refactor: delegate _apply_tool_truncation_async to sync impl

[praisonai-triage-agent]

Fixes #2345

Summary

_apply_tool_truncation_async in agent/chat_mixin.py was a byte-identical copy of the sync _apply_tool_truncation (differing only in docstring and the -async log tag) and contained zero await statements. It is now a thin delegate to the sync implementation, eliminating ~28 duplicated lines and removing the sync/async drift risk.

Changes

• _apply_tool_truncation_async now calls self._apply_tool_truncation(messages, compactor, policy).
• Net: 2 insertions, 30 deletions.

Capability preserved

• Same threshold (1000 chars), same head/tail slicing, same truncation message, same (CompactionRoute.TRUNCATE_TOOLS, truncated_msgs) return.
• Async call sites still await the method — unaffected.

Validation

• Functional parity check: sync and async paths produce identical output for a 2000-char tool message.
• Module imports cleanly.

Generated with Claude Code

Summary by CodeRabbit

• Refactor
  • Simplified tool-output truncation so async handling now uses the same shared logic as the synchronous path.
  • Centralized truncation behavior to keep results more consistent across chat processing.

[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]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: eb583258-fdd0-420b-ae6d-2edfab67a151

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

📝 Walkthrough

Walkthrough

The async tool-output truncation helper now delegates to the shared synchronous truncation implementation. The async-specific copy of truncation, token counting, and logging logic was removed.

Changes

Tool truncation delegation

Layer / File(s)	Summary
Async wrapper delegation src/praisonai-agents/praisonaiagents/agent/chat_mixin.py	_apply_tool_truncation_async now forwards to _apply_tool_truncation, and the async-specific truncation body was removed.

Sequence Diagram(s)

None

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• MervinPraison/PraisonAI#1572: Also touches the tool-execution path and truncation behavior in ChatMixin.

Suggested labels

Review effort 2/5

Suggested reviewers

• MervinPraison

Poem

A bunny hopped through truncation light,
🐇 snippets trimmed and tucked just right.
The async path gave sync a call,
one shared trail now serves them all.
Flop, hop, done — neat as a night.

🚥 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 summarizes the refactor to delegate _apply_tool_truncation_async to the sync implementation.
Linked Issues check	✅ Passed	The change removes duplicated async truncation logic by delegating to the sync helper, matching issue #2345's no-behavior-change goal.
Out of Scope Changes check	✅ Passed	The PR only refactors the async truncation path in chat_mixin.py and does not introduce unrelated changes.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch claude/issue-2345-20260626-1711

---

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 tool-output truncation so the async path reuses the shared helper.

• Adds a configurable log tag to the sync truncation helper.
• Keeps the sync path on the tool-truncation log tag.
• Delegates async truncation to the shared helper with the tool-truncation-async log tag.

Confidence Score: 5/5

This looks safe to merge.

• No blocking issues found in the changed code.

Important Files Changed

Filename	Overview
src/praisonai-agents/praisonaiagents/agent/chat_mixin.py	The async truncation wrapper now delegates to the shared helper while preserving its async log tag.

_{Reviews (2): Last reviewed commit: "fix: preserve [tool-truncation-async] lo..." | 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 #2346 ✅

• Read AGENTS.md guidelines
• Read changed file chat_mixin.py
• Assess Greptile P2 log-tag concern
• Apply fix
• Run tests (functional parity verified)
• Final verdict + push

---

Phase 1 — Review per AGENTS.md

Criterion	Verdict
Protocol-driven	✅ Pure refactor in the wrapper layer; no new heavy impl in core.
Backward compatible	✅ Same threshold (1000), same head/tail slicing, same return tuple (TRUNCATE_TOOLS, msgs). Async call sites still await. Zero behavior regression.
Performance	✅ No hot-path regression — removes a duplicated loop; delegation is a single sync call (the async body had zero await, so nothing is lost).
SDK value	✅ Genuinely strengthens the SDK: eliminates ~28 byte-identical duplicated lines and removes a real sync/async drift risk. Not scope creep.
No Agent bloat	✅ No new Agent params. The fix below adds only a private-method kwarg, not a public surface.

This is a clean, valuable refactor that matches issue #2345 exactly.

Phase 2 — Fixed valid issue

Greptile P2 (VALID): Async truncation log misclassified. After delegation, the async path emitted the sync [tool-truncation] tag, dropping the prior [tool-truncation-async] marker. Any log filter/dashboard keying on the async tag would silently lose those events.

Fix (src/praisonai-agents/praisonaiagents/agent/chat_mixin.py):

• Added optional log_tag="tool-truncation" kwarg to _apply_tool_truncation (line 789).
• Log line now uses f"[{log_tag}] …" (line 815).
• _apply_tool_truncation_async delegates with log_tag="tool-truncation-async" (line 910).

This restores the diagnostic distinction without re-introducing the duplicated body — the refactor's core goal is preserved (net +3/-3, still a thin delegate).

Skipped (not actionable): Qodo (reviews paused — no findings), CodeRabbit (🎉 no actionable comments), Copilot/Gemini (no concrete blocking items surfaced beyond the log tag already handled).

Validation

import OK
functional parity OK   # sync & async produce identical output for a 2000-char tool msg

Confirmed: async path now logs [tool-truncation-async], sync logs [tool-truncation]. No tests/external code depend on the tag string (grep-verified), so this is a safe, additive change.

Phase 3 — Verdict: ✅ Approve (changes applied)

All reviewer feedback resolved. The PR is a net-positive de-duplication with backward-compatible behavior and now correct diagnostics. Pushed c23b7338 to this branch.

Note: I can't formally approve via GitHub review (security restriction), but from an architecture standpoint this is ready to merge.
• Branch: claude/issue-2345-20260626-1711

[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 #2346 ✅

• Read AGENTS.md guidelines
• Read changed file chat_mixin.py (current state)
• Verify Greptile P2 log-tag fix is in place
• Run validation
• Final verdict

---

Phase 1 — Review per AGENTS.md

Criterion	Verdict
Protocol-driven	✅ Pure refactor in the wrapper-method layer; no new heavy impl in core.
Backward compatible	✅ Same threshold (1000 chars), same head/tail slicing ([:300] / [-200:]), same return tuple (TRUNCATE_TOOLS, msgs). Async call sites still await (lines 855, 861). Zero behavior regression.
Performance	✅ No hot-path regression — the deleted async body had zero await, so delegation to the sync impl loses nothing and removes a duplicated loop.
SDK value	✅ Genuinely strengthens the SDK: removes ~28 byte-identical duplicated lines and eliminates real sync/async drift risk. Not scope creep.
No Agent bloat	✅ No new Agent params. Only a private-method kwarg (log_tag) was added — not public surface.

Phase 2 — Valid issues already fixed

Greptile P2 (VALID, resolved in commit c23b7338): After delegation the async path would have emitted the sync [tool-truncation] tag, dropping the prior [tool-truncation-async] marker. Confirmed fixed:

• _apply_tool_truncation(... log_tag="tool-truncation") — chat_mixin.py:789
• Log line uses f"[{log_tag}] …" — chat_mixin.py:814-816
• Async wrapper delegates with log_tag="tool-truncation-async" — chat_mixin.py:910

This restores the diagnostic distinction without re-introducing the duplicated body.

Skipped (not actionable): Qodo (reviews paused — no findings), CodeRabbit (no actionable comments), Copilot/Gemini (no concrete blocking items beyond the log tag, already handled).

Validation

import OK
async delegates to sync: True
async log_tag = "tool-truncation-async": True

(pytest not installed in this runner env; verified via static + runtime introspection. grep confirms no tests/external code depend on the tag string, so the change is safe and additive.)

Phase 3 — Verdict: ✅ Approve (no further changes required)

All reviewer feedback is resolved on the current HEAD (c23b7338). The PR is a net-positive de-duplication with backward-compatible behavior and correct diagnostics. From an architecture standpoint this is ready to merge.

Note: I can't formally approve via the GitHub review API (security restriction), but this is my architectural sign-off. No new commits were needed this round — the branch already contains the complete fix.
• Branch: claude/issue-2345-20260626-1711