Repository navigation
[BUG] Session title generation fails silently since v1.3.3 — effort parameter leaks into small model call #20269
Description
Bug Description
Session title generation has been silently failing since v1.3.3. All new sessions retain their default "New session - <timestamp>" title instead of getting an LLM-generated title.
The root cause: when the user's selected model has a variant that includes an effort parameter (e.g. anthropic/claude-opus-4-6 with variant max), that parameter leaks into the LLM.stream call for the title agent. The title agent resolves to a small model (claude-haiku-4-5-20251001) which does not support the effort parameter, causing a 400 error from the Anthropic API. The error is swallowed by Effect.ignore on the fork, so the failure is completely silent.
Reproduction
- Set your model to
anthropic/claude-opus-4-6with variantmax(or any variant that maps tooutput_config.effort) - Start a new session and send a message
- Observe the session title remains
"New session - <timestamp>"
Evidence from logs
INFO service=llm providerID=anthropic modelID=claude-haiku-4-5-20251001
sessionID=ses_xxx small=true agent=title mode=primary stream
ERROR service=llm
requestBodyValues: {
"model": "claude-haiku-4-5-20251001",
"output_config": { "effort": "high" }, ← should not be here
...
}
responseBody: {
"type": "error",
"error": {
"type": "invalid_request_error",
"message": "This model does not support the effort parameter."
}
}
ERROR service=session.prompt
error=No output generated. Check the stream for errors.
failed to generate title
Impact data (from local DB)
| Version | Sessions with title | Sessions without title | Success rate |
|---|---|---|---|
| 1.3.9 | 0 | 4 | 0% |
| 1.3.5 | 0 | 3 | 0% |
| 1.3.3 | 0 | 6 | 0% |
| 1.3.2 | 29 | 2 | 93.5% |
| 1.3.0 | 40 | 3 | 93.0% |
| 1.2.27 | 42 | 2 | 95.5% |
Title generation drops to 0% success starting from v1.3.3 for users with an effort-bearing variant.
Root cause
In packages/opencode/src/session/prompt.ts, the ensureTitle function passes user: firstInfo to LLM.stream:
const result = await LLM.stream({
agent: ag,
user: firstInfo, // ← carries variant from user's main model
// ...
model: mdl, // ← this is the small model (haiku)
})The user message's variant (e.g. max → effort: high) is applied to the API call even though the resolved model (claude-haiku-4-5) doesn't support it.
Suggested fix
Strip or ignore the user variant when calling the title agent's small model. For example:
- Pass
user: { ...firstInfo, variant: undefined }in the title generation call - Or have
LLM.streamskip unsupported parameters whensmall: true - Or catch the specific error and retry without the variant
Workaround
Override the title agent's model in config to one that isn't affected:
// opencode.json agent config
"title": {
"model": "google/gemini-3-flash"
}Environment
- opencode: v1.3.3 → v1.3.9 (all affected)
- Provider: anthropic (confirmed), likely affects any provider where variant maps to unsupported model params
- OS: macOS (arm64)
Activity
fix: strip variant from title generation to prevent effort parameter …
rekram1-node commentedon Mar 31, 2026
can u share opencode debug config, I cant replicate.
If request is "small" which title gen is, it shouldnt be using the options
anas-asghar4831 commentedon Apr 4, 2026
Reproducing this on the web UI with
claude-opus-4-6+maxvariant. All sessions stuck at "New session - " with no title generation. No errors visible in the web UI — completely silent failure.Environment:
anthropic/claude-opus-4-6maxSwitching variant away from
maxlikely works around it, but the effort parameter leak into the title agent's small model call should be guarded regardless.smrr723 commentedon Apr 9, 2026
Confirming title generation failures, though my data shows a slightly different pattern.
Environment:
gitlab/duo-chat-opus-4-6(GitLab provider, proxies to Anthropic)Impact data (from local DB at
~/.local/share/opencode/opencode.db):Total: 353 with title, 29 without (92.4% overall).
The biggest drop is at v1.4.0 (28.6%). Earlier versions show sporadic failures but not the complete 0% reported by others — likely because my provider (GitLab) may handle the effort parameter differently than direct Anthropic.
skwid138 commentedon Jun 3, 2026
1.15.13:
reasoning_effort: "low"reached a title-generation call and 400'd (GitHub Copilot)On 1.15.13, when my configured
small_model(openai/gpt-5-mini) returnedmodel_not_found, the title call routed to the session model (small=false agent=gandalf,github-copilot/claude-opus-4.7) and carriedreasoning_effort: "low". The API rejected it:The response reported supported values
[medium], solowfails on that path. The error is swallowed (Effect.ignoreinsession/prompt.ts), so the session silently stays "New session" (more on the swallow in #29734).Workaround: set
small_modelto a model available for my account (openai/gpt-5.4-mini), which avoids the session-model path entirely.What I could not confirm: whether the same effort value also reaches the normal small-model path, or only this case where the title call routed to the session model. In mine it was specifically the session-model call (
small=false).Repro:
opencode.jsoncwith session modelgithub-copilot/claude-opus-4.7andsmall_modelset to a model unavailable for your account; start a session and send a prompt; the new session stays "New session" and DEBUG logs show theinvalid_reasoning_effort400. Version 1.15.13.github-actions commentedon Aug 3, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.