fix: remove duplicate attempt field in OnRetryInput dataclass

[praisonai-triage-agent]

Fixes #2896

Summary

The OnRetryInput hook dataclass in praisonaiagents/hooks/events.py declared the attempt field twice with conflicting defaults (1 then 0). Python keeps only the last annotation, so the intended 1-based default was silently shadowed by 0. The to_dict() method also wrote the "attempt" key twice (a no-op).

Changes

• Removed the shadowing second attempt: int = 0 declaration, keeping a single attempt: int = 1 field with the intended 1-based default and a clarifying comment.
• Removed the duplicate "attempt" key in to_dict().

Capability preserved

• All four production constructors (agent/tool_execution.py, agent/execution_mixin.py, agent/chat_mixin.py:4254 and :4335) pass attempt= explicitly, so runtime behaviour is unchanged.
• to_dict() output is identical (the duplicate key produced a single entry).
• All legacy back-compat fields and hook firing behaviour untouched.

Validation

• Verified default is now 1 and to_dict()["attempt"] returns 1.
• tests/unit/hooks/ — 65 passed.
• tests/unit/tools/test_retry.py + tests/unit/test_tool_retry_integration.py — 38 passed.

Generated with Claude Code

Summary by CodeRabbit

• Bug Fixes
  • Retry attempt numbering now starts at 1, providing clearer and more intuitive retry tracking.
  • Retry event details continue to include delay information in the serialized output.

[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: 4c7460e9-0241-4ee7-a7fa-66543a25fb87

📥 Commits

Reviewing files that changed from the base of the PR and between ca6489a and f3f5463.

📒 Files selected for processing (1)

• src/praisonai-agents/praisonaiagents/hooks/events.py

---

📝 Walkthrough

Walkthrough

OnRetryInput now defaults attempt to 1-based indexing, and its serialized delay_seconds field is emitted later in the payload.

Changes

Retry input contract

Layer / File(s)	Summary
Retry input default and serialization src/praisonai-agents/praisonaiagents/hooks/events.py	Updates the default attempt value and changes the position of delay_seconds in to_dict() output.

Estimated code review effort: 2 (Simple) | ~10 minutes

🚥 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 clearly matches the main OnRetryInput cleanup and is specific enough for history scanning.
Linked Issues check	✅ Passed	The PR removes the duplicate attempt field and duplicate to_dict key requested in #2896 and keeps the intended default of 1.
Out of Scope Changes check	✅ Passed	No unrelated changes are evident beyond the requested OnRetryInput cleanup and a minor dict field ordering adjustment.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ 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-2896-20260710-1713

---

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.}

[greptile-apps]

Greptile Summary

This PR cleans up the retry hook input shape. The main changes are:

• Keeps a single OnRetryInput.attempt field with the 1-based default.
• Removes the shadowing duplicate attempt declaration.
• Removes the duplicate attempt entry from to_dict().

Confidence Score: 5/5

This looks safe to merge.

• No blocking issues found in the changed code.
• Current production retry hook constructors pass attempt explicitly.
• Serialized retry hook output stays the same for those paths.

Important Files Changed

Filename	Overview
src/praisonai-agents/praisonaiagents/hooks/events.py	Removes duplicate attempt declarations and serialization keys from OnRetryInput without changing current explicit constructor paths.

_{Reviews (1): Last reviewed commit: "fix: remove duplicate attempt field in O..." | 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.
6. Repo routing: agent-callable tools → PraisonAI-Tools; lifecycle plugins → PraisonAI-Plugins; optional sandbox backends → PraisonAI-Plugins (praisonai.sandbox entry point) — request changes if wrongly added to praisonaiagents/

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

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

[praisonai-triage-agent]

Claude finished @MervinPraison's task —— View job

---

Final Architecture Review — PR #2898 ✅ Approved

• Read AGENTS.md + changed file
• Validate the fix (correctness, backward compat)
• Review reviewer feedback (Greptile, CodeRabbit, Qodo)
• Verify runtime behaviour
• Final verdict

---

Phase 1 — Architecture Review

Criterion	Verdict
Protocol-driven	✅ Change is confined to a hook input dataclass in core praisonaiagents/hooks/events.py — correct location, no heavy impl.
Backward compatible	✅ All 4 production constructors pass attempt= explicitly (execution_mixin.py:1490, chat_mixin.py:4254 & :4335, tool_execution.py:2001), so runtime behaviour is unchanged. Legacy fields untouched.
Performance	✅ Pure dataclass cleanup, zero hot-path impact.
SDK value	✅ Genuine correctness fix — a duplicate attempt annotation silently shadowed the intended 1‑based default with 0, and to_dict() wrote the key twice. Removing it makes the default correct and the shape unambiguous. No scope creep.
Agent bloat	✅ No Agent params added.
Repo routing	✅ Hook lifecycle type lives correctly in core (it is a protocol/data type, not a heavy plugin implementation).

Phase 2 — Reviewer Feedback

• Greptile: 5/5, safe to merge, no blocking issues. ✅ Concur.
• CodeRabbit: still processing; nothing actionable flagged. Diff is 2 lines net.
• Qodo: reviews paused (billing) — nothing to action.

No valid bugs or architectural flaws raised by any reviewer. No additional fixes needed.

Verification (runtime)

default attempt = 1
to_dict attempt = 1
delay_seconds in dict = True   # not accidentally dropped
attempt key count = 1          # duplicate key removed
OK

Note: I was unable to run the full pytest suite here (the pytest invocation was outside my approved command allowlist). Correctness was validated via direct construction/serialization above; the PR author reports 65 + 38 tests passing. If you'd like me to run the suites, add Bash(python -m pytest:*) / the relevant path to --allowedTools.

Phase 3 — Final Verdict

✅ Approved. Minimal, focused, backward-compatible correctness fix. No files modified by me — the committed change is already complete and correct. Safe to merge.
• Branch: claude/issue-2896-20260710-1713