[Network connection lost] due to Context overflow at model limit misclassified — no compaction, no retry, session dies!!

[AdityaPagare619]

Description

Hey, spent some time digging into a session crash and traced it to what I think is a gap in the error classification path. Wanted to share findings in case it helps.

What happened

Long-running session (heavy tool-calling, sequential thinking) hit the model's context window limit. The next request exceeded it, provider returned a context-length error. Instead of triggering auto-compaction, OpenCode classified the error as "Network connection lost." (an UnknownError) and killed the session immediately.

The error is not retryable and doesn't trigger compaction — so the session is just dead with no way to recover.

Why it happens

The issue is in fromError() in packages/opencode/src/session/message-v2.ts. There's a catch-all at the end:

case e instanceof Error:
  return new NamedError.Unknown({ message: errorMessage(e) }, { cause: e }).toObject()

When the provider returns a context-length error wrapped in a generic Error (not an APICallError), it hits this case instead of being recognized as a context overflow. The function never reaches ProviderError.parseStreamError() because the error is instanceof Error.

Then in retry.ts, retryable() only handles APIError — so NamedError.Unknown gets no retry, and the processor calls halt().

Repro

1. Long session with a model that has a defined context limit (mine was mimo-v2.5-free @ 1,048,576 tokens)
2. Heavy tool-calling workflow that grows context incrementally
3. Continue until you're right at the limit
4. Send one more message — session dies with "Network connection lost."

Suggested fix

Before the case e instanceof Error: catch-all, detect context overflow patterns:

case e instanceof Error: {
  const msg = errorMessage(e)
  if (/context.*(length|window|limit|exceed)|token.*limit|input.*too.*long|maximum.*context/i.test(msg)) {
    return new ContextOverflowError(
      { message: msg },
      { cause: e },
    ).toObject()
  }
  return new NamedError.Unknown({ message: msg }, { cause: e }).toObject()
}

This way context overflow from any provider gets classified properly and triggers auto-compaction.

Related issues I found while digging

Some of these might be the same root cause showing up differently:

• 502 provider_unavailable errors from OpenRouter are not retried, causing subagent/session aborts #22448 — 502 provider_unavailable errors not retried. Same error classification gap but for a different error type. The numeric code check in retry.ts (typeof json.code === "string") doesn't handle numeric codes from OpenRouter.
• [BUG]: Desktop task execution is unexpectedly interrupted with file watcher Invalid handle and undici terminated errors on Windows #29589 — undici TypeError: terminated on Windows. Also falls through to NamedError.Unknown in fromError(). Same catch-all gap.
• Session token usage grows unbounded via cache.read and causes unrecoverable context-window errors #30649 — cache.read token inflation. Makes this worse because cumulative token counts can make the session think it's already over the limit when the actual context is smaller.
• Network Connection Lost #20060 — "Network Connection Lost" (labeled bug + core). Probably the same thing.
• Request size exceeds model context window #10220 — "Request size exceeds model context window". Same class of issue.

Environment

• OpenCode v1.15.7 (crash), v1.15.11 (retry), v1.17.9 (current — bug still present)
• mimo-v2.5-free via OpenCode Zen (1,048,576 token context)
• Windows 11

Not sure if this is the right place for all of this or if some of these should be separate issues. Happy to split or combine however makes sense for the team.

Plugins

custom framework

OpenCode version

1.17.9

Steps to reproduce

1. Start a long-running session with a model that has a defined context window limit (e.g., mimo-v2.5-free with 1,048,576 token limit)

2. Use a heavy tool-calling workflow — sequential thinking, file operations, web searches — anything that incrementally adds tokens to the context each turn

3. Keep going until the session's total tokens are right at the model's limit. In my case, the session reached 1,048,572 tokens (4 below the 1,048,576 ceiling)

4. Send one more message that would push the total over the limit

5. Expected: OpenCode triggers auto-compaction, reduces context, retries the request

6. Actual: Session dies immediately with error "Network connection lost." — no compaction, no retry, session unrecoverable

The error shows up in the session data as:

{
  "name": "UnknownError",
  "data": {
    "message": "\"Network connection lost.\""
  }
}

This is a context_length_exceeded error from the provider that got misclassified by fromError() in message-v2.ts.

Screenshot and/or share link

No response

Operating System

Windows 11

Terminal

Windows Terminal

[github-actions]

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

• Network Connection Lost #20060: Same symptom — session dies with "Network connection lost" error
• Sub-agents hang indefinitely on context overflow — no compaction triggered #25187: Same root cause — context overflow not triggering compaction, session unrecoverable
• GLM / Vertex overflow errors with INVALID_ARGUMENT are not classified as context overflow #23713: Same root cause — overflow errors misclassified (not recognized as context overflow)
• fix(provider): Z.AI GLM overflow error not classified as context overflow, causing chain compaction #27629: Same root cause — provider overflow errors not classified correctly, no compaction triggered

If your issue is distinct from these, please clarify what makes it different. Otherwise, consider adding a comment to the most relevant existing issue.

[AdityaPagare619]

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

• Network Connection Lost #20060: Same symptom — session dies with "Network connection lost" error
• Sub-agents hang indefinitely on context overflow — no compaction triggered #25187: Same root cause — context overflow not triggering compaction, session unrecoverable
• GLM / Vertex overflow errors with INVALID_ARGUMENT are not classified as context overflow #23713: Same root cause — overflow errors misclassified (not recognized as context overflow)
• fix(provider): Z.AI GLM overflow error not classified as context overflow, causing chain compaction #27629: Same root cause — provider overflow errors not classified correctly, no compaction triggered

If your issue is distinct from these, please clarify what makes it different. Otherwise, consider adding a comment to the most relevant existing issue.

The issue is completely different bec it talks about the network problems spawning due to flaw in logic of code and also miss bug discusses about the miss alignment between model and open code itself so its more about these not just the networks failure or timeouts only!