* 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)
* feat: add before_compaction and before_reset plugin hooks with session context
- Pass session messages to before_compaction hook
- Add before_reset plugin hook for /new and /reset commands
- Add sessionId to plugin hook agent context
* feat: extraBootstrapFiles config with glob pattern support
Add extraBootstrapFiles to agent defaults config, allowing glob patterns
(e.g. "projects/*/TOOLS.md") to auto-load project-level bootstrap files
into agent context every turn. Missing files silently skipped.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(status): show custom memory plugins as enabled, not unavailable
The status command probes memory availability using the built-in
memory-core manager. Custom memory plugins (e.g. via plugin slot)
can't be probed this way, so they incorrectly showed "unavailable".
Now they show "enabled (plugin X)" without the misleading label.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use async fs.glob and capture pre-compaction messages
- Replace globSync (node:fs) with fs.glob (node:fs/promises) to match
codebase conventions for async file operations
- Capture session.messages BEFORE replaceMessages(limited) so
before_compaction hook receives the full conversation history,
not the already-truncated list
* fix: resolve lint errors from CI (oxlint strict mode)
- Add void to fire-and-forget IIFE (no-floating-promises)
- Use String() for unknown catch params in template literals
- Add curly braces to single-statement if (curly rule)
* fix: resolve remaining CI lint errors in workspace.ts
- Remove `| string` from WorkspaceBootstrapFileName union (made all
typeof members redundant per no-redundant-type-constituents)
- Use type assertion for extra bootstrap file names
- Drop redundant await on fs.glob() AsyncIterable (await-thenable)
* fix: address Greptile review — path traversal guard + fs/promises import
- workspace.ts: use path.resolve() + traversal check in loadExtraBootstrapFiles()
- commands-core.ts: import fs from node:fs/promises, drop fs.promises prefix
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resolve symlinks before workspace boundary check
Greptile correctly identified that symlinks inside the workspace could
point to files outside it, bypassing the path prefix check. Now uses
fs.realpath() to resolve symlinks before verifying the real path stays
within the workspace boundary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address Greptile review — hook reliability and type safety
1. before_compaction: add compactingCount field so plugins know both
the full pre-compaction message count and the truncated count being
fed to the compaction LLM. Clarify semantics in comment.
2. loadExtraBootstrapFiles: use path.basename() for the name field
so "projects/quaid/TOOLS.md" maps to the known "TOOLS.md" type
instead of an invalid WorkspaceBootstrapFileName cast.
3. before_reset: fire the hook even when no session file exists.
Previously, short sessions without a persisted file would silently
skip the hook. Now fires with empty messages array so plugins
always know a reset occurred.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: validate bootstrap filenames and add compaction hook timeout
- Only load extra bootstrap files whose basename matches a recognized
workspace filename (AGENTS.md, TOOLS.md, etc.), preventing arbitrary
files from being injected into agent context.
- Wrap before_compaction hook in a 30-second Promise.race timeout so
misbehaving plugins cannot stall the compaction pipeline.
- Clarify hook comments: before_compaction is intentionally awaited
(plugins need messages before they're discarded) but bounded.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: make before_compaction non-blocking, add sessionFile to after_compaction
- before_compaction is now true fire-and-forget — no await, no timeout.
Plugins that need full conversation data should persist it themselves
and return quickly, or use after_compaction for async processing.
- after_compaction now includes sessionFile path so plugins can read
the full JSONL transcript asynchronously. All pre-compaction messages
are preserved on disk, eliminating the need to block compaction.
- Removes Promise.race timeout pattern that didn't actually cancel
slow hooks (just raced past them while they continued running).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add sessionFile to before_compaction for parallel processing
The session JSONL already has all messages on disk before compaction
starts. By providing sessionFile in before_compaction, plugins can
read and extract data in parallel with the compaction LLM call rather
than waiting for after_compaction. This is the optimal path for memory
plugins that need the full conversation history.
sessionFile is also kept on after_compaction for plugins that only
need to act after compaction completes (analytics, cleanup, etc.).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: move bootstrap extras into bundled hook
---------
Co-authored-by: Solomon Steadman <solstead@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Clawdbot <clawdbot@alfie.local>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix: defer gateway restart until all replies are sent
Fixes a race condition where gateway config changes (e.g., enabling
plugins via iMessage) trigger an immediate SIGUSR1 restart, killing the
iMessage RPC connection before replies are delivered.
Both restart paths (config watcher and RPC-triggered) now defer until
all queued operations, pending replies, and embedded agent runs complete
(polling every 500ms, 30s timeout). A shared emitGatewayRestart() guard
prevents double SIGUSR1 when both paths fire simultaneously.
Key changes:
- Dispatcher registry tracks active reply dispatchers globally
- markComplete() called in finally block for guaranteed cleanup
- Pre-restart deferral hook registered at gateway startup
- Centralized extractDeliveryInfo() for session key parsing
- Post-restart sentinel messages delivered directly (not via agent)
- config-patch distinguished from config-apply in sentinel kind
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: single-source gateway restart authorization
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(agents): wait for agent idle before flushing pending tool results
When pi-agent-core's auto-retry mechanism handles overloaded/rate-limit
errors, it resolves waitForRetry() on assistant message receipt — before
tool execution completes in the retried agent loop. This causes the
attempt's finally block to call flushPendingToolResults() while tools
are still executing, inserting synthetic 'missing tool result' errors
and causing silent agent failures.
The fix adds a waitForIdle() call before the flush to ensure the agent's
retry loop (including tool execution) has fully completed.
Evidence from real session: tool call and synthetic error were only 53ms
apart — the tool never had a chance to execute before being flushed.
Root cause is in pi-agent-core's _resolveRetry() firing on message_end
instead of agent_end, but this workaround in OpenClaw prevents the
symptom without requiring an upstream fix.
Fixes#8643Fixes#13351
Refs #6682, #12595
* test: add tests for tool result flush race condition
Validates that:
- Real tool results are not replaced by synthetic errors when they arrive in time
- Flush correctly inserts synthetic errors for genuinely orphaned tool calls
- Flush is a no-op after real tool results have already been received
Refs #8643, #13748
* fix(agents): add waitForIdle to all flushPendingToolResults call sites
The original fix only covered the main run finally block, but there are
two additional call sites that can trigger flushPendingToolResults while
tools are still executing:
1. The catch block in attempt.ts (session setup error handler)
2. The finally block in compact.ts (compaction teardown)
Both now await agent.waitForIdle() with a 30s timeout before flushing,
matching the pattern already applied to the main finally block.
Production testing on VPS with debug logging confirmed these additional
paths can fire during sub-agent runs, producing spurious synthetic
'missing tool result' errors.
* fix(agents): centralize idle-wait flush and clear timeout handle
---------
Co-authored-by: Renue Development <dev@renuebyscience.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* Agents: allow gpt-5.3-codex-spark in fallback and thinking
* Fix: model picker issue for openai-codex/gpt-5.3-codex-spark
Fixed an issue in the model picker.
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>
Two fixes for Google Antigravity (Cloud Code Assist) reliability:
1. Forward-compat model fallback: pi-ai's model registry doesn't include
claude-opus-4-6-thinking. Add resolveAntigravityOpus46ForwardCompatModel()
that clones the opus-4-5 template so the correct api ("google-gemini-cli")
and baseUrl are preserved. Fixes#13765.
2. Fix thinking.signature rejection: The API returns Claude thinking blocks
without signatures, then rejects them on replay. The existing sanitizer
strips unsigned blocks, but the orphaned-user-message path in attempt.ts
bypassed it by reading directly from disk. Now applies
sanitizeAntigravityThinkingBlocks at that code path.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Move appendCacheTtlTimestamp() to after prompt + compaction retry
completes instead of before. The previous placement inserted a custom
entry (openclaw.cache-ttl) between compaction and the next prompt,
which broke pi-coding-agent's prepareCompaction() guard — the guard
only checks if the last entry is type 'compaction', and the cache-ttl
custom entry made it type 'custom', allowing an immediate second
compaction at very low token counts (e.g. 5,545 tokens) that nuked
all preserved context.
Fixes#9282
Relates to #12170
