fix(strategize): propagate actor options (openai_api_base, openai_api_key) to LLM client creation in Strategize/Execute paths #11257

Merged

HAL9000 merged 4 commits from bugfix/m5-actor-options-ignored into master 2026-05-29 00:09:42 +00:00

Conversation 3 Commits 4 Files changed 16 +775 -100

CoreRasurae commented 2026-05-28 13:40:51 +00:00

Member

Copy link

Summary

Propagates actor-level YAML options (such as openai_api_base and openai_api_key) through to ProviderRegistry.create_llm() in the Strategize and Execute phases, and in session-based workflows.

Previously these options were silently ignored, causing LLM calls to fall back to the real OpenAI internet endpoint instead of the user-configured local backend.

Root Cause

Two independent gaps:

1. ActorConfigSchema silently dropped options — no options field, and Pydantic v2 defaults to extra='ignore', so options was stripped during validation.

2. Four call sites never forwarded options to create_llm() — StrategyActor._execute_with_llm(), LLMStrategizeActor.execute(), LLMExecuteActor.execute(), and SessionWorkflow._resolve_llm() all created the LLM with zero extra kwargs.

Changes

New shared utility (src/cleveragents/actor/config.py)

• build_llm_kwargs_from_options() — extracts openai_api_base, openai_api_key (via __api_key_sentinel), and other allowed kwargs from actor options dict
• _ALLOWED_LLM_OPTIONS / _RESERVED_LLM_OPTIONS constants

Schema fix (src/cleveragents/actor/schema.py)

• Added options: dict[str, Any] field to ActorConfigSchema

Lifecycle/protocol additions

• PlanLifecycleService.resolve_actor_options() — retrieves options from actor config_blob
• Added resolve_actor_options() to LifecycleService protocol (strategy_resolution.py)
• Added resolve_actor_options() to PlanLifecycleProtocol (llm_actors.py)
• build_actor_options_resolver() utility in strategy_resolution.py

Fixed 4 call sites

• StrategyActor._execute_with_llm() — resolves options before calling create_llm()
• LLMStrategizeActor.execute() — resolves options before calling create_llm()
• LLMExecuteActor.execute() — resolves options before calling create_llm()
• SessionWorkflow._resolve_llm() — new actor_options_resolver parameter

Refactored reactive path

• reactive/stream_router.py and reactive/tool_caller.py now use build_llm_kwargs_from_options() instead of inline copies

Wiring

• CLI _build_actor_options_resolver() wired to SessionWorkflow
• A2A facade _build_actor_options_resolver_for_session_workflow() wired

Tests

• features/actor_options_propagation.feature — 14 BDD scenarios passing

Closes #11256

## Summary Propagates actor-level YAML `options` (such as `openai_api_base` and `openai_api_key`) through to `ProviderRegistry.create_llm()` in the Strategize and Execute phases, and in session-based workflows. Previously these options were silently ignored, causing LLM calls to fall back to the real OpenAI internet endpoint instead of the user-configured local backend. ## Root Cause Two independent gaps: 1. **`ActorConfigSchema` silently dropped `options`** — no `options` field, and Pydantic v2 defaults to `extra='ignore'`, so `options` was stripped during validation. 2. **Four call sites never forwarded options to `create_llm()`** — `StrategyActor._execute_with_llm()`, `LLMStrategizeActor.execute()`, `LLMExecuteActor.execute()`, and `SessionWorkflow._resolve_llm()` all created the LLM with zero extra kwargs. ## Changes ### New shared utility (`src/cleveragents/actor/config.py`) - `build_llm_kwargs_from_options()` — extracts `openai_api_base`, `openai_api_key` (via `__api_key_sentinel`), and other allowed kwargs from actor options dict - `_ALLOWED_LLM_OPTIONS` / `_RESERVED_LLM_OPTIONS` constants ### Schema fix (`src/cleveragents/actor/schema.py`) - Added `options: dict[str, Any]` field to `ActorConfigSchema` ### Lifecycle/protocol additions - `PlanLifecycleService.resolve_actor_options()` — retrieves options from actor `config_blob` - Added `resolve_actor_options()` to `LifecycleService` protocol (strategy_resolution.py) - Added `resolve_actor_options()` to `PlanLifecycleProtocol` (llm_actors.py) - `build_actor_options_resolver()` utility in strategy_resolution.py ### Fixed 4 call sites - `StrategyActor._execute_with_llm()` — resolves options before calling `create_llm()` - `LLMStrategizeActor.execute()` — resolves options before calling `create_llm()` - `LLMExecuteActor.execute()` — resolves options before calling `create_llm()` - `SessionWorkflow._resolve_llm()` — new `actor_options_resolver` parameter ### Refactored reactive path - `reactive/stream_router.py` and `reactive/tool_caller.py` now use `build_llm_kwargs_from_options()` instead of inline copies ### Wiring - CLI `_build_actor_options_resolver()` wired to `SessionWorkflow` - A2A facade `_build_actor_options_resolver_for_session_workflow()` wired ### Tests - `features/actor_options_propagation.feature` — 14 BDD scenarios passing Closes #11256

CoreRasurae added this to the v3.4.0 milestone 2026-05-28 13:40:51 +00:00

CoreRasurae added 1 commit 2026-05-28 13:40:51 +00:00

fix(strategize): propagate actor options.openai_api_base and options.openai_api_key to LLM client creation in Strategize/Execute paths ... 7a7d3b8121

Extract shared build_llm_kwargs_from_options() utility in actor/config.py
that converts actor-level YAML options (openai_api_base, openai_api_key,
temperature, max_tokens, etc.) into kwargs for ProviderRegistry.create_llm().

Add options field to ActorConfigSchema so it survives Pydantic validation
instead of being silently dropped by extra='ignore' default.

Add resolve_actor_options() to PlanLifecycleService and both LifecycleService
and PlanLifecycleProtocol protocols so every call site can retrieve the
actor's config_blob.options dict.

Fix the four call sites that previously called create_llm() with zero extra
kwargs, preventing local/custom LLM backends from working:

- StrategyActor._execute_with_llm() in strategy_actor.py
- LLMStrategizeActor.execute() in llm_actors.py
- LLMExecuteActor.execute() in llm_actors.py
- SessionWorkflow._resolve_llm() in session_workflow.py

Refactor reactive path (stream_router.py, tool_caller.py) to use the
shared build_llm_kwargs_from_options() utility instead of inline copies.

Wire actor_options_resolver through CLI session builder and A2A facade.

ISSUES CLOSED: #11256

CoreRasurae added the

Type

Bug

Priority

Critical

labels 2026-05-28 13:43:34 +00:00

HAL9000 added the

controller-managed

label 2026-05-28 13:44:36 +00:00

CoreRasurae force-pushed bugfix/m5-actor-options-ignored from 7a7d3b8121 to 0ecacf9f22 2026-05-28 13:48:32 +00:00 Compare

CoreRasurae added a new dependency 2026-05-28 13:48:54 +00:00

#11256 Actor options (openai_api_base, openai_api_key) ignored in Strategize/Execute paths — LLM calls fall back to real OpenAI instead of local backend

HAL9000 force-pushed bugfix/m5-actor-options-ignored from 0ecacf9f22 to 9a10e79b02 2026-05-28 14:02:28 +00:00 Compare

HAL9000 force-pushed bugfix/m5-actor-options-ignored from 9a10e79b02 to 080e1d5e3f 2026-05-28 19:46:09 +00:00 Compare

HAL9000 added 1 commit 2026-05-28 20:10:24 +00:00

fix(tests): add resolve_actor_options to mock lifecycle helpers ... 4f53c21a7e

The PR added resolve_actor_options() to StrategyActor, LLMStrategizeActor,
and LLMExecuteActor, but the three mock lifecycle SimpleNamespace objects
used by tests did not include this method, causing AttributeError at
runtime:

- features/mocks/mock_strategy_llm.py: make_mock_lifecycle() used by
  robot/helper_strategy_actor.py (strategy_actor.robot llm-json test)
  and features/steps/strategy_actor_llm_steps.py
- features/steps/llm_actors_coverage_steps.py: _make_mock_lifecycle()
  used by llm_actors_coverage.feature scenarios
- robot/helper_m5_e2e_context.py: inline lifecycle SimpleNamespace
  used by m5_e2e_verification.robot Execute Phase LLM Uses ACMS Context

All three now include resolve_actor_options=MagicMock(return_value=None)
matching the None-return contract the actors use when no custom backend
is configured.

ISSUES CLOSED: #11256

HAL9000 added 1 commit 2026-05-28 21:03:38 +00:00

fix(actor): top-level config keys take precedence over options block duplicates ... 8d9cedce8c

In both ToolCallingLLMCaller._resolve_llm and SimpleLLMAgent._resolve_llm,
the options block was merged after top-level keys were applied, causing
llm_kwargs.update(...) to overwrite top-level temperature/max_tokens/
max_retries with any duplicate values from the options block.

Fix: apply build_llm_kwargs_from_options first, then re-apply the
top-level extracted values so they always win.

ISSUES CLOSED: #11243 #11223

HAL9000 added the

auto/claimed-merge

label 2026-05-28 21:35:06 +00:00

HAL9000 commented 2026-05-28 21:35:06 +00:00

Owner

Copy link

Claimed by merge_drive.py (pid 1264876) until 2026-05-28T23:05:06.184455+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 1264876) until `2026-05-28T23:05:06.184455+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/m5-actor-options-ignored from 8d9cedce8c to fae4384370 2026-05-28 21:35:09 +00:00 Compare

HAL9000 removed the

auto/claimed-merge

label 2026-05-28 22:40:54 +00:00

HAL9000 added 1 commit 2026-05-28 23:35:35 +00:00

chore: re-trigger CI [controller] 8cace12f66

HAL9000 added the

auto/claimed-merge

label 2026-05-29 00:09:37 +00:00

HAL9000 commented 2026-05-29 00:09:37 +00:00

Owner

Copy link

Claimed by merge_drive.py (pid 1264876) until 2026-05-29T01:39:37.590838+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 1264876) until `2026-05-29T01:39:37.590838+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 2026-05-29 00:09:41 +00:00

HAL9001 left a comment

Copy link

Approved by the controller reviewer stage (workflow 19).

Approved by the controller reviewer stage (workflow 19).

HAL9000 merged commit 0fa82ee6a0 into master 2026-05-29 00:09:42 +00:00

HAL9000 removed the

auto/claimed-merge

label 2026-05-29 00:09:43 +00:00

HAL9000 referenced this pull request from a commit 2026-05-29 00:09:43 +00:00

Merge pull request 'fix(strategize): propagate actor options (openai_api_base, openai_api_key) to LLM client creation in Strategize/Execute paths' (#11257) from bugfix/m5-actor-options-ignored into master

Sign in to join this conversation.

Reviewers

No reviewers

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

v3.4.0

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

#11256 Actor options (openai_api_base, openai_api_key) ignored in Strategize/Execute paths — LLM calls fall back to real OpenAI instead of local backend

cleveragents/cleveragents-core

Reference

cleveragents/cleveragents-core!11257

No description provided.