feat(claude_code): per-agent reasoning effort via claudeConfig by vprudnikoff · Pull Request #283 · awslabs/cli-agent-orchestrator

vprudnikoff · 2026-06-06T14:37:02Z

What

Adds a claudeConfig field to the agent profile, the Claude Code analog of codexConfig (PR #278) for the codex provider. The claude_code provider maps it to Claude Code CLI flags at launch:

`claudeConfig` key	Claude Code flag
`effort`	`--effort <level>`
`fallback_model`	`--fallback-model <model>`

The top-level model field still maps to --model (unchanged), mirroring how codex keeps model separate from codexConfig.

Why

Today the only lever for a claude_code agent's reasoning effort is the machine-global effortLevel in ~/.claude/settings.json (or the CLAUDE_CODE_EFFORT_LEVEL env var, which the provider already preserves). That silently differs between machines: an orchestrator profile meant to run at xhigh falls back to the Claude Code default (high) on any host where the global setting is absent. codexConfig already solves the equivalent problem per-agent for codex; this brings parity to claude_code.

Example

name: cto
provider: claude_code
claudeConfig:
  effort: xhigh

Tests

test/providers/test_claude_code_unit.py::TestClaudeCodeProviderClaudeConfig: effort flag emitted when set, fallback-model emitted when set, no flag when claudeConfig is absent. Docs updated in docs/agent-profile.md.

Add a `claudeConfig` field to the agent profile, the Claude Code analog of `codexConfig` for the codex provider. The claude_code provider maps it to Claude Code CLI flags at launch: - effort -> --effort <level> - fallback_model -> --fallback-model <model> This lets a profile set per-agent reasoning effort (e.g. an orchestrator at xhigh) without relying on the machine-global `effortLevel` in ~/.claude/settings.json, which silently differs between machines. The top-level `model` field still maps to `--model`.

codecov-commenter · 2026-06-11T08:49:53Z

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (main@1224cd0). Learn more about missing BASE report.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #283   +/-   ##
=======================================
  Coverage        ?   92.15%           
=======================================
  Files           ?       70           
  Lines           ?     7115           
  Branches        ?        0           
=======================================
  Hits            ?     6557           
  Misses          ?      558           
  Partials        ?        0

Flag	Coverage Δ
unittests	`92.15% <100.00%> (?)`

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

Copilot

Pull request overview

Adds per-agent Claude Code launch overrides by introducing a claudeConfig map on AgentProfile, and mapping selected keys to Claude Code CLI flags when building the claude command. This brings profile-level control over reasoning effort / fallback model without relying on machine-global ~/.claude/settings.json settings.

Changes:

Add claudeConfig to AgentProfile and document it in docs/agent-profile.md.
Update ClaudeCodeProvider._build_claude_command() to emit --effort and --fallback-model when profile.claudeConfig is set.
Add unit tests ensuring the flags are emitted/omitted as expected.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

File	Description
`src/cli_agent_orchestrator/providers/claude_code.py`	Map `profile.claudeConfig` entries to `claude` CLI flags during command construction.
`src/cli_agent_orchestrator/models/agent_profile.py`	Extend the agent profile schema with the new optional `claudeConfig` field.
`test/providers/test_claude_code_unit.py`	Add unit tests covering `claudeConfig` → CLI flag behavior.
`docs/agent-profile.md`	Document the new `claudeConfig` profile field and its flag mappings.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

vprudnikoff · 2026-06-19T10:33:16Z

+            # Apply Claude Code-only per-agent knobs from claudeConfig:
+            #   effort         -> --effort <level>
+            #   fallback_model -> --fallback-model <model>
+            # Claude analog of codexConfig: per-agent reasoning effort without
+            # depending on the machine-global effortLevel in
+            # ~/.claude/settings.json.


For context: codexConfig is introduced by the sibling PR #278 (feat/codex-agent-config). This launch-override comment intentionally mirrors that field — claudeConfig is the claude_code analog — so it resolves once both PRs merge. If reviewers prefer this PR to stand alone regardless of merge order, I'm happy to drop the codexConfig mention and describe the behavior on its own.

vprudnikoff · 2026-06-19T10:33:14Z

+    # Claude Code-only. Per-agent Claude Code knobs mapped to CLI flags at
+    # launch: {"effort": "<low|medium|high|xhigh>"} -> `--effort <level>` and
+    # {"fallback_model": "<model>"} -> `--fallback-model <model>`. Lets a
+    # profile set per-agent reasoning effort without relying on the
+    # machine-global `effortLevel` in ~/.claude/settings.json. This is the
+    # Claude analog of codexConfig for the codex provider; the top-level
+    # `model` field still maps to `--model`.


For context: codexConfig is added by the sibling PR #278 (feat/codex-agent-config). claudeConfig here is the deliberate claude_code analog of that field, so this comment cross-references it on purpose; it becomes accurate once both PRs merge. If you'd rather keep this PR independent of merge order, I can drop the codexConfig reference and just describe claudeConfig on its own.

vprudnikoff · 2026-06-19T10:33:13Z

 - `model` (string): AI model to use
 - `permissionMode` (string, `claude_code` only): One of `"default"`, `"acceptEdits"`, `"plan"`, `"auto"`, `"bypassPermissions"`. When set, the `claude_code` provider passes `--permission-mode <value>` instead of `--dangerously-skip-permissions`. `cao launch --yolo` overrides this and forces bypass. See [Claude Code permission modes](https://code.claude.com/docs/en/permission-modes).
 - `native_agent` (string, `claude_code` only): Name of a native Claude Code agent (`~/.claude/agents/`). When set, the provider passes `--agent <name>` directly and skips system prompt / MCP config decomposition (thin-wrapper mode). See [Claude Code native agent routing](claude-code.md#native-agent-routing).
+- `claudeConfig` (object, `claude_code` only): Per-agent Claude Code knobs mapped to CLI flags at launch. `{"effort": "<low|medium|high|xhigh>"}` adds `--effort <level>` and `{"fallback_model": "<model>"}` adds `--fallback-model <model>`. Lets a profile set per-agent reasoning effort without relying on the machine-global `effortLevel` in `~/.claude/settings.json`. The Claude analog of `codexConfig`; the top-level `model` field still maps to `--model`.


Context: codexConfig is introduced by the sibling PR #278 (feat/codex-agent-config). These two are a pair — per-agent provider config: codexConfig for the codex provider, claudeConfig for claude_code — so the cross-reference is intentional and resolves once both land. If you'd prefer each PR to read as fully self-contained regardless of merge order, I'm happy to drop the codexConfig mention here.

haofeif · 2026-06-20T12:40:12Z

@vprudnikoff great PR. I think this needs one behavior fix before approval.

The new claudeConfig.effort emits --effort, but the provider still preserves CLAUDE_CODE_EFFORT_LEVEL in the spawned Claude environment. Claude's model-config docs say the environment variable takes precedence over the other effort mechanisms, so a host-level CLAUDE_CODE_EFFORT_LEVEL can silently override the profile's per-agent effort. That undercuts the PR's stated goal of avoiding machine-global effort drift.

Could we make claudeConfig.effort win explicitly, either by unsetting CLAUDE_CODE_EFFORT_LEVEL when a profile effort is present or by setting it to the same profile value, and add a regression test for that command construction?

On the existing codexConfig comments: I saw your note that #278 is the paired PR. That is fine if #283 is intentionally sequenced after #278, but if this PR may merge independently I would still drop the codexConfig references so the docs are accurate on current main.

One smaller compatibility note: local Claude Code 2.1.181 help says --fallback-model only works with --print, while CAO launches interactive sessions. The public docs no longer show that limitation, so I would just verify/document the minimum Claude Code behavior for that field.


## Checks Run

```bash
git fetch origin main
git -C /tmp/cao-pr283 fetch origin pull/283/head
git -C /tmp/cao-pr283-merge reset --hard origin/main
git -C /tmp/cao-pr283-merge merge --no-commit --no-ff pr-283
git diff --check
uv run pytest test/providers/test_claude_code_unit.py -q
claude -v
claude --claude-help
curl -L https://code.claude.com/docs/en/model-config.md
curl -L https://code.claude.com/docs/en/env-vars.md
curl -L https://code.claude.com/docs/en/cli-reference.md

Results:

git diff --check: passed
test/providers/test_claude_code_unit.py: 111 passed
Local Claude Code: 2.1.181

haofeif requested a review from Copilot June 11, 2026 08:48

Copilot started reviewing on behalf of haofeif June 11, 2026 08:48 View session

Copilot AI reviewed Jun 11, 2026

View reviewed changes

haofeif added the enhancement New feature or request label Jun 12, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(claude_code): per-agent reasoning effort via claudeConfig#283

feat(claude_code): per-agent reasoning effort via claudeConfig#283
vprudnikoff wants to merge 1 commit into
awslabs:mainfrom
vprudnikoff:feat/claude-config

vprudnikoff commented Jun 6, 2026

Uh oh!

codecov-commenter commented Jun 11, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

vprudnikoff Jun 19, 2026

Uh oh!

vprudnikoff Jun 19, 2026

Uh oh!

vprudnikoff Jun 19, 2026

Uh oh!

haofeif commented Jun 20, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

vprudnikoff commented Jun 6, 2026

What

Why

Example

Tests

Uh oh!

codecov-commenter commented Jun 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

vprudnikoff Jun 19, 2026

Choose a reason for hiding this comment

Uh oh!

vprudnikoff Jun 19, 2026

Choose a reason for hiding this comment

Uh oh!

vprudnikoff Jun 19, 2026

Choose a reason for hiding this comment

Uh oh!

haofeif commented Jun 20, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

codecov-commenter commented Jun 11, 2026 •

edited

Loading