Add a `spawn` action to the /subagents command handler that invokes
spawnSubagentDirect() to deterministically launch a named subagent.
Usage: /subagents spawn <agentId> <task> [--model <model>] [--thinking <level>]
Also includes the shared subagent-spawn module extraction (same as the
refactor/extract-shared-subagent-spawn branch) since it hasn't merged yet.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* 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)
* refactor: update cron job wake mode and run mode handling
- Changed default wake mode from 'next-heartbeat' to 'now' in CronJobEditor and related CLI commands.
- Updated cron-tool tests to reflect changes in run mode, introducing 'due' and 'force' options.
- Enhanced cron-tool logic to handle new run modes and ensure compatibility with existing job structures.
- Added new tests for delivery plan consistency and job execution behavior under various conditions.
- Improved normalization functions to handle wake mode and session target casing.
This refactor aims to streamline cron job configurations and enhance the overall user experience with clearer defaults and improved functionality.
* test: enhance cron job functionality and UI
- Added tests to ensure the isolated agent correctly announces the final payload text when delivering messages via Telegram.
- Implemented a new function to pick the last deliverable payload from a list of delivery payloads.
- Enhanced the cron service to maintain legacy "every" jobs while minute cron jobs recompute schedules.
- Updated the cron store migration tests to verify the addition of anchorMs to legacy every schedules.
- Improved the UI for displaying cron job details, including job state and delivery information, with new styles and layout adjustments.
These changes aim to improve the reliability and user experience of the cron job system.
* test: enhance sessions thinking level handling
- Added tests to verify that the correct thinking levels are applied during session spawning.
- Updated the sessions-spawn-tool to include a new parameter for overriding thinking levels.
- Enhanced the UI to support additional thinking levels, including "xhigh" and "full", and improved the handling of current options in dropdowns.
These changes aim to improve the flexibility and accuracy of thinking level configurations in session management.
* feat: enhance session management and cron job functionality
- Introduced passthrough arguments in the test-parallel script to allow for flexible command-line options.
- Updated session handling to hide cron run alias session keys from the sessions list, improving clarity.
- Enhanced the cron service to accurately record job start times and durations, ensuring better tracking of job execution.
- Added tests to verify the correct behavior of the cron service under various conditions, including zero-delay timers.
These changes aim to improve the usability and reliability of session and cron job management.
* feat: implement job running state checks in cron service
- Added functionality to prevent manual job runs if a job is already in progress, enhancing job management.
- Updated the `isJobDue` function to include checks for running jobs, ensuring accurate scheduling.
- Enhanced the `run` function to return a specific reason when a job is already running.
- Introduced a new test case to verify the behavior of forced manual runs during active job execution.
These changes aim to improve the reliability and clarity of cron job execution and management.
* feat: add session ID and key to CronRunLogEntry model
- Introduced `sessionid` and `sessionkey` properties to the `CronRunLogEntry` struct for enhanced tracking of session-related information.
- Updated the initializer and Codable conformance to accommodate the new properties, ensuring proper serialization and deserialization.
These changes aim to improve the granularity of logging and session management within the cron job system.
* fix: improve session display name resolution
- Updated the `resolveSessionDisplayName` function to ensure that both label and displayName are trimmed and default to an empty string if not present.
- Enhanced the logic to prevent returning the key if it matches the label or displayName, improving clarity in session naming.
These changes aim to enhance the accuracy and usability of session display names in the UI.
* perf: skip cron store persist when idle timer tick produces no changes
recomputeNextRuns now returns a boolean indicating whether any job
state was mutated. The idle path in onTimer only persists when the
return value is true, eliminating unnecessary file writes every 60s
for far-future or idle schedules.
* fix: prep for merge - explicit delivery mode migration, docs + changelog (#10776) (thanks @tyler6204)
When spawning a subagent, the requesterOrigin's threadId, to, and
accountId were not forwarded to the callGateway({method:'agent'}) params.
This meant the subagent's runContext had no currentThreadTs or
currentChannelId, so resolveTelegramAutoThreadId could not auto-inject
the forum topic thread ID when the subagent used the message tool.
Changes:
- sessions-spawn-tool: pass to, accountId, threadId from requesterOrigin
- run-context: populate currentChannelId from opts.to as fallback
Fixes subagent messages landing in General Topic instead of the correct
Telegram DM topic thread.
* feat(config): add subagent default thinking
* fix: accept config subagents.thinking + stabilize test mocks (#7372) (thanks @tyler6204)
* fix: use findLast instead of clearAllMocks in test (#7372)
* fix: correct test assertions for tool result structure (#7372)
* fix: remove unnecessary type assertion after rebase
When a cron job runs in isolated mode, the sessions_spawn tool now correctly
inherits the allowAgents permissions from the parent agent's config.
The fix adds a requesterAgentIdOverride parameter that flows through the
tool creation chain:
- resolveEffectiveToolPolicy() extracts the correct agentId from the session key
- This agentId is passed to sessions_spawn and agents_list tools
- The tools use this override instead of re-parsing the session key
This fixes#1767
Replaces Type.Integer with Type.Number and simplifies the sessions_send tool schema to avoid anyOf/oneOf unions that cause 400 errors with Google Cloud Code Assist API.
- Add `label` field to session entries and expose it in `sessions.list`
- Display label column in the web UI sessions table
- Support `label` parameter in `sessions_send` for lookup by label instead of sessionKey
- `sessions.patch`: Accept and store `label` field
- `sessions.list`: Return `label` in session entries
- `sessions_spawn`: Pass label through to registry and announce flow
- `sessions_send`: Accept optional `label` param, lookup session by label if sessionKey not provided
- `agent` method: Accept `label` and `spawnedBy` params (stored in session entry)
- Add `label` column to sessions table in web UI
- Changed session store writes to merge with existing entry (`{ ...existing, ...new }`)
to preserve fields like `label` that might be set separately
We attempted to implement label persistence "properly" by passing the label
through the `agent` call and storing it during session initialization. However,
the auto-reply flow has multiple write points that overwrite the session entry,
and making all of them merge-aware proved unreliable.
The working solution patches the label in the `finally` block of
`runSubagentAnnounceFlow`, after all other session writes complete.
This is a workaround but robust - the patch happens at the very end,
just before potential cleanup.
A future refactor could make session writes consistently merge-based,
which would allow the cleaner approach of setting label at spawn time.
```typescript
// Spawn with label
sessions_spawn({ task: "...", label: "my-worker" })
// Later, find by label
sessions_send({ label: "my-worker", message: "continue..." })
// Or use sessions_list to see labels
sessions_list() // includes label field in response
```
