Agents: add nested subagent orchestration controls and reduce subagent token waste#14447
Merged
Agents: add nested subagent orchestration controls and reduce subagent token waste#14447
Conversation
openclaw-barnacle
bot
added
docs
|
The formal models extracted constants ( This check is informational (not blocking merges yet). If this change is intentional, follow up by updating the formal models repo or regenerating the extracted artifacts there. |
1 similar comment
|
The formal models extracted constants ( This check is informational (not blocking merges yet). If this change is intentional, follow up by updating the formal models repo or regenerating the extracted artifacts there. |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Comment on lines
42
to
46
| timeout: Type.Optional( | ||
| Type.Number({ | ||
| description: "For poll: wait up to this many milliseconds before returning", | ||
| }), | ||
| ), |
Contributor
There was a problem hiding this comment.
Schema/handler mismatch
processSchema declares timeout as a number (Type.Number), but the execute path accepts timeout?: number | string and resolvePollWaitMs explicitly parses string values. Any tool-arg schema validation will reject string timeouts even though they’re intended to work here, so callers passing "5000" will fail before reaching resolvePollWaitMs.
Prompt To Fix With AI
This is a comment left during a code review.
Path: src/agents/bash-tools.process.ts
Line: 42:46
Comment:
**Schema/handler mismatch**
`processSchema` declares `timeout` as a number (`Type.Number`), but the execute path accepts `timeout?: number | string` and `resolvePollWaitMs` explicitly parses string values. Any tool-arg schema validation will reject string timeouts even though they’re intended to work here, so callers passing `"5000"` will fail before reaching `resolvePollWaitMs`.
How can I resolve this? If you propose a fix, please make it concise.
Comment on lines
+444
to
+456
| let activeChildDescendantRuns = 0; | ||
| try { | ||
| const { countActiveDescendantRuns } = await import("./subagent-registry.js"); | ||
| activeChildDescendantRuns = Math.max(0, countActiveDescendantRuns(params.childSessionKey)); | ||
| } catch { | ||
| // Best-effort only; fall back to direct announce behavior when unavailable. | ||
| } | ||
| if (activeChildDescendantRuns > 0) { | ||
| // The finished run still has active descendant subagents. Defer announcing | ||
| // this run until descendants settle so we avoid posting in-progress updates. | ||
| shouldDeleteChildSession = false; | ||
| return false; | ||
| } |
Contributor
There was a problem hiding this comment.
Deferred announce marked done
When activeChildDescendantRuns > 0, this path says it’s deferring the announce, but it sets didAnnounce = true and returns true. subagent-registry.finalizeSubagentCleanup treats a true return as “announce handled” and won’t retry, so the parent run’s completion can be permanently skipped once descendants finish.
Prompt To Fix With AI
This is a comment left during a code review.
Path: src/agents/subagent-announce.ts
Line: 444:456
Comment:
**Deferred announce marked done**
When `activeChildDescendantRuns > 0`, this path says it’s deferring the announce, but it sets `didAnnounce = true` and returns `true`. `subagent-registry.finalizeSubagentCleanup` treats a `true` return as “announce handled” and won’t retry, so the parent run’s completion can be permanently skipped once descendants finish.
How can I resolve this? If you propose a fix, please make it concise.![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 882badba0a
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Comment on lines
548
to
552
| await callGateway({ | ||
| method: "agent", | ||
| params: { | ||
| sessionKey: params.requesterSessionKey, | ||
| sessionKey: targetRequesterSessionKey, | ||
| message: triggerMessage, |
There was a problem hiding this comment.
This announce dispatch no longer uses expectFinal: true, so the gateway call resolves on the initial status: "accepted" ack rather than the final run result. runSubagentAnnounceFlow then marks the announce as successful and cleanup proceeds, which means a later failure in the queued announce run (model/auth/runtime error) is never retried and the user-facing subagent completion update can be silently dropped.
Useful? React with 👍 / 👎.
Comment on lines
+355
to
+357
| return { | ||
| requesterSessionKey: spawnedBy || callerSessionKey, | ||
| callerSessionKey, |
There was a problem hiding this comment.
Leaf subagents are remapped to their parent requester scope here, and later subagents actions (kill/steer) run against that scope without a depth/orchestrator gate. In practice, a depth-2 worker can kill or steer sibling runs that it did not spawn, which contradicts the policy intent that leaf subagents access is for visibility/status only and can disrupt unrelated parallel work.
Useful? React with 👍 / 👎.
tyler6204
force-pushed
the
codex/subagent-improvements
branch
from
e84167c to
4e476ae
Compare
|
The formal models extracted constants ( This check is informational (not blocking merges yet). If this change is intentional, follow up by updating the formal models repo or regenerating the extracted artifacts there. |
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
force-pushed
the
codex/subagent-improvements
branch
from
eadcb8e to
68e492e
Compare
|
The formal models extracted constants ( This check is informational (not blocking merges yet). If this change is intentional, follow up by updating the formal models repo or regenerating the extracted artifacts there. |
tyler6204
force-pushed
the
codex/subagent-improvements
branch
from
68e492e to
53ff09c
Compare
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
tyler6204
force-pushed
the
codex/subagent-improvements
branch
from
53ff09c to
17a46ef
Compare
tyler6204
added a commit
that referenced
this pull request
Feb 15, 2026
- 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.
… 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.
- 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.
tyler6204
force-pushed
the
codex/subagent-improvements
branch
from
a14a1e5 to
aa44a9c
Compare
Member
Author
|
Merged via squash.
Thanks @tyler6204! |
|
The formal models extracted constants ( This check is informational (not blocking merges yet). If this change is intentional, follow up by updating the formal models repo or regenerating the extracted artifacts there. |
This was referenced Feb 15, 2026
GwonHyeok
pushed a commit
to learners-superpumped/openclaw
that referenced
this pull request
Feb 15, 2026
…t token waste (openclaw#14447) * 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 (openclaw#14447) (thanks @tyler6204) * fix: restore cron delivery-plan import after rebase (openclaw#14447) (thanks @tyler6204) * fix: resolve test failures from rebase conflicts (openclaw#14447) (thanks @tyler6204) * fix: apply formatting after rebase (openclaw#14447) (thanks @tyler6204)
Benkei-dev
pushed a commit
to Benkei-dev/openclaw
that referenced
this pull request
Feb 15, 2026
…t token waste (openclaw#14447) * 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 (openclaw#14447) (thanks @tyler6204) * fix: restore cron delivery-plan import after rebase (openclaw#14447) (thanks @tyler6204) * fix: resolve test failures from rebase conflicts (openclaw#14447) (thanks @tyler6204) * fix: apply formatting after rebase (openclaw#14447) (thanks @tyler6204)
This was referenced Feb 17, 2026
This was referenced Feb 18, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds first-class nested subagent orchestration for both users and models, improves subagent control UX/reliability, and reduces token waste during long-running shell waits.
What changed
subagentstool with actions:liststeerkillsubagentsinto core tools, policy groups, sandbox default allowlists, system prompt guidance, and tool display metadata.agents.defaults.subagents.maxSpawnDepth(default behavior remains depth 1)agents.defaults.subagents.maxChildrenPerAgent(per-parent active child cap)spawnDepthpersistence + gateway patch/schema supportmaxSpawnDepth >= 2/subagents list|stop|kill|log|info|send|steer/kill <id|#|all>/steer <id|#> <message>/tell <id|#> <message>Behavior updates
agent.wait) before restart.sessionIdso the steer message appends to the same conversation.0(no 10-minute default timeout fallback)./subagents stop|kill|steer/kill,/steer,/tellsubagentstoolkill|steer[System Message].Reliability fixes (timeout/model/restart)
0inagentcommand handling when timeout is omitted.openai/gpt-5.3-codex*toopenai-codex/...so fallback/cooldown behavior keys match provider identity.Registry + test isolation fixes
OPENCLAW_STATE_DIRis unset, preventing writes into real user state.Token reporting fixes/clarity
subagentslist (tool + slash command) and announce stats now show usage as:tokens X (in A / out B)for actual I/O, andprompt/cache Ywhen prompt/cache/context cost is larger than I/O.tokens ... io (...).Tooling optimization for long waits
process.polltimeout support (timeoutin ms) so a single poll can wait for completion instead of repeated short poll loops.execwith sufficientyieldMs, orprocess(action=poll, timeout=...)to reduce unnecessary polling turns and token churn.
Additional fixes bundled in this branch
spawnDepthwhen agent handler rewrites session entries.Tests
subagentstool schema and behavior/kill,/steer,/tell)tokens ... (in/out),prompt/cache ...)subagentsprocess poll timeoutbehavioragent.waitbefore restart, samesessionId, timeout0)openaicodex model/provider normalization in model selection + fallback executionValidation run
pnpm vitest src/auto-reply/reply/commands.test.tspnpm vitest src/agents/openclaw-tools.sessions.test.tspnpm vitest src/agents/subagent-registry.steer-restart.test.tspnpm vitest src/agents/model-selection.test.ts src/agents/model-fallback.test.tspnpm vitest src/infra/restart-sentinel.test.ts src/infra/process-respawn.test.tspnpm vitest src/agents/subagent-registry.persistence.test.ts src/auto-reply/reply/abort.test.tspnpm checkGreptile Overview
Greptile Summary
This PR adds nested sub-agent orchestration controls (model
subagentstool + new/kill,/steer,/tellcommand UX), introduces spawn-depth persistence/limits, and updates announce routing so descendant results can bubble correctly without leaking internal context.Key codepaths touched include the subagent registry (termination + steer-restart suppression/replacement), announce flow (internal
[System Message]tagging + depth-aware routing), model selection/fallback normalization, and the process tool (polltimeoutwait support to reduce polling turns).Confidence Score: 3/5
processtool that will reject valid intended inputs for some clients, and (2) a deferred-announce path that is treated as completed, potentially dropping parent completion announcements permanently.