Bug: OpenCode Enters Infinite Loop After Tool Calls Complete

Description

OpenCode (opencode) enters an infinite loop and stops responding to user input after completing tool calls. The process stays alive but never exits or continues meaningfully.

Affected Versions

• Big Pickle (opencode/big-pickle) with OpenCode Zen provider ⚠️ PRIMARY ISSUE
• v1.1.60+ (GitHub Copilot provider with claude-sonnet-4.6) - similar symptoms
• v1.3.0+ (with OpenAI-compatible providers) - similar symptoms
• Issue opencode run hangs after completing tool calls — process never exits #17516 confirmed in v1.1.65 through v1.3.0

Symptoms

1. Process never exits: opencode run hangs indefinitely after tool calls complete
2. Silent infinite loop: Session processor keeps calling LLM with empty responses
3. No CPU usage: Process alive at 0-2% CPU, doing nothing useful
4. No error output: Logs show no errors, no timeouts
5. Parent sessions block: When used as subagent, parent hangs forever waiting

Root Cause (from issue #17516)

OpenCode doesn't detect "done" state properly.

After the model finishes tool calls and produces final text response:

1. Session processor should detect finish_reason=stop or "no tool calls in text-only response"
2. Instead, it treats the response as requiring another iteration
3. Calls LLM again with same context
4. Creates infinite loop of empty LLM calls

Timeline from debug logs:

18:53:24 | step=0  | Session created, prompt resolved
18:53:27 | step=1  | Model calls Read/Write → both succeed
18:53:32 | step=2  | LLM stream → NO tool call, NO visible output
18:53:35 | step=3  | Same pattern — empty loop iteration
...
18:55:21 | step=42 | Still looping when killed at 120s

Pattern per step (steps 2-42):

session.prompt step=N
session.prompt status=started resolveTools
tool.registry status=started/completed (all 12 tools)
permission evaluate (task general, task explore)
session.prompt status=completed resolveTools
session.processor process
llm providerID=opencode/big-pickle modelID=zen stream
→ next step (infinite loop)

Related Issues Found

Reproduction Steps

# Create a prompt that uses tools
cat > /tmp/test-prompt.md << 'EOF'
Read compress.py and replace the RLE implementation with zlib.
Edit the file directly. Do not run any commands.
EOF

# Run with debug logging - using Big Pickle + Zen provider
opencode run --print-logs --log-level DEBUG \
  -m opencode/big-pickle \
  < /tmp/test-prompt.md 2>debug.log

# Process hangs after tool calls complete
# debug.log shows session.prompt stepping infinitely with no tool calls
# LLM provider: opencode/big-pickle with Zen

Expected Behavior

After the model's final text response (post-tool-call), OpenCode should:

1. Detect that the model has finished (finish_reason=stop or no tool calls)
2. Exit cleanly with code 0
3. NOT call LLM again

Actual Behavior

OpenCode:

1. Treats final response as requiring another iteration
2. Calls LLM again with same context
3. Loops infinitely with empty LLM calls every ~2.5s
4. Never exits, never produces output
5. Must be killed manually (Ctrl+C or kill -9)

Workarounds

1. Switch models: Use gpt-5.3-codex instead of claude-sonnet-4.6 (works perfectly)
2. Switch providers: Use different provider that sends proper stop signals
3. Manual kill + restart: Ctrl+C and rephrase prompt

Suggested Fixes

Fix 1: Detect finish_reason=stop (Primary)

In processor.ts, the process() function should return "stop" when finish_reason=stop:

// In processor.ts process() function
if (response.finish_reason === 'stop' && !response.tool_calls) {
  return "stop"; // Currently returns "continue"
}

Fix 2: Break on Empty Responses

If LLM is called but produces NO tool calls and NO text, treat as done:

// After LLM stream completes
if (!response.content && (!response.tool_calls || response.tool_calls.length === 0)) {
  logger.info('Empty response detected, stopping loop');
  return "stop";
}

Fix 3: Add Loop Detection

Detect when same prompt step repeats without progress:

// Track consecutive empty responses
let consecutiveEmptyResponses = 0;

if (isEmptyResponse(response)) {
  consecutiveEmptyResponses++;
  if (consecutiveEmptyResponses > 3) {
    logger.warn('Infinite loop detected, forcing stop');
    return "stop";
  }
}

Fix 4: Add Timeout Protection

Add configurable timeout for headless mode:

{
  "experimental": {
    "headless_timeout": 300000  // 5 minutes
  }
}

Environment

• OpenCode version: big-pickle (opencode/big-pickle)
• Affected providers: OpenCode Zen (primary issue)
• Also affected: claude-sonnet-4.6 via github-copilot provider (similar symptoms)
• Works fine: gpt-5.3-codex, simple prompts without tool calls
• Process state: Alive, 0-2% CPU, consuming 500-900MB RSS
• Key difference: Zen provider with big-pickle model causes mid-process stopping/looping

Impact

1. Breaks automation: CLI tools that spawn opencode run as subprocess hang forever
2. Wastes API calls: Infinite loop consumes quota/credits
3. Blocks parent sessions: Subagent hangs block parent indefinitely
4. Poor UX: No error message, no indication of what's wrong

References

• Original issue: opencode run hangs after completing tool calls — process never exits #17516
• Related fix attempt: fix(session): stop loop when model returns non-tool finish reason #11152
• Session loop fix: fix(session): stop prompt loop after model completion #18500
• Compaction loop fix: fix(session): stop prompt loop after model completion #19424