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

Merged

CoreRasurae merged 1 commit from feature/m1-inherit-tool-timeout-ceilings into master 2026-08-24 10:58:35 +00:00

Conversation 2 Commits 1 Files changed 12 +750 -39

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)

## 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)

CoreRasurae added this to the v2.1.0 milestone 2026-08-21 16:59:48 +00:00

CoreRasurae added the

Type

Feature

label 2026-08-21 16:59:48 +00:00

CoreRasurae added 1 commit 2026-08-21 16:59:50 +00:00

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

CoreRasurae added a new dependency 2026-08-21 17:00:34 +00:00

#140 Ephemeral tool-call ToolAgent instances do not inherit tools_max_timeout/shell_max_timeout from the parent LLM agent

CoreRasurae added 1 commit 2026-08-21 17:06:52 +00:00

docs(tools): document type: llm agents honoring tools_max_timeout ... 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 to 49e7e263a0 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.

CoreRasurae force-pushed feature/m1-inherit-tool-timeout-ceilings from 49e7e263a0 to cb48550f16 2026-08-24 10:40:09 +00:00 Compare

CoreRasurae commented 2026-08-24 10:43:02 +00:00

Author

Member

Copy link

@hurui200320 Thanks for the review — all three Minor items and the Nit are addressed in cb48550 (force-pushed to this branch). Details below, checked against docs/index.md §4.4/§4.5, ADR-2030 D-9/D-10, and issue #140's acceptance criteria before applying.

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

Done. Added a scenario ("A post-loop stuck-model synthesis tool dispatch also honors an inherited tools_max_timeout ceiling") in features/llm_agent_tool_loop.feature that drives the loop to the third _build_ephemeral_tool_config() call site (tool_config_s, the post-loop synthesis dispatch) with a shell call carrying a timeout above the built-in default but within an inherited tools_max_timeout: 300, and asserts it succeeds. This now gives Behave coverage across all three dispatch sites named in #140's acceptance criteria (normal round — already covered; budget-exhaustion synthesis — already covered; post-loop synthesis — new).

Minor 2 — Invalid ceiling test only exercised tools_max_timeout: 0

Done. Added three scenarios alongside the existing tools_max_timeout: 0 case:

• negative tools_max_timeout (-5)
• non-numeric tools_max_timeout (not_a_number)
• non-finite tools_max_timeout (nan)
• invalid shell_max_timeout (-5, with a valid tools_max_timeout)

All four assert AgentCreationError at ephemeral-agent construction, matching #140's "non-numeric, zero, negative, or non-finite... for either tools_max_timeout or shell_max_timeout" criterion. (Implementation note: the negative cases reuse the existing integer-typed Given steps rather than new step definitions, since -5 is representable there directly — no behavioral difference, just avoided adding redundant step functions.)

Minor 3 — Robot integration tests do not exercise inherited shell_max_timeout

Done. Added LLM Agent's shell_max_timeout Raises The Shell-Only Ceiling For A Dispatched Shell Call (Ticket 140) to robot/llm_tool_calling.robot, using the shell_max_timeout parameter already wired into Create Executor With Shell Tool Calling Agent (robot/ToolCallingTestLib.py). It configures tools_max_timeout=2/shell_max_timeout=100 and issues a per-call timeout=50 (above the generic ceiling, below the shell-only one) — exactly the case you suggested.

Nit — Hardcoded fallback values mirror ToolAgent defaults

Done. Extracted DEFAULT_TOOLS_MAX_TIMEOUT = 120.0 and DEFAULT_SHELL_MAX_TIMEOUT = None as module-level constants in src/cleveractors/agents/tool.py, and both ToolAgent.__init__ and LLMAgent._build_ephemeral_tool_config() now read from them instead of each hardcoding the literals independently. This closes the exact drift risk you flagged — the two call sites can no longer diverge silently if the default ever changes.

Not changed

Nothing from your review was skipped or rejected — all four items were verified as correct against the spec/ADR/issue before being applied, and all are now in the diff.

Verification

• nox -s lint / format --check — green
• nox -s typecheck — 0 errors
• nox -s unit_tests — 3094 scenarios passed (5 new, all exercising this change), 0 failed
• nox -s coverage_report — 96.9% (unchanged from the prior report; no new uncovered lines introduced)
• nox -s integration_tests — 365 Robot tests passed (was 364), 0 failed
• nox -s dead_code / nox -s security_scan — clean

Ready for another look whenever convenient.

@hurui200320 Thanks for the review — all three Minor items and the Nit are addressed in `cb48550` (force-pushed to this branch). Details below, checked against `docs/index.md` §4.4/§4.5, ADR-2030 D-9/D-10, and issue #140's acceptance criteria before applying. ### Minor 1 — Missing Behave coverage for the post-loop stuck-model synthesis dispatch site **Done.** Added a scenario ("A post-loop stuck-model synthesis tool dispatch also honors an inherited tools_max_timeout ceiling") in `features/llm_agent_tool_loop.feature` that drives the loop to the third `_build_ephemeral_tool_config()` call site (`tool_config_s`, the post-loop synthesis dispatch) with a `shell` call carrying a `timeout` above the built-in default but within an inherited `tools_max_timeout: 300`, and asserts it succeeds. This now gives Behave coverage across all three dispatch sites named in #140's acceptance criteria (normal round — already covered; budget-exhaustion synthesis — already covered; post-loop synthesis — new). ### Minor 2 — Invalid ceiling test only exercised tools_max_timeout: 0 **Done.** Added three scenarios alongside the existing `tools_max_timeout: 0` case: - negative `tools_max_timeout` (`-5`) - non-numeric `tools_max_timeout` (`not_a_number`) - non-finite `tools_max_timeout` (`nan`) - invalid `shell_max_timeout` (`-5`, with a valid `tools_max_timeout`) All four assert `AgentCreationError` at ephemeral-agent construction, matching #140's "non-numeric, zero, negative, or non-finite... for either tools_max_timeout or shell_max_timeout" criterion. (Implementation note: the negative cases reuse the existing integer-typed Given steps rather than new step definitions, since `-5` is representable there directly — no behavioral difference, just avoided adding redundant step functions.) ### Minor 3 — Robot integration tests do not exercise inherited shell_max_timeout **Done.** Added `LLM Agent's shell_max_timeout Raises The Shell-Only Ceiling For A Dispatched Shell Call (Ticket 140)` to `robot/llm_tool_calling.robot`, using the `shell_max_timeout` parameter already wired into `Create Executor With Shell Tool Calling Agent` (`robot/ToolCallingTestLib.py`). It configures `tools_max_timeout=2`/`shell_max_timeout=100` and issues a per-call `timeout=50` (above the generic ceiling, below the shell-only one) — exactly the case you suggested. ### Nit — Hardcoded fallback values mirror ToolAgent defaults **Done.** Extracted `DEFAULT_TOOLS_MAX_TIMEOUT = 120.0` and `DEFAULT_SHELL_MAX_TIMEOUT = None` as module-level constants in `src/cleveractors/agents/tool.py`, and both `ToolAgent.__init__` and `LLMAgent._build_ephemeral_tool_config()` now read from them instead of each hardcoding the literals independently. This closes the exact drift risk you flagged — the two call sites can no longer diverge silently if the default ever changes. ### Not changed Nothing from your review was skipped or rejected — all four items were verified as correct against the spec/ADR/issue before being applied, and all are now in the diff. ### Verification - `nox -s lint` / `format --check` — green - `nox -s typecheck` — 0 errors - `nox -s unit_tests` — 3094 scenarios passed (5 new, all exercising this change), 0 failed - `nox -s coverage_report` — 96.9% (unchanged from the prior report; no new uncovered lines introduced) - `nox -s integration_tests` — 365 Robot tests passed (was 364), 0 failed - `nox -s dead_code` / `nox -s security_scan` — clean Ready for another look whenever convenient.

CoreRasurae force-pushed feature/m1-inherit-tool-timeout-ceilings from cb48550f16 to d1f17c0b20 2026-08-24 10:44:04 +00:00 Compare

CoreRasurae merged commit d1f17c0b20 into master 2026-08-24 10:58:35 +00:00

CoreRasurae deleted branch feature/m1-inherit-tool-timeout-ceilings 2026-08-24 10:58:37 +00:00

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

Subscribe

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.