and recent subagents, adding separators for better readability.
- Updated related tests to reflect changes in command output structure.
* fix(subagent): default sessions_spawn to no timeout when runTimeoutSeconds omitted
The previous fix (75a791106) correctly handled the case where
runTimeoutSeconds was explicitly set to 0 ("no timeout"). However,
when models omit the parameter entirely (which is common since the
schema marks it as optional), runTimeoutSeconds resolved to undefined.
undefined flowed through the chain as:
sessions_spawn → timeout: undefined (since undefined != null is false)
→ gateway agent handler → agentCommand opts.timeout: undefined
→ resolveAgentTimeoutMs({ overrideSeconds: undefined })
→ DEFAULT_AGENT_TIMEOUT_SECONDS (600s = 10 minutes)
This caused subagents to be killed at exactly 10 minutes even though
the user's intent (via TOOLS.md) was for subagents to run without a
timeout.
Fix: default runTimeoutSeconds to 0 (no timeout) when neither
runTimeoutSeconds nor timeoutSeconds is provided by the caller.
Subagent spawns are long-running by design and should not inherit the
600s agent-command default timeout.
* fix(subagent): accept timeout=0 in agent-via-gateway path (second 600s default)
* fix: thread timeout override through getReplyFromConfig dispatch path
getReplyFromConfig called resolveAgentTimeoutMs({ cfg }) with no override,
always falling back to the config default (600s). Add timeoutOverrideSeconds
to GetReplyOptions and pass it through as overrideSeconds so callers of the
dispatch chain can specify a custom timeout (0 = no timeout).
This complements the existing timeout threading in agentCommand and the
cron isolated-agent runner, which already pass overrideSeconds correctly.
* feat(model-fallback): normalize OpenAI Codex model references and enhance fallback handling
- Added normalization for OpenAI Codex model references, specifically converting "gpt-5.3-codex" to "openai-codex" before execution.
- Updated the `resolveFallbackCandidates` function to utilize the new normalization logic.
- Enhanced tests to verify the correct behavior of model normalization and fallback mechanisms.
- Introduced a new test case to ensure that the normalization process works as expected for various input formats.
* feat(tests): add unit tests for steer failure behavior in openclaw-tools
- Introduced a new test file to validate the behavior of subagents when steer replacement dispatch fails.
- Implemented tests to ensure that the announce behavior is restored correctly and that the suppression reason is cleared as expected.
- Enhanced the subagent registry with a new function to clear steer restart suppression.
- Updated related components to support the new test scenarios.
* fix(subagents): replace stop command with kill in slash commands and documentation
- Updated the `/subagents` command to replace `stop` with `kill` for consistency in controlling sub-agent runs.
- Modified related documentation to reflect the change in command usage.
- Removed legacy timeoutSeconds references from the sessions-spawn-tool schema and tests to streamline timeout handling.
- Enhanced tests to ensure correct behavior of the updated commands and their interactions.
* feat(tests): add unit tests for readLatestAssistantReply function
- Introduced a new test file for the `readLatestAssistantReply` function to validate its behavior with various message scenarios.
- Implemented tests to ensure the function correctly retrieves the latest assistant message and handles cases where the latest message has no text.
- Mocked the gateway call to simulate different message histories for comprehensive testing.
* feat(tests): enhance subagent kill-all cascade tests and announce formatting
- Added a new test to verify that the `kill-all` command cascades through ended parents to active descendants in subagents.
- Updated the subagent announce formatting tests to reflect changes in message structure, including the replacement of "Findings:" with "Result:" and the addition of new expectations for message content.
- Improved the handling of long findings and stats in the announce formatting logic to ensure concise output.
- Refactored related functions to enhance clarity and maintainability in the subagent registry and tools.
* refactor(subagent): update announce formatting and remove unused constants
- Modified the subagent announce formatting to replace "Findings:" with "Result:" and adjusted related expectations in tests.
- Removed constants for maximum announce findings characters and summary words, simplifying the announcement logic.
- Updated the handling of findings to retain full content instead of truncating, ensuring more informative outputs.
- Cleaned up unused imports in the commands-subagents file to enhance code clarity.
* feat(tests): enhance billing error handling in user-facing text
- Added tests to ensure that normal text mentioning billing plans is not rewritten, preserving user context.
- Updated the `isBillingErrorMessage` and `sanitizeUserFacingText` functions to improve handling of billing-related messages.
- Introduced new test cases for various scenarios involving billing messages to ensure accurate processing and output.
- Enhanced the subagent announce flow to correctly manage active descendant runs, preventing premature announcements.
* feat(subagent): enhance workflow guidance and auto-announcement clarity
- Added a new guideline in the subagent system prompt to emphasize trust in push-based completion, discouraging busy polling for status updates.
- Updated documentation to clarify that sub-agents will automatically announce their results, improving user understanding of the workflow.
- Enhanced tests to verify the new guidance on avoiding polling loops and to ensure the accuracy of the updated prompts.
* fix(cron): avoid announcing interim subagent spawn acks
* chore: clean post-rebase imports
* fix(cron): fall back to child replies when parent stays interim
* fix(subagents): make active-run guidance advisory
* fix(subagents): update announce flow to handle active descendants and enhance test coverage
- Modified the announce flow to defer announcements when active descendant runs are present, ensuring accurate status reporting.
- Updated tests to verify the new behavior, including scenarios where no fallback requester is available and ensuring proper handling of finished subagents.
- Enhanced the announce formatting to include an `expectFinal` flag for better clarity in the announcement process.
* fix(subagents): enhance announce flow and formatting for user updates
- Updated the announce flow to provide clearer instructions for user updates based on active subagent runs and requester context.
- Refactored the announcement logic to improve clarity and ensure internal context remains private.
- Enhanced tests to verify the new message expectations and formatting, including updated prompts for user-facing updates.
- Introduced a new function to build reply instructions based on session context, improving the overall announcement process.
* fix: resolve prep blockers and changelog placement (#14447) (thanks @tyler6204)
* fix: restore cron delivery-plan import after rebase (#14447) (thanks @tyler6204)
* fix: resolve test failures from rebase conflicts (#14447) (thanks @tyler6204)
* fix: apply formatting after rebase (#14447) (thanks @tyler6204)
The UsageAccumulator sums cacheRead/cacheWrite across all API calls
within a single turn. With Anthropic prompt caching, each call reports
cacheRead ≈ current_context_size, so after N tool-call round-trips the
accumulated total becomes N × actual_context, which gets clamped to
contextWindow (200k) by deriveSessionTotalTokens().
Fix: track the most recent API call's cache fields separately and use
them in toNormalizedUsage() for context-size reporting. This makes
/status Context display accurate while preserving accumulated output
token counts.
Fixes#13698Fixes#13782
Co-authored-by: akari-musubi <259925157+akari-musubi@users.noreply.github.com>
