cleveragents/cleveractors-core
0
0
Fork 0
Code Issues 22 Pull requests 7 Projects Releases Packages Wiki Activity Actions 373

feat(agents): inherit tool timeout ceilings from parent LLM agent #141

Open
CoreRasurae wants to merge 1 commit from feature/m1-inherit-tool-timeout-ceilings into master
pull from: feature/m1-inherit-tool-timeout-ceilings
merge into: cleveragents:master
Conversation 1 Commits 1 Files changed 11 +587 -36
CoreRasurae commented 2026-08-21 16:59:48 +00:00
Member
Copy link

Summary

  • A type: llm agent's tools_max_timeout/shell_max_timeout config now bounds the per-invocation timeout tool-call argument for shell/http_request calls that agent dispatches internally, exactly as it already does for a directly-configured type: tool agent. timeout itself already inherited correctly and is untouched.
  • All three ephemeral-ToolAgent-construction sites in LLMAgent._execute_tool_loop now share one _build_ephemeral_tool_config() helper (Template/Factory Method) instead of three near-identical inline dict literals, closing the drift that let tools_max_timeout/shell_max_timeout diverge from timeout in the first place.
  • Extends docs/adr/ADR-2030-tool-calling-spec-extensions.md with D-10 and docs/index.md §4.4 (Version 1.6.0, §21.1 Revision History) per the spec-revision procedure, since this makes the two fields usable/discoverable on a type: llm agent for the first time.
  • The per-invocation timeout tool-call argument mechanism (ADR-2030 D-9, TimeoutPolicy) is unaffected: a model-supplied override still takes precedence over the (now possibly inherited) default/ceiling for that one call.

Closes #140

Test plan

  • nox -s lint / nox -s format -- --check — green
  • nox -s typecheck — green (0 errors)
  • nox -s security_scan / nox -s dead_code — green, no findings
  • nox -s unit_tests — 154 features, 3089 scenarios, 0 failed (6 new scenarios in features/llm_agent_tool_loop.feature)
  • nox -s coverage_report — 96.9% (threshold 96.5%); no new uncovered lines
  • nox -s integration_tests — 364 Robot tests, 0 failed (2 new tests in robot/llm_tool_calling.robot)
  • nox -s benchmark_regression -- --quick — BENCHMARKS NOT SIGNIFICANTLY CHANGED (expected: config-threading only, no perf-sensitive path touched)

🤖 Generated with Claude Code

## Summary - A `type: llm` agent's `tools_max_timeout`/`shell_max_timeout` config now bounds the per-invocation `timeout` tool-call argument for `shell`/`http_request` calls that agent dispatches internally, exactly as it already does for a directly-configured `type: tool` agent. `timeout` itself already inherited correctly and is untouched. - All three ephemeral-`ToolAgent`-construction sites in `LLMAgent._execute_tool_loop` now share one `_build_ephemeral_tool_config()` helper (Template/Factory Method) instead of three near-identical inline dict literals, closing the drift that let `tools_max_timeout`/`shell_max_timeout` diverge from `timeout` in the first place. - Extends `docs/adr/ADR-2030-tool-calling-spec-extensions.md` with D-10 and `docs/index.md` §4.4 (Version 1.6.0, §21.1 Revision History) per the spec-revision procedure, since this makes the two fields usable/discoverable on a `type: llm` agent for the first time. - The per-invocation `timeout` tool-call argument mechanism (ADR-2030 D-9, `TimeoutPolicy`) is unaffected: a model-supplied override still takes precedence over the (now possibly inherited) default/ceiling for that one call. Closes #140 ## Test plan - [x] `nox -s lint` / `nox -s format -- --check` — green - [x] `nox -s typecheck` — green (0 errors) - [x] `nox -s security_scan` / `nox -s dead_code` — green, no findings - [x] `nox -s unit_tests` — 154 features, 3089 scenarios, 0 failed (6 new scenarios in `features/llm_agent_tool_loop.feature`) - [x] `nox -s coverage_report` — 96.9% (threshold 96.5%); no new uncovered lines - [x] `nox -s integration_tests` — 364 Robot tests, 0 failed (2 new tests in `robot/llm_tool_calling.robot`) - [x] `nox -s benchmark_regression -- --quick` — BENCHMARKS NOT SIGNIFICANTLY CHANGED (expected: config-threading only, no perf-sensitive path touched) 🤖 Generated with [Claude Code](https://claude.com/claude-code)
CoreRasurae added this to the v2.1.0 milestone 2026-08-21 16:59:48 +00:00
feat(agents): inherit tool timeout ceilings from parent LLM agent
Some checks failed
CI / lint (pull_request) Successful in 51s
Details
CI / typecheck (pull_request) Successful in 1m27s
Details
CI / unit_tests (pull_request) Has started running
Details
CI / benchmark (pull_request) Has started running
Details
CI / quality (pull_request) Successful in 1m12s
Details
CI / security (pull_request) Successful in 2m40s
Details
CI / build (pull_request) Successful in 1m50s
Details
CI / integration_tests (pull_request) Successful in 2m48s
Details
CI / coverage (pull_request) Has been cancelled
Details
CI / status-check (pull_request) Has been cancelled
Details
b834a518f2 
A type: llm agent dispatches its built-in shell/http_request tool calls
through an ephemeral, per-call ToolAgent it constructs internally. That
ephemeral agent's `timeout` default already came from the parent LLM
agent's own config; `tools_max_timeout`/`shell_max_timeout` did not,
so every LLM-agent-dispatched tool call was capped at the ephemeral
agent's built-in 120s ceiling no matter what the parent agent declared.

All three tool-call dispatch sites in LLMAgent._execute_tool_loop now
share a new _build_ephemeral_tool_config() helper that forwards
tools_max_timeout/shell_max_timeout from the parent's config (falling
back to ToolAgent's own defaults when absent), replacing three
near-identical inline dict literals that had already let the ceiling
fields drift out of sync with timeout. The per-invocation timeout
tool-call argument (ADR-2030 D-9) is unaffected: a model-supplied
override still takes precedence over the (now possibly inherited)
default and ceiling for that one call.

Extends docs/adr/ADR-2030-tool-calling-spec-extensions.md with D-10
and docs/index.md §4.4 (Version 1.6.0) per the spec-revision procedure,
since this makes tools_max_timeout/shell_max_timeout usable/discoverable
on a type: llm agent for the first time.

ISSUES CLOSED: #140
docs(tools): document type: llm agents honoring tools_max_timeout
Some checks failed
CI / lint (pull_request) Successful in 37s
Details
CI / integration_tests (pull_request) Has started running
Details
CI / benchmark (pull_request) Has started running
Details
CI / typecheck (pull_request) Successful in 1m27s
Details
CI / quality (pull_request) Successful in 1m29s
Details
CI / build (pull_request) Successful in 36s
Details
CI / security (pull_request) Successful in 1m46s
Details
CI / coverage (pull_request) Has been cancelled
Details
CI / status-check (pull_request) Has been cancelled
Details
CI / unit_tests (pull_request) Has been cancelled
Details
9eb8378d64 
The tool-agent user guide (docs/tools/timeouts.md, index.md,
built-in-tools.md) only described tools_max_timeout/shell_max_timeout
in the context of a type: tool agent. Adds a section and cross-links
covering the ADR-2030 D-10 behavior: a type: llm agent's own config
now accepts the same three fields for tool calls it dispatches
internally.

Refs: #140
CoreRasurae force-pushed feature/m1-inherit-tool-timeout-ceilings from 9eb8378d64
Some checks failed
CI / lint (pull_request) Successful in 37s
Details
CI / integration_tests (pull_request) Has started running
Details
CI / benchmark (pull_request) Has started running
Details
CI / typecheck (pull_request) Successful in 1m27s
Details
CI / quality (pull_request) Successful in 1m29s
Details
CI / build (pull_request) Successful in 36s
Details
CI / security (pull_request) Successful in 1m46s
Details
CI / coverage (pull_request) Has been cancelled
Details
CI / status-check (pull_request) Has been cancelled
Details
CI / unit_tests (pull_request) Has been cancelled
Details
to 49e7e263a0
Some checks failed
CI / lint (pull_request) Successful in 39s
Details
CI / quality (pull_request) Successful in 55s
Details
CI / security (pull_request) Successful in 1m21s
Details
CI / typecheck (pull_request) Successful in 1m36s
Details
CI / build (pull_request) Successful in 38s
Details
CI / integration_tests (pull_request) Successful in 2m7s
Details
CI / unit_tests (pull_request) Successful in 5m28s
Details
CI / coverage (pull_request) Failing after 11m52s
Details
CI / benchmark (pull_request) Failing after 16m36s
Details
CI / status-check (pull_request) Has been cancelled
Details
2026-08-21 17:09:31 +00:00 Compare
hurui200320 approved these changes 2026-08-22 06:21:53 +00:00
hurui200320 left a comment
Copy link

PR Review: !141 (Ticket #140)

Verdict: Approve

The implementation correctly threads tools_max_timeout and shell_max_timeout from a parent type: llm agent into the ephemeral ToolAgent instances it constructs per dispatched tool call, satisfying the functional requirements of #140. The code is clean, well-documented, and the spec/ADR updates are consistent. No critical or major issues were found.

Critical Issues

None

Major Issues

None

Minor Issues

  1. Missing Behave coverage for the post-loop stuck-model synthesis dispatch site

    • File: features/llm_agent_tool_loop.feature
    • Line: 177-182
    • Problem: The acceptance criteria require coverage "across all three dispatch sites" (normal round, budget-exhaustion synthesis, post-loop synthesis). The PR adds a scenario for the budget-exhaustion site, but the post-loop stuck-model synthesis site is not explicitly exercised. Since all three sites now call the shared _build_ephemeral_tool_config() helper, the functional risk is low, but the requirement coverage is incomplete.
    • Recommendation: Add a Behave scenario that forces the post-loop stuck-model synthesis path and asserts that the inherited tools_max_timeout ceiling is honored there.

  2. Invalid ceiling test only exercises tools_max_timeout: 0

    • File: features/llm_agent_tool_loop.feature
    • Line: 170-175
    • Problem: The acceptance criteria state that non-numeric, zero, negative, and non-finite values for either tools_max_timeout or shell_max_timeout must raise AgentCreationError at ephemeral-agent construction. The new scenario only tests tools_max_timeout: 0; it does not cover non-numeric, negative, non-finite, or shell_max_timeout invalid values.
    • Recommendation: Expand the invalid-config coverage with parameterized or additional scenarios for negative, non-numeric, non-finite, and shell_max_timeout cases.

  3. Robot integration tests do not exercise inherited shell_max_timeout

    • File: robot/llm_tool_calling.robot
    • Line: 107-123
    • Problem: The Robot suite verifies tools_max_timeout inheritance but does not include a case for shell_max_timeout overriding the shell-only ceiling.
    • Recommendation: Add a Robot test that configures shell_max_timeout on the LLM agent and verifies a per-call timeout above tools_max_timeout but below shell_max_timeout is accepted for a shell call.

Nits

  1. Hardcoded fallback values mirror ToolAgent defaults
    • File: src/cleveractors/agents/llm.py
    • Line: 978-979
    • Problem: _build_ephemeral_tool_config() hardcodes 120.0 and None as fallbacks. These match ToolAgent.__init__ defaults today, but if those defaults ever change, this helper could silently drift out of sync.
    • Recommendation: Consider referencing ToolAgent defaults via module constants or a shared helper to make the coupling explicit. (This is consistent with the existing timeout: 1 pattern, so purely a nit.)

Summary

This is a focused, well-scoped change. Extracting the ephemeral-tool-agent config construction into _build_ephemeral_tool_config() removes the drift that allowed the timeout ceilings to diverge, and the ADR/spec updates follow the established process. The implementation is functionally correct and backward-compatible. Addressing the minor test-coverage gaps would make the PR fully satisfy the acceptance criteria, but the current state is safe to approve.

## PR Review: !141 (Ticket #140) ### Verdict: Approve The implementation correctly threads `tools_max_timeout` and `shell_max_timeout` from a parent `type: llm` agent into the ephemeral `ToolAgent` instances it constructs per dispatched tool call, satisfying the functional requirements of #140. The code is clean, well-documented, and the spec/ADR updates are consistent. No critical or major issues were found. ### Critical Issues None ### Major Issues None ### Minor Issues 1. **Missing Behave coverage for the post-loop stuck-model synthesis dispatch site** - **File:** `features/llm_agent_tool_loop.feature` - **Line:** 177-182 - **Problem:** The acceptance criteria require coverage "across all three dispatch sites" (normal round, budget-exhaustion synthesis, post-loop synthesis). The PR adds a scenario for the budget-exhaustion site, but the post-loop stuck-model synthesis site is not explicitly exercised. Since all three sites now call the shared `_build_ephemeral_tool_config()` helper, the functional risk is low, but the requirement coverage is incomplete. - **Recommendation:** Add a Behave scenario that forces the post-loop stuck-model synthesis path and asserts that the inherited `tools_max_timeout` ceiling is honored there. 2. **Invalid ceiling test only exercises `tools_max_timeout: 0`** - **File:** `features/llm_agent_tool_loop.feature` - **Line:** 170-175 - **Problem:** The acceptance criteria state that non-numeric, zero, negative, and non-finite values for either `tools_max_timeout` or `shell_max_timeout` must raise `AgentCreationError` at ephemeral-agent construction. The new scenario only tests `tools_max_timeout: 0`; it does not cover non-numeric, negative, non-finite, or `shell_max_timeout` invalid values. - **Recommendation:** Expand the invalid-config coverage with parameterized or additional scenarios for negative, non-numeric, non-finite, and `shell_max_timeout` cases. 3. **Robot integration tests do not exercise inherited `shell_max_timeout`** - **File:** `robot/llm_tool_calling.robot` - **Line:** 107-123 - **Problem:** The Robot suite verifies `tools_max_timeout` inheritance but does not include a case for `shell_max_timeout` overriding the shell-only ceiling. - **Recommendation:** Add a Robot test that configures `shell_max_timeout` on the LLM agent and verifies a per-call `timeout` above `tools_max_timeout` but below `shell_max_timeout` is accepted for a `shell` call. ### Nits 1. **Hardcoded fallback values mirror `ToolAgent` defaults** - **File:** `src/cleveractors/agents/llm.py` - **Line:** 978-979 - **Problem:** `_build_ephemeral_tool_config()` hardcodes `120.0` and `None` as fallbacks. These match `ToolAgent.__init__` defaults today, but if those defaults ever change, this helper could silently drift out of sync. - **Recommendation:** Consider referencing `ToolAgent` defaults via module constants or a shared helper to make the coupling explicit. (This is consistent with the existing `timeout: 1` pattern, so purely a nit.) ### Summary This is a focused, well-scoped change. Extracting the ephemeral-tool-agent config construction into `_build_ephemeral_tool_config()` removes the drift that allowed the timeout ceilings to diverge, and the ADR/spec updates follow the established process. The implementation is functionally correct and backward-compatible. Addressing the minor test-coverage gaps would make the PR fully satisfy the acceptance criteria, but the current state is safe to approve.
Some checks failed
CI / lint (pull_request) Successful in 39s
Details
CI / quality (pull_request) Successful in 55s
Details
CI / security (pull_request) Successful in 1m21s
Details
CI / typecheck (pull_request) Successful in 1m36s
Details
CI / build (pull_request) Successful in 38s
Details
CI / integration_tests (pull_request) Successful in 2m7s
Details
CI / unit_tests (pull_request) Successful in 5m28s
Details
CI / coverage (pull_request) Failing after 11m52s
Details
CI / benchmark (pull_request) Failing after 16m36s
Details
CI / status-check (pull_request) Has been cancelled
Details
This pull request can be merged automatically.
You are not authorized to merge this pull request.
View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.
git fetch -u origin feature/m1-inherit-tool-timeout-ceilings:feature/m1-inherit-tool-timeout-ceilings
git switch feature/m1-inherit-tool-timeout-ceilings

Merge

Merge the changes and update on Forgejo.

Warning: The "Autodetect manual merge" setting is not enabled for this repository, you will have to mark this pull request as manually merged afterwards.

git switch master
git merge --no-ff feature/m1-inherit-tool-timeout-ceilings
git switch feature/m1-inherit-tool-timeout-ceilings
git rebase master
git switch master
git merge --ff-only feature/m1-inherit-tool-timeout-ceilings
git switch feature/m1-inherit-tool-timeout-ceilings
git rebase master
git switch master
git merge --no-ff feature/m1-inherit-tool-timeout-ceilings
git switch master
git merge --squash feature/m1-inherit-tool-timeout-ceilings
git switch master
git merge --ff-only feature/m1-inherit-tool-timeout-ceilings
git switch master
git merge feature/m1-inherit-tool-timeout-ceilings
git push origin master
Sign in to join this conversation.
Reviewers
No reviewers
hurui200320
Labels
Clear labels
  
auto/blocked-by-deps
PR blocked by an open issue dependency. Operator must close the dep (or remove the dependency link) before the merge driver can act. Auto-cleared by merge_drive when no open deps remain.

  
auto/ci-timeout
Most recent merge cycle hit CI timeout. Driver excludes this PR while last merge_cycle row is < 30 min old; label persists thereafter as visible history.

  
auto/claimed-implementer
Currently being processed by an implementer worker.

  
auto/claimed-merge
Currently being processed by the merge driver.

  
auto/claimed-reviewer
Currently being processed by a reviewer worker.

  
auto/driver-down
Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.

  
auto/invariant-violation
Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.

  
auto/last-attempt-tier-0
In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.

  
auto/last-attempt-tier-1
In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.

  
auto/last-attempt-tier-2
In-cycle escalation: most recent attempt ran at the Tier 2 slot (`tier-2`). Slot's model defined in .opencode/models/tiers.yaml. Gated behind IMPLEMENTER_ESCALATION_TIER2_ENABLED.

  
auto/last-attempt-tier-min
In-cycle escalation: most recent attempt ran at the Tier -1 slot (`tier-min`). Slot's model defined in .opencode/models/tiers.yaml. Suffix is ``-min`` (not ``--1``) so the Forgejo UI reads naturally.

  
Automation Tracking
Tracking issues used by the AI Automation system for agents to communicate and report.

  
auto/needs-conflict-resolution
Rebase conflict needs LLM conflict-resolver.

  
auto/needs-implementer
Failing CI needs implementer attention.

  
auto/postmortem
Documenting a driver incident or rollback.

  
auto/ready-to-merge
Reviewer has APPROVED this PR and no later REQUEST_CHANGES is outstanding. The merge driver requires this label to even consider a PR for merging. Set by the reviewer worker on APPROVE; cleared on REQUEST_CHANGES.

  
auto/restart-throttled
Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.

  
auto/revert
Revert PR backing out an invariant violation. Fast-tracked through the merge driver.

  
auto/sentinel
Sentinel PR duplicated from upstream into a personal fork by tools/duplicate_prs_to_fork.py for pipeline testing. Lives only in the fork; the canonical pipeline never sees it.

  
auto/stale-inactivity
No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.

  
auto/unstable
Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.

  
Blocked
A ticket in a blocked state and unable to complete until some other task is completed first.

  
Bounty
$100
 A bounty of $100 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$1000
 A bounty of $1000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$10000
 A bounty of $10000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$20
 A bounty of $20 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$2000
 A bounty of $2000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$250
 A bounty of $250 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$50
 A bounty of $50 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$500
 A bounty of $500 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$5000
 A bounty of $5000 for any open-source contributor who provides a MR that solves this issue

  
Bounty
$750
 A bounty of $750 for any open-source contributor who provides a MR that solves this issue

  
MoSCoW
Could have
 Could have feature in order to satisfy the epic/legendary.

  
MoSCoW
Must have
 Must have feature in order to satisfy the epic/legendary.

  
MoSCoW
Should have
 Should have feature in order to satisfy the epic/legendary.

  
Needs Feedback
There are questions in the ticket that can not be completed until the project owner provides clarity.

  
Points
1
 1 man-hours worth of work for an expert with no learning curve.

  
Points
13
 13 man-hours worth of work for an expert with no learning curve.

  
Points
2
 2 man-hours worth of work for an expert with no learning curve.

  
Points
21
 21 man-hours worth of work for an expert with no learning curve.

  
Points
3
 3 man-hours worth of work for an expert with no learning curve.

  
Points
34
 34 man-hours worth of work for an expert with no learning curve.

  
Points
5
 5 man-hours worth of work for an expert with no learning curve.

  
Points
55
 55 man-hours worth of work for an expert with no learning curve.

  
Points
8
 8 man-hours worth of work for an expert with no learning curve.

  
Points
88
 88 man-hours worth of work for an expert with no learning curve.

  
Priority
Backlog
 This ticket has backlogged priority and is not to be worked on yet

  
Priority
CI Blocker
 Critical priority issue that blocks CI/CD pipeline and prevents PR merges

  
Priority
Critical
 The priority is critical

  
Priority
High
 The priority is high

  
Priority
Low
 The priority is low

  
Priority
Medium
 The priority is medium

  
Signed-off: Owner
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  
Signed-off: Scrum Master
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  
Signed-off: Tech Lead
When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

  
Spike
A ticket for learning a tool or technology that is needed to be able to do future planning and design.

  
State
Completed
 The ticket has been fully implemented, completed, and merged with the source code. This label should only be applied once a ticket is closed.

  
State
Duplicate
 A ticket that represents the same content as an existing ticket.

  
State
In Progress
 A ticket that is actively being developed.

  
State
In Review
 A ticket that has had some code completed to implement but is waiting to pass peer review and is not yet merged in.

  
State
Paused
 This ticket's work started but wasn't finished. It's on hold (likely in a feature branch) and will be resumed later, either due to a blocker or a delay.

  
State
Unverified
 All new tickets start in this state. A developer may set it to show the ticket is unverified. This means we haven't agreed to work on it. It will either move to a verified state or be closed as wontdo.

  
State
Verified
 The issue has been verified by a developer as legitimate. It will be worked on and verified tickets are now considered part of the backlog.

  
State
Wont Do
 This ticket has been decided it wont be done. This may mean the bug has been determined to not be real (cant verify) or the feature is one we have decided we dont want to adopt.

  
Type
Automation
 Any edits or discussion about the AI automated coding system.

  
Type
Bug
 Something that doesnt work as intended.

  
Type
Discussion
 Anytime a ticket represents a discussion about a subject and doesnt fall into one of the other categories.

  
Type
Documentation
 An error or improvement needed in the documentation.

  
Type
Epic
 Any first tier epic. That is, an epic which contains only issues as children and will not have sub-epics.

  
Type
Feature
 Some new functionality not present.

  
Type
Legendary
 A type of Epic which will contain other Epics.

  
Type
Refactor
 A code change that restructures existing code without changing its external behavior.

  
Type
Support
 Someone needs help using the project.

  
Type
Task
 A generic task that doesnt fit into the other type categories.

  
Type
Testing
 Work exclusively focusing on fixing or expanding testing.

No labels
auto/blocked-by-deps
auto/ci-timeout
auto/claimed-implementer
auto/claimed-merge
auto/claimed-reviewer
auto/driver-down
auto/invariant-violation
auto/last-attempt-tier-0
auto/last-attempt-tier-1
auto/last-attempt-tier-2
auto/last-attempt-tier-min
Automation Tracking
auto/needs-conflict-resolution
auto/needs-implementer
auto/postmortem
auto/ready-to-merge
auto/restart-throttled
auto/revert
auto/sentinel
auto/stale-inactivity
auto/unstable
Blocked
Bounty
$100
Bounty
$1000
Bounty
$10000
Bounty
$20
Bounty
$2000
Bounty
$250
Bounty
$50
Bounty
$500
Bounty
$5000
Bounty
$750
MoSCoW
Could have
MoSCoW
Must have
MoSCoW
Should have
Needs Feedback
Points
1
Points
13
Points
2
Points
21
Points
3
Points
34
Points
5
Points
55
Points
8
Points
88
Priority
Backlog
Priority
CI Blocker
Priority
Critical
Priority
High
Priority
Low
Priority
Medium
Signed-off: Owner
Signed-off: Scrum Master
Signed-off: Tech Lead
Spike
State
Completed
State
Duplicate
State
In Progress
State
In Review
State
Paused
State
Unverified
State
Verified
State
Wont Do
Type
Automation
Type
Bug
Type
Discussion
Type
Documentation
Type
Epic
Type
Feature
Type
Legendary
Type
Refactor
Type
Support
Type
Task
Type
Testing
Milestone
Clear milestone
No items
No milestone
v2.1.0
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Blocks
#140 Ephemeral tool-call ToolAgent instances do not inherit tools_max_timeout/shell_max_timeout from the parent LLM agent
cleveragents/cleveractors-core
Reference
cleveragents/cleveractors-core!141
No description provided.