feat(dynamic-workflow): run subagents on a chosen model

[elkaix]

Related Issue

No issue — problem described below.

Problem

Every subagent in a Dynamic Workflow ran on whatever model the calling agent
was using. A workflow that fans 128 children out over mechanical work — reading
files, applying a mechanical edit, running a check — paid the orchestrator's
model for all of it, and there was no way to say "plan here, implement there"
without editing an agent profile up front.

The provider layer already supported this: a model alias resolves to its own
provider per agent, and configureChild already honoured profile.model /
profile.effort (kept across resume by #28). The routing decision just had no
way to reach a single run.

What changed

DynamicWorkflow accepts model and effort. Both apply to every subagent in
the call and travel on QueuedSubagentTask through SubagentBatch into
RunSubagentOptions, where the existing option → profile → parent precedence
resolves them, so the choice also survives resume and retry. An alias the
provider cannot resolve falls back to the calling agent's model instead of
failing at generate time.

/workflow model <alias> stores the choice for the session; /workflow model
reports it and /workflow model off clears it. The alias reaches the run as an
instruction on the task prompt rather than a hard override, so the agent can
still pick something else when the work plainly calls for it — the same shape
as the existing Dynamic Workflow mode reminders.

/workflow model deepseek-v4
/workflow audit every route handler under src/routes/ for missing auth
→ orchestrator stays on the session model, all 128 children run on deepseek-v4

Checklist

• I have read the CONTRIBUTING document.
• I have linked a related issue, or explained the problem above.
• I have added tests that prove my feature works.
• Ran gen-changesets skill, or this PR needs no changeset.
• Ran gen-docs skill, or this PR needs no doc update.

Summary by CodeRabbit

• New Features

  • Configure a model and reasoning effort for all Dynamic Workflow subagents.
  • Use /workflow model <alias> to view, select, or clear the session’s subagent model.
  • Added autocomplete support for the new workflow model command.

• Documentation

  • Updated Dynamic Workflow and slash-command documentation with model and effort configuration details.

• Bug Fixes

  • Ensured selected model and reasoning settings apply consistently to spawned and resumed workflow tasks.

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 37 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 68a04f63-f559-47b4-bfc4-bfb9c9b9b634

📥 Commits

Reviewing files that changed from the base of the PR and between f7f731e and 3758a37.

📒 Files selected for processing (4)

• apps/pythinker-code/src/tui/commands/dynamic-workflow.ts
• apps/pythinker-code/test/tui/commands/dynamic-workflow.test.ts
• packages/agent-core/src/tools/builtin/collaboration/dynamic-workflow.md
• packages/agent-core/test/session/subagent-batch.test.ts

📝 Walkthrough

Walkthrough

DynamicWorkflow now accepts optional subagent model and effort settings. Queued tasks propagate these settings to subagent runs. The TUI adds /workflow model for session-scoped model selection.

Changes

Dynamic Workflow model configuration

Layer / File(s)	Summary
Workflow configuration and subagent propagation packages/agent-core/src/tools/builtin/collaboration/dynamic-workflow.ts, packages/agent-core/src/session/subagent-batch.ts, packages/agent-core/test/session/*, packages/agent-core/test/tools/*, docs/reference/tools.md, packages/agent-core/src/tools/builtin/collaboration/dynamic-workflow.md	DynamicWorkflow accepts optional model and effort values. Queued tasks pass the normalized settings to spawned, resumed, and retried subagents. Tests verify propagation and schema ordering.
TUI model selection and prompt handling apps/pythinker-code/src/tui/commands/dynamic-workflow.ts, apps/pythinker-code/src/tui/types.ts, apps/pythinker-code/test/tui/commands/dynamic-workflow.test.ts	/workflow model reports, sets, and clears the session model preference. Configured preferences are added to subsequent task prompts.
Command discoverability and documentation apps/pythinker-code/src/tui/commands/registry.ts, apps/pythinker-code/test/tui/commands/registry.test.ts, docs/reference/slash-commands.md, .changeset/dynamic-workflow-subagent-model.md	Command completion and descriptions include model. Reference documentation and the changeset describe the new settings.

Estimated code review effort: 3 (Moderate) | ~20 minutes

Possibly related PRs

• Pythoughts-labs/pythinker-code#22: Both changes modify DynamicWorkflow-related TUI behavior, but this change concerns model configuration.
• Pythoughts-labs/pythinker-code#28: Both changes modify subagent model and effort propagation across subagent execution paths.

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title uses a valid conventional-commit prefix, imperative wording, stays within 72 characters, and accurately describes the main change.
Description check	✅ Passed	The description includes all required sections, explains the problem and implementation, and confirms tests, changeset, and documentation updates.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

---

_{Comment @coderabbitai help to get the list of available commands.}

[pkg-pr-new]

pnpm dlx https://pkg.pr.new/@pythoughts/pythinker-code@3758a37

npx https://pkg.pr.new/@pythoughts/pythinker-code@3758a37

commit: 3758a37

[elkaix]

@coderabbitai review

[coderabbitai]

✅ Action performed

Review finished.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

[coderabbitai]

Actionable comments posted: 4

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@apps/pythinker-code/src/tui/commands/dynamic-workflow.ts`:
- Line 114: Update the regular expression in the command parser to include the
Unicode (`u`) flag, preserving its existing case-insensitive matching and
capture behavior so it satisfies Oxlint’s require-unicode-regexp rule.

In `@apps/pythinker-code/test/tui/commands/dynamic-workflow.test.ts`:
- Around line 356-359: Update the test covering handleDynamicWorkflowCommand
with 'model off' to also assert that host.state.appState.dynamicWorkflowModel is
undefined after the command completes, while retaining the existing
status-message assertion.

In `@packages/agent-core/src/tools/builtin/collaboration/dynamic-workflow.md`:
- Line 7: Update the workflow documentation describing model fallback behavior
to include all outcomes: fallback to the calling agent when no model is
configured by the subagent profile, and fallback behavior when the configured
model alias cannot be resolved. Keep the existing subagent-profile fallback
guidance and ensure the documented rules apply to every subagent in the call.

In `@packages/agent-core/test/session/subagent-batch.test.ts`:
- Around line 672-685: Extend the existing resume and rate-limit retry test
cases alongside the spawn-task coverage to assert that every recorded
RunSubagentOptions attempt preserves both modelAlias and thinkingLevel. Use the
existing attempt collections and expected routed-task values, while keeping the
current completion and retry behavior unchanged.

🪄 Autofix

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: a73b5b13-e3c9-49b2-a1c1-ff1638d0f432

📥 Commits

Reviewing files that changed from the base of the PR and between cf5b6b1 and f7f731e.

📒 Files selected for processing (13)

• .changeset/dynamic-workflow-subagent-model.md
• apps/pythinker-code/src/tui/commands/dynamic-workflow.ts
• apps/pythinker-code/src/tui/commands/registry.ts
• apps/pythinker-code/src/tui/types.ts
• apps/pythinker-code/test/tui/commands/dynamic-workflow.test.ts
• apps/pythinker-code/test/tui/commands/registry.test.ts
• docs/reference/slash-commands.md
• docs/reference/tools.md
• packages/agent-core/src/session/subagent-batch.ts
• packages/agent-core/src/tools/builtin/collaboration/dynamic-workflow.md
• packages/agent-core/src/tools/builtin/collaboration/dynamic-workflow.ts
• packages/agent-core/test/session/subagent-batch.test.ts
• packages/agent-core/test/tools/builtin-current.test.ts