fix(reactive): forward actor options block in ToolCallingLLMCaller._resolve_llm #11244

Merged

HAL9000 merged 2 commits from bugfix/m7-tool-calling-llm-options into master 2026-05-28 03:08:32 +00:00

Conversation 7 Commits 2 Files changed 3 +256

hurui200320 commented 2026-05-18 08:45:32 +00:00

Member

Copy link

Summary

Fixes a bug where running an actor with --skill would ignore the options block in the actor YAML config, causing openai_api_base and openai_api_key to be silently dropped. This caused actors that correctly route to a local llama-swap/llama.cpp backend without --skill to fail with an OpenAI 401 when --skill was attached.

Closes #11243

Root Cause

PR #11225 (commit b3851693) added options-block forwarding to SimpleLLMAgent._resolve_llm() in stream_router.py. PR #11211 later introduced ToolCallingLLMCaller._resolve_llm() in tool_caller.py — the parallel resolution path used when tools are attached via --skill — but never ported that logic. As a result, the two paths diverged silently.

Changes

src/cleveragents/reactive/tool_caller.py

ToolCallingLLMCaller._resolve_llm(): ported the full options-block merging logic from SimpleLLMAgent._resolve_llm():

• openai_api_key in options is extracted and forwarded as __api_key_sentinel (overrides env-sourced key in provider registry)
• openai_api_base, timeout, top_p, frequency_penalty, presence_penalty from options are forwarded to create_llm() when not already set by a top-level config key (top-level takes precedence)
• Reserved keys (provider_type, model_id) are rejected with logger.warning
• Unknown keys are rejected with logger.warning citing allowed keys
• Behaviour is now identical to SimpleLLMAgent._resolve_llm()

features/actor_run_tool_calling.feature

Added five BDD regression scenarios in section V (@tdd_issue @tdd_issue_11243):

1. openai_api_base and openai_api_key forwarded from options block
2. Allowed extra keys (timeout, top_p, frequency_penalty, presence_penalty) forwarded
3. Reserved key provider_type rejected without TypeError
4. Unknown key foo_bar not forwarded to create_llm()
5. Top-level temperature takes precedence over options.temperature

features/steps/actor_run_tool_calling_steps.py

Added step definitions for the 5 new scenarios using patch("cleveragents.reactive.tool_caller.get_provider_registry") to capture create_llm() call kwargs.

Quality Gates

Gate	Result
nox -e lint	✅ PASS
nox -e typecheck	✅ PASS (0 errors)
nox -e unit_tests	✅ PASS (15822 scenarios, 0 failures)
nox -e integration_tests	✅ PASS (1999 tests, 0 failures)
nox -e coverage_report	✅ PASS (97%)

## Summary Fixes a bug where running an actor with `--skill` would ignore the `options` block in the actor YAML config, causing `openai_api_base` and `openai_api_key` to be silently dropped. This caused actors that correctly route to a local llama-swap/llama.cpp backend without `--skill` to fail with an OpenAI 401 when `--skill` was attached. Closes #11243 ## Root Cause PR #11225 (commit `b3851693`) added options-block forwarding to `SimpleLLMAgent._resolve_llm()` in `stream_router.py`. PR #11211 later introduced `ToolCallingLLMCaller._resolve_llm()` in `tool_caller.py` — the parallel resolution path used when tools are attached via `--skill` — but never ported that logic. As a result, the two paths diverged silently. ## Changes ### `src/cleveragents/reactive/tool_caller.py` `ToolCallingLLMCaller._resolve_llm()`: ported the full options-block merging logic from `SimpleLLMAgent._resolve_llm()`: - `openai_api_key` in `options` is extracted and forwarded as `__api_key_sentinel` (overrides env-sourced key in provider registry) - `openai_api_base`, `timeout`, `top_p`, `frequency_penalty`, `presence_penalty` from `options` are forwarded to `create_llm()` when not already set by a top-level config key (top-level takes precedence) - Reserved keys (`provider_type`, `model_id`) are rejected with `logger.warning` - Unknown keys are rejected with `logger.warning` citing allowed keys - Behaviour is now identical to `SimpleLLMAgent._resolve_llm()` ### `features/actor_run_tool_calling.feature` Added five BDD regression scenarios in section **V** (`@tdd_issue @tdd_issue_11243`): 1. `openai_api_base` and `openai_api_key` forwarded from options block 2. Allowed extra keys (`timeout`, `top_p`, `frequency_penalty`, `presence_penalty`) forwarded 3. Reserved key `provider_type` rejected without TypeError 4. Unknown key `foo_bar` not forwarded to `create_llm()` 5. Top-level `temperature` takes precedence over `options.temperature` ### `features/steps/actor_run_tool_calling_steps.py` Added step definitions for the 5 new scenarios using `patch("cleveragents.reactive.tool_caller.get_provider_registry")` to capture `create_llm()` call kwargs. ## Quality Gates | Gate | Result | |------|--------| | `nox -e lint` | ✅ PASS | | `nox -e typecheck` | ✅ PASS (0 errors) | | `nox -e unit_tests` | ✅ PASS (15822 scenarios, 0 failures) | | `nox -e integration_tests` | ✅ PASS (1999 tests, 0 failures) | | `nox -e coverage_report` | ✅ PASS (97%) |

hurui200320 added 1 commit 2026-05-18 08:45:32 +00:00

fix(reactive): forward actor options block in ToolCallingLLMCaller._resolve_llm ... 1842995056

Port the options-block merging logic from SimpleLLMAgent._resolve_llm()
(stream_router.py, added in PR #11225 / commit b3851693) to the parallel
resolution path ToolCallingLLMCaller._resolve_llm() in tool_caller.py.

Without this fix, running an actor with --skill would ignore the options
block in the actor YAML, causing openai_api_base and openai_api_key to be
silently dropped.  The provider registry then fell back to OPENAI_API_KEY
from the environment, routing requests to api.openai.com instead of the
configured local llama-swap/llama.cpp backend (HTTP 401).

Changes:
- tool_caller.ToolCallingLLMCaller._resolve_llm: read actor_config.options;
  extract openai_api_key -> __api_key_sentinel; forward allowed keys
  (openai_api_base, timeout, top_p, frequency_penalty, presence_penalty);
  reject reserved keys (provider_type, model_id) and unknown keys with
  logger.warning, matching SimpleLLMAgent behaviour exactly.
- features/actor_run_tool_calling.feature: add five BDD regression
  scenarios (section V, tagged @tdd_issue @tdd_issue_11243) covering
  api_base+key forwarding, allowed extra keys, reserved key rejection,
  unknown key rejection, and top-level precedence over options.
- features/steps/actor_run_tool_calling_steps.py: add corresponding step
  definitions for all five scenarios.

All nox quality gates pass (lint, typecheck, unit_tests 15822/0 fail,
integration_tests 1999/0 fail, coverage_report 97%).

ISSUES CLOSED: #11243

hurui200320 added this to the v3.6.0 milestone 2026-05-18 08:45:38 +00:00

hurui200320 added the

Type

Bug

label 2026-05-18 08:45:51 +00:00

hurui200320 added a new dependency 2026-05-18 08:46:34 +00:00

#11243 Bug: ToolCallingLLMCaller ignores actor options block, causing wrong LLM provider when skill is used

hurui200320 removed a dependency 2026-05-18 08:47:05 +00:00

#11243 Bug: ToolCallingLLMCaller ignores actor options block, causing wrong LLM provider when skill is used

hurui200320 added a new dependency 2026-05-18 08:47:15 +00:00

#11243 Bug: ToolCallingLLMCaller ignores actor options block, causing wrong LLM provider when skill is used

hurui200320 commented 2026-05-18 09:43:07 +00:00

Author

Member

Copy link

Note: This PR contains both TDD and fix. To speed up the bug fixes, I decided to not have a dedicated PR for TDD test cases since it usually take days to get a PR merged in.

Note: This PR contains both TDD and fix. To speed up the bug fixes, I decided to not have a dedicated PR for TDD test cases since it usually take days to get a PR merged in.

hurui200320 2026-05-18 09:48:02 +00:00

• added the
  State
  In Review
  Priority
  Critical
  MoSCoW
  Must have
  labels
• requested reviews from HAL9000, HAL9001

hurui200320 force-pushed bugfix/m7-tool-calling-llm-options from 1842995056 to 4b05d9a181 2026-05-18 14:29:01 +00:00 Compare

hurui200320 scheduled this pull request to auto merge when all checks succeed 2026-05-18 14:29:18 +00:00

HAL9000 added the

auto/blocked-by-deps

label 2026-05-19 16:44:58 +00:00

HAL9000 added the

controller-managed

label 2026-05-27 13:26:23 +00:00

HAL9000 added

auto/claimed-merge

and removed

auto/blocked-by-deps

labels 2026-05-27 16:10:36 +00:00

HAL9000 commented 2026-05-27 16:13:58 +00:00

Owner

Copy link

Claimed by merge_drive.py (pid 292598) until 2026-05-27T17:43:57.982964+00:00.

This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

<!-- merge_drive.py: claim --> Claimed by `merge_drive.py` (pid 292598) until `2026-05-27T17:43:57.982964+00:00`. This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

HAL9000 force-pushed bugfix/m7-tool-calling-llm-options from 4b05d9a181 to 91691750ed 2026-05-27 16:14:06 +00:00 Compare

HAL9000 added

auto/needs-implementer

and removed

auto/claimed-merge

labels 2026-05-27 16:33:40 +00:00

HAL9000 commented 2026-05-27 16:33:41 +00:00

Owner

Copy link

Released by merge_drive.py (pid 292598). terminal_state=ci-fail-on-rebased-sha, op_label=auto/needs-implementer

<!-- merge_drive.py: release --> Released by `merge_drive.py` (pid 292598). terminal_state=`ci-fail-on-rebased-sha`, op_label=`auto/needs-implementer`

HAL9000 added the

auto/claimed-merge

label 2026-05-27 17:28:30 +00:00

HAL9000 commented 2026-05-27 17:28:30 +00:00

Owner

Copy link

Claimed by merge_drive.py (pid 309620) until 2026-05-27T18:58:30.373348+00:00.

This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

<!-- merge_drive.py: claim --> Claimed by `merge_drive.py` (pid 309620) until `2026-05-27T18:58:30.373348+00:00`. This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

HAL9000 removed the

auto/claimed-merge

label 2026-05-27 17:28:33 +00:00

HAL9000 commented 2026-05-27 17:28:35 +00:00

Owner

Copy link

Released by merge_drive.py (pid 309620). terminal_state=ci-fail-on-rebased-sha, op_label=auto/needs-implementer

<!-- merge_drive.py: release --> Released by `merge_drive.py` (pid 309620). terminal_state=`ci-fail-on-rebased-sha`, op_label=`auto/needs-implementer`

drew referenced this pull request from a commit 2026-05-28 01:45:48 +00:00

fix(controller): P-9 — switch dep probe to /dependencies endpoint

drew referenced this pull request from a commit 2026-05-28 01:45:48 +00:00

fix(controller): P-5b — release SQLite write-tx before slow Forgejo I/O in scheduler / reconciliation / ci_status_poll

HAL9000 added 1 commit 2026-05-28 02:28:22 +00:00

chore: re-trigger CI [controller] 38aa457841

HAL9000 added the

auto/claimed-merge

label 2026-05-28 03:08:26 +00:00

HAL9000 commented 2026-05-28 03:08:27 +00:00

Owner

Copy link

Claimed by merge_drive.py (pid 779633) until 2026-05-28T04:38:26.859563+00:00.

This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

<!-- merge_drive.py: claim --> Claimed by `merge_drive.py` (pid 779633) until `2026-05-28T04:38:26.859563+00:00`. This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

HAL9001 approved these changes 2026-05-28 03:08:31 +00:00

HAL9001 left a comment

Copy link

Approved by the controller reviewer stage (workflow 3).

Approved by the controller reviewer stage (workflow 3).

HAL9000 merged commit 56338db205 into master 2026-05-28 03:08:32 +00:00

HAL9000 referenced this pull request from a commit 2026-05-28 03:08:33 +00:00

Merge pull request 'fix(reactive): forward actor options block in ToolCallingLLMCaller._resolve_llm' (#11244) from bugfix/m7-tool-calling-llm-options into master

HAL9000 removed the

auto/claimed-merge

label 2026-05-28 03:08:33 +00:00

Sign in to join this conversation.

Reviewers

No reviewers

HAL9000

HAL9001

Labels

Clear labels   

auto/needs-reevaluation

Controller deferred this PR; awaiting Phase 6+ scope-evaluator or operator re-enablement.

  

controller-managed

Auto-agents controller manages this PR/issue (see tools/controller/deploy/RUNBOOK.md). Remove this label to abandon controller management.

  

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/needs-reevaluation

controller-managed

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

v3.6.0

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

3 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

#11243 Bug: ToolCallingLLMCaller ignores actor options block, causing wrong LLM provider when skill is used

cleveragents/cleveragents-core

Reference

cleveragents/cleveragents-core!11244

No description provided.