Rockachopa/Timmy-time-dashboard
1
0
Fork 2
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

[loop-generated] [bug] Agent run crashes on Ollama 500 — no retry for XML parse errors #131

New Issue
Closed
opened 2026-03-15 12:47:38 +00:00 by hermes · 0 comments
hermes commented 2026-03-15 12:47:38 +00:00
Collaborator
Copy Link

Problem

When qwen3.5 (or any model) generates malformed tool-call XML, Ollama's Go layer returns a 500 with:

XML syntax error on line 6: element <function> closed by </parameter> (status code: 500)

This bubbles up through Agno as an unhandled exception in base.py:134 and crashes the agent run. There is no retry logic.

Impact

  • Timmy's triage call in the dev loop fails entirely
  • Any chat session hitting this transient error gets no response
  • The error is non-deterministic (same prompt works on retry)

Root Cause

Ollama 500s are transient — the model's sampling produced bad XML on that particular generation. Retrying with the same prompt almost always succeeds.

Fix

Add retry logic in src/timmy/agents/base.py run() method:

  1. Catch generic exceptions that include "status code: 500" or "XML syntax error"
  2. Retry up to 2 times with a brief delay
  3. Log each retry attempt
  4. Only raise after all retries exhausted

Alternatively, add retry at the Agno/Ollama model layer in agent.py create_timmy().

Files

  • src/timmy/agents/base.py — run() method (line 121-147)
  • src/timmy/agent.py — create_timmy() agent creation

Observed in

Loop cycle 37 triage call, 2026-03-15

## Problem When qwen3.5 (or any model) generates malformed tool-call XML, Ollama's Go layer returns a 500 with: ``` XML syntax error on line 6: element <function> closed by </parameter> (status code: 500) ``` This bubbles up through Agno as an unhandled exception in `base.py:134` and crashes the agent run. There is no retry logic. ## Impact - Timmy's triage call in the dev loop fails entirely - Any chat session hitting this transient error gets no response - The error is non-deterministic (same prompt works on retry) ## Root Cause Ollama 500s are transient — the model's sampling produced bad XML on that particular generation. Retrying with the same prompt almost always succeeds. ## Fix Add retry logic in `src/timmy/agents/base.py` `run()` method: 1. Catch generic exceptions that include "status code: 500" or "XML syntax error" 2. Retry up to 2 times with a brief delay 3. Log each retry attempt 4. Only raise after all retries exhausted Alternatively, add retry at the Agno/Ollama model layer in `agent.py` `create_timmy()`. ## Files - `src/timmy/agents/base.py` — `run()` method (line 121-147) - `src/timmy/agent.py` — `create_timmy()` agent creation ## Observed in Loop cycle 37 triage call, 2026-03-15
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
222-epic
Workshop: Timmy as Presence (Epic #222)
 actionable
Has a concrete code/config task extracted
 assigned-claude
Issue currently assigned to Claude agent — do not assign to another agent
 assigned-gemini
Issue currently assigned to Gemini agent — do not assign to another agent
 assigned-groq
assigned-kimi
Issue currently assigned to Kimi agent — do not assign to another agent
 assigned-manus
Issue currently assigned to Manus agent — do not assign to another agent
 claude-ready
consolidation
Part of a consolidation epic
 deprioritized
Keep open but not blocking P0 work
 deprioritized
Keep open but not blocking P0 work
 duplicate
Duplicate of another issue
 gemini-review
Auto-generated by Gemini, needs relevance review
 groq-ready
harness
Core product: agent framework, heartbeat, inference, memory
 heartbeat
Harness: Agent heartbeat loop
 inference
Harness: Inference and model routing
 infrastructure
Supporting stage: dashboard, CI/CD, deployment, DNS
 kimi-ready
Scoped and ready for Kimi to pick up
 memory-session
Harness: Memory and session crystallization
 morrowind
Harness: Morrowind embodiment
 needs-design
Needs architectural design before implementation
 needs-extraction
Philosophy with unextracted engineering work
 p0-critical
Priority 0: Must fix now
 p1-important
Priority 1: Important, next sprint
 p2-backlog
Priority 2: Backlog, do when time permits
 philosophy
Philosophical foundation — informs architecture decisions
 rejected-direction
Closed: rejected or superseded direction
 seed:know-purpose
Three Seeds: KNOW YOUR PURPOSE
 seed:serve-real
Three Seeds: SERVE THE REAL
 seed:tell-truth
Three Seeds: TELL THE TRUTH
 sovereignty
Harness: Sovereignty stack
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
Timmy claude grok groq kimi manus perplexity Rockachopa
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Rockachopa/Timmy-time-dashboard#131
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?