ECONNRESET with zai-coding-plan provider (api.z.ai)

[gletushov]

Summary

Requests to Z.AI API (api.z.ai) fail with ECONNRESET after ~40-100 seconds when using the zai-coding-plan provider. The same API works correctly via curl and in other tools (e.g., OpenClaw via VPS proxy).

Environment

• OpenCode: v1.2.15
• Platform: macOS (arm64)
• Provider: zai-coding-plan
• Model: glm-5
• Endpoint: https://api.z.ai/api/coding/paas/v4/chat/completions

Error Details

From ~/Library/Logs/ai.opencode.desktop/opencode-desktop_*.log:

ERROR service=llm providerID=zai-coding-plan modelID=glm-5 sessionID=ses_xxx small=false agent=build mode=primary 
error={"error":{"code":"ECONNRESET","path":"https://api.z.ai/api/coding/paas/v4/chat/completions","errno":0}} stream error

Timing pattern of failures (from logs):

• Most failures occur after 39-100 seconds
• Some as long as 1000+ seconds
• 0 successful requests logged (101 ECONNRESET errors in one session)

Reproduction

1. Configure zai-coding-plan provider with a valid API key via opencode auth login
2. Select glm-5 model
3. Send any prompt
4. After ~40-100 seconds: ECONNRESET error

Verification that API works

Direct curl requests work fine:

curl -X POST "https://api.z.ai/api/coding/paas/v4/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <key>" \
  -d '{"model":"glm-5","messages":[{"role":"user","content":"hi"}],"stream":true}'
# Returns streaming response successfully

Same API also works when routed through a VPS proxy (tested with OpenClaw which proxies through a France VPS).

Analysis

The issue appears to be with Bun's HTTP client in the OpenCode sidecar:

1. Bun's connection pooling: Bun aggressively reuses HTTP connections (keep-alive)
2. Z.AI's idle timeout: Server likely closes idle connections after 30-60 seconds
3. Race condition: When Bun tries to reuse a connection that the server has already closed → ECONNRESET

The sidecar process (opencode-cli serve) makes the actual API calls:

/Applications/OpenCode.app/Contents/MacOS/opencode-cli --print-logs --log-level WARN serve --hostname 127.0.0.1 --port XXXXX

Suggested Fix

1. Disable keep-alive for Z.AI endpoints, or
2. Add retry logic with fresh connection on ECONNRESET, or
3. Reduce connection pool lifetime for streaming endpoints

Workaround Attempts

• Setting HTTPS_PROXY environment variable: doesn't help (sidecar is separate process)
• Bun config (~/.bunfig.toml): OpenCode binary appears to ignore it
• VPN: issue persists regardless of network route

Related

• Z.AI documentation for OpenCode: https://docs.z.ai/integrations/opencode

[github-actions]

This issue might be a duplicate of existing issues. Please check:

• Z.ai coding model connection issue #4349: Z.ai coding model connection issue — same provider (zai-coding-plan), same endpoint, curl works but OpenCode times out/fails
• Z.ai subscription API fails to work in opencode but works in other agents #8515: Z.ai subscription API fails to work in opencode but works in other agents (closed) — same pattern of API working externally but failing within OpenCode