fix: consolidate duplicate AutoGen config_list builder into shared helper

[praisonai-triage-agent]

Fixes #2339

Summary

Introduces a single shared helper praisonai/llm/config.py::build_config_list() that performs the endpoint resolve + AutoGen-style dict build, and updates the three duplicated call sites to delegate to it.

Changes

• New praisonai/llm/config.py: build_config_list(*, include_api_type=True) — single owner of the endpoint→config mapping, reusing resolve_llm_endpoint().
• _entrypoint.py: _build_config_list() now delegates to the helper.
• cli/main.py: PraisonAI.__init__ uses build_config_list().
• auto.py: AutoGenerator.__init__ uses build_config_list(include_api_type=False) to preserve its existing behaviour (no api_type).

Behaviour

No command, flag, or behaviour changes. All three call sites build exactly the same config_list as before — the include_api_type flag preserves auto.py's prior omission of api_type.

Validation

• grep "'model': ep.model" now matches only the new helper.
• Verified build_config_list() returns {model, base_url, api_key, api_type} and include_api_type=False omits api_type; _build_config_list() output is identical to before.

Generated with Claude Code

Summary by CodeRabbit

• Bug Fixes

  • Unified how the app builds LLM connection settings across the CLI and agent startup paths.
  • Improved default configuration handling when no custom settings are provided, helping reduce startup inconsistencies.

• Refactor

  • Moved configuration assembly into a shared flow so multiple entry points now use the same setup logic.

[MervinPraison]

@coderabbitai review

[MervinPraison]

/review

[qodo-code-review]

Qodo reviews are paused for this user.

Troubleshooting steps vary by plan Learn more →

On a Teams plan?
Reviews resume once this user has a paid seat and their Git account is linked in Qodo.
Link Git account →

Using GitHub Enterprise Server, GitLab Self-Managed, or Bitbucket Data Center?
These require an Enterprise plan - Contact us
Contact us →

[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]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 33629a00-9a18-4624-9a54-cc80bccf0435

📥 Commits

Reviewing files that changed from the base of the PR and between b5a45bf and 5b84a84.

📒 Files selected for processing (4)

• src/praisonai/praisonai/_entrypoint.py
• src/praisonai/praisonai/auto.py
• src/praisonai/praisonai/cli/main.py
• src/praisonai/praisonai/llm/config.py

---

📝 Walkthrough

Walkthrough

A shared build_config_list() helper was added in praisonai.llm.config, and the Python entrypoint, CLI startup, and auto generator initialization now use it to construct their AutoGen config_list values.

Changes

Shared AutoGen config list

Layer / File(s)	Summary
Add shared builder src/praisonai/praisonai/llm/config.py	A new helper resolves the active LLM endpoint and returns a one-entry AutoGen config list, optionally adding api_type.
Delegate wrapper call sites src/praisonai/praisonai/_entrypoint.py, src/praisonai/praisonai/cli/main.py, src/praisonai/praisonai/auto.py	The entrypoint, CLI constructor, and base auto generator now call the shared helper instead of building the config list inline. auto.py passes include_api_type=False.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Poem

A bunny hopped through config glades,
One helper now where three paths strayed.
🐇 base_url twinkles, api_key bright,
The list grows once, then feels just right.
Thump-thump—shared hops make the code parade.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the main change: consolidating duplicated AutoGen config_list construction into a shared helper.
Linked Issues check	✅ Passed	The PR adds a shared build_config_list helper and updates the three duplicated call sites while preserving auto.py's api_type behavior.
Out of Scope Changes check	✅ Passed	The changes are narrowly scoped to the config_list duplication fix and do not introduce unrelated functionality.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch claude/issue-2339-20260626-1610

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

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

[MervinPraison]

@copilot Do a thorough review of this PR. Read ALL existing reviewer comments above from Qodo, Coderabbit, and Gemini first — incorporate their findings.

Review areas:

1. Bloat check: Are changes minimal and focused? Any unnecessary code or scope creep?
2. Security: Any hardcoded secrets, unsafe eval/exec, missing input validation?
3. Performance: Any module-level heavy imports? Hot-path regressions?
4. Tests: Are tests included? Do they cover the changes adequately?
5. Backward compat: Any public API changes without deprecation?
6. Code quality: DRY violations, naming conventions, error handling?
7. Address reviewer feedback: If Qodo, Coderabbit, or Gemini flagged valid issues, include them in your review
8. Suggest specific improvements with code examples where possible

[greptile-apps]

Greptile Summary

This PR centralizes the AutoGen config list builder. The main changes are:

• Added build_config_list() in praisonai.llm.config.
• Updated the entrypoint and CLI paths to use the shared helper.
• Updated auto.py to use the helper while still omitting api_type.

Confidence Score: 5/5

This looks safe to merge.

• No blocking issues found in the changed code.
• The helper preserves the old config shapes for each updated caller.
• The new import path remains lazy and does not add a new import cycle.

Important Files Changed

Filename	Overview
src/praisonai/praisonai/llm/config.py	Adds the shared helper that builds a fresh config list from the resolved LLM endpoint.
src/praisonai/praisonai/_entrypoint.py	Replaces inline config construction with the shared helper while keeping api_type included.
src/praisonai/praisonai/cli/main.py	Uses the shared helper for CLI config list initialization.
src/praisonai/praisonai/auto.py	Uses the shared helper with include_api_type=False to preserve the existing fallback shape.

_{Reviews (1): Last reviewed commit: "fix: consolidate duplicate AutoGen confi..." | Re-trigger Greptile}

[MervinPraison]

@claude You are the FINAL architecture reviewer. If the branch is under MervinPraison/PraisonAI (not a fork), you are able to make modifications to this branch and push directly. SCOPE: Focus ONLY on Python packages (praisonaiagents, praisonai). Do NOT modify praisonai-rust or praisonai-ts. Read ALL comments above from Gemini, Qodo, CodeRabbit, and Copilot carefully before responding.

Phase 1: Review per AGENTS.md

1. Protocol-driven: check heavy implementations vs core SDK
2. Backward compatible: ensure zero feature regressions
3. Performance: no hot-path regressions
4. SDK value: review in depth whether the change genuinely adds value to the SDK — never add features for the sake of adding them. It must strengthen the SDK (simpler, more user-friendly, robust, world-class, secure). If it does not clearly add value, request changes or recommend rejecting/closing rather than merging scope creep
5. Do not bloat the Agent class with additional params — only if absolutely required; we already support many params.

Phase 2: FIX Valid Issues
5. For any VALID bugs or architectural flaws found by Gemini, CodeRabbit, Qodo, Copilot, or any other reviewer: implement the fix
6. Push all code fixes directly to THIS branch (do NOT create a new PR)
7. Comment a summary of exact files modified and what you skipped

Phase 3: Final Verdict
8. If all issues are resolved, approve the PR / close the Issue
9. If blocking issues remain, request changes / leave clear action items

[praisonai-triage-agent]

Claude finished @MervinPraison's task —— View job

---

Final Architecture Review — PR #2342 ✅ Approve

• Read AGENTS.md guidelines
• Read all 4 changed files
• Validate refactor (backward compat, performance, value)
• Address reviewer feedback (CodeRabbit, Greptile, Copilot, Qodo)
• Run tests
• Final verdict

---

Phase 1 — Architecture Review (per AGENTS.md)

Check	Verdict
Routing (core vs wrapper)	✅ Correctly placed in wrapper (praisonai/llm/config.py), not core SDK. AutoGen config assembly is wrapper-level concern.
Protocol-driven	✅ No heavy logic; just reuses existing resolve_llm_endpoint().
Backward compatible	✅ Verified byte-for-byte identical output (see below).
Performance / hot path	✅ Import stays lazy (from praisonai.llm.config import build_config_list inside functions). No module-level heavy import added. Minimal API surface in _entrypoint.py preserved.
SDK value	✅ Genuine DRY win — removes 3 copies of the endpoint→dict mapping. Future provider fields change in one place. No scope creep, no new params, no Agent bloat.
Agent class bloat	✅ N/A — Agent untouched.

Phase 2 — Reviewer Feedback

All prior reviewers (CodeRabbit — no actionable comments; Greptile — 5/5, safe to merge; Copilot/Qodo — no blocking issues; Qodo paused) reported no valid bugs. I independently verified rather than rubber-stamping:

Verified backward compatibility (ran locally):

with api_type:    ['api_key', 'api_type', 'base_url', 'model']   # cli/main.py path
without api_type: ['api_key', 'base_url', 'model']               # auto.py path
OK backward compatible

• cli/main.py previously included 'api_type': 'openai' → now build_config_list() (default include_api_type=True). ✅ identical.
• auto.py previously omitted api_type → now build_config_list(include_api_type=False). ✅ identical.
• Diff confirms the inline dicts were removed verbatim and replaced 1:1.

Validation claim confirmed — grep "'model': ep.model" now matches only llm/config.py:31. Single owner achieved.

Tests: tests/unit/llm/test_env_resolver.py (46 passed). One failure in test_auto_lazy_loading.py::test_typer_commands_failure_does_not_poison_cache is pre-existing and unrelated — it asserts on praisonai.cli.app typer registration, not config_list, and is not touched by this PR.

Phase 3 — Verdict

✅ Approve. No fixes required — the refactor is minimal, focused, behaviour-preserving, and a legitimate DRY improvement. No bugs, no security issues (no secrets, no eval/exec), no performance regression, no public API change. Nothing to push.

Files reviewed: llm/config.py (new), _entrypoint.py, cli/main.py, auto.py. Skipped: none.
• Branch: claude/issue-2339-20260626-1610

[MervinPraison]

MERGE_GATE_VERDICT: APPROVE

Automated fallback — Claude assess did not post a verdict comment (e.g. GitHub MCP unavailable).
All deterministic merge gates passed.

[MervinPraison]

Merged by Claude PR merge gate (claude-merge-gate.yml).
Verdict: MERGE_GATE_VERDICT: APPROVE
SHA: 5b84a84
Method: merge