examples/workflows/workflow_evaluator_optimizer/mcp_agent.config.yaml (1)

25-25: Confirm model id and avoid double-setting it.

• Verify that "gpt-5" is a valid and enabled model for your OpenAI account/region; otherwise runs will fail at runtime.
• Since you also pass model="gpt-5" at the call site, prefer a single source of truth (config OR request_params), not both.

Would you like me to strip the per-call override in main.py to rely solely on this config?

examples/workflows/workflow_evaluator_optimizer/requirements.txt (1)

2-2: Clarify local-dev install and consider reproducibility.

• The commented local path is fine; consider moving this to a dev extra (pyproject) or a "requirements.dev.txt" to avoid accidental commits flipping it.
• Pin or constrain anthropic/openai to avoid surprise breaks in examples run in CI or cloud.

Apply this small wording tweak for clarity:

-# mcp-agent @ file://../../../  # Link to the local mcp-agent project root, to run locally remove comment of this line
+# To run locally against the monorepo, uncomment the next line:
+# mcp-agent @ file://../../../

examples/workflows/workflow_evaluator_optimizer/main.py (2)

27-33: Make inputs required (or lighter) for cleaner tool schemas.

The long default texts become part of the tool schema and may clutter UIs. Prefer required params (no defaults) or short illustrative examples in the description.

Example:

-async def example_usage(
-    job_posting: str = "Software Engineer at LastMile AI. Responsibilities include developing AI systems, "
-                       "collaborating with cross-functional teams, and enhancing scalability. Skills required: "
-                       "Python, distributed systems, and machine learning.",
-    candidate_details: str = "Alex Johnson, 3 years in machine learning, contributor to open-source AI projects, "
-                            "proficient in Python and TensorFlow. Motivated by building scalable AI systems to solve real-world problems.",
-    company_information: str = "Look up from the LastMile AI About page: https://lastmileai.dev/about"
-):
+async def example_usage(
+    job_posting: str,
+    candidate_details: str,
+    company_information: str,
+):

---

78-79: Don’t override the model if config sets it; also verify gpt-5 availability.

Let the config pick the default model to keep flexibility across environments.

-            request_params=RequestParams(model="gpt-5"),
+            request_params=RequestParams(),

If you need a per-call override later, wire it as a function parameter instead of hardcoding.

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

Learnt from: rholinshead
PR: lastmile-ai/mcp-agent#414
File: src/mcp_agent/logging/logger.py:18-19
Timestamp: 2025-09-05T14:31:48.115Z
Learning: In the mcp-agent logging module (src/mcp_agent/logging/logger.py), temporalio should be imported lazily with try/except ImportError to avoid making it a hard dependency. Use temporalio.workflow.in_workflow() instead of isinstance checks on internal classes like _WorkflowInstanceImpl.

examples/workflows/workflow_evaluator_optimizer/main.py (1)

81-82: Avoid logging full generated content (PII/large payloads).

-        logger.info(f"Generated cover letter: {result}")
+        preview = result[:400]
+        logger.info(
+            "Generated cover letter",
+            preview=preview + ("..." if len(result) > len(preview) else ""),
+            length=len(result),
+        )

examples/workflows/workflow_evaluator_optimizer/mcp_agent.secrets.yaml.example (2)

9-11: Prefer commented placeholders to avoid accidental check‑ins.

Comment out the example api_key line and highlight !developer_secret as the primary path.

-  api_key: your-openai-api-key
-  # For cloud deployment, use developer secrets:
-  # api_key: !developer_secret OPENAI_API_KEY
+  # api_key: your-openai-api-key
+  # For cloud deployment, prefer developer secrets:
+  # api_key: !developer_secret OPENAI_API_KEY

---

16-18: Mirror the OpenAI section change for consistency.

-  api_key: your-anthropic-api-key
-  # For cloud deployment, use developer secrets:
-  # api_key: !developer_secret ANTHROPIC_API_KEY
+  # api_key: your-anthropic-api-key
+  # For cloud deployment, prefer developer secrets:
+  # api_key: !developer_secret ANTHROPIC_API_KEY

examples/workflows/workflow_evaluator_optimizer/mcp_agent.config.yaml (2)

8-15: Default log level “debug” is noisy for cloud. Suggest “info” + env override.

-  level: debug          # Logging level (debug, info, warning, error)
+  level: info           # Default to info in examples; override via env if needed

Optional: support LOG_LEVEL env in your logger bootstrap.

---

32-34: Model default aligned with code; consider removing the explicit override in code.

Since default_model is gpt-4.1, you can omit RequestParams(model="gpt-4.1") to rely on config.

examples/workflows/workflow_evaluator_optimizer/README.md (3)

69-69: Repeat of the provider mismatch.

The “only one API key” guidance implies either provider. This will confuse Anthropic‑only users unless code supports it.

---

105-113: Secrets snippet uses the config schema header.

Use a secrets schema (if available) or remove $schema from the secrets file example to prevent invalid schema validation.

-$schema: ../../../schema/mcp-agent.config.schema.json
-
 openai:
   api_key: !developer_secret OPENAI_API_KEY
@@
 anthropic:
   api_key: !developer_secret ANTHROPIC_API_KEY

---

204-214: Sample output looks like a Python repr embedded in JSON.

Consider showing realistic JSON (not a Python‑style dict string) or clearly marking it as a string preview.

-    "result": "{'kind': 'workflow_result', 'value': '[Your optimized cover letter]'}",
+    "result": "[Your optimized cover letter preview…]",
+    "meta": { "kind": "workflow_result" }

examples/workflows/workflow_evaluator_optimizer/main.py (2)

76-79: Redundant explicit model override.

Config already sets default_model to gpt‑4.1. Consider relying on config unless you need to override per‑workflow.

-        result = await evaluator_optimizer.generate_str(
-            message=f"Write a cover letter for the following job posting: {job_posting}\n\nCandidate Details: {candidate_details}\n\nCompany information: {company_information}",
-            request_params=RequestParams(model="gpt-4.1"),
-        )
+        result = await evaluator_optimizer.generate_str(
+            message=f"Write a cover letter for the following job posting: {job_posting}\n\nCandidate Details: {candidate_details}\n\nCompany information: {company_information}",
+            request_params=RequestParams(),
+        )

---

27-33: Enrich tool schema with parameter descriptions.

Use typing.Annotated to surface per‑param docs in the tool’s JSON schema.

from typing import Annotated

async def example_usage(
    job_posting: Annotated[str, "Job description and requirements"] = "...",
    candidate_details: Annotated[str, "Candidate background and qualifications"] = "...",
    company_information: Annotated[str, "Company details or a URL to fetch"] = "...",
):
    ...

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

Learnt from: CR
PR: lastmile-ai/mcp-agent#0
File: examples/usecases/reliable_conversation/CLAUDE.md:0-0
Timestamp: 2025-07-22T18:59:49.368Z
Learning: Applies to examples/usecases/reliable_conversation/examples/reliable_conversation/src/utils/config.py : Configuration values such as quality_threshold, max_refinement_attempts, consolidation_interval, and evaluator_model_provider must be loaded from mcp_agent.config.yaml.