Models and keys

Three request kinds route to providers independently, configured in ~/.cues/OPENCUES.md. Failures are written into the line, with their cause; that is their only surface.

Missing keys

The three buckets

ScalarCovers
cues-llm-providerword and sentence suggestions
auditors-llm-providerbackground prose rewrites, including agent tasks
blanks-llm-providereverything requested with _

Each has a matching -model scalar. Splitting them lets the constant background work run on a fast, cheap model while requests you make directly go to a stronger one. A single global llm-provider covers any bucket left unset.

opencues doctor shows the effective routing

cues: cerebras · gemma-4-31b (<- llm-provider) auditors: cerebras · gemma-4-31b (<- llm-provider) blanks: cerebras · gemma-4-31b

One line per bucket: the provider and model that will actually serve it, and, in the marker, which setting decided that. Precedence is bucket scalar over global scalar over automatic selection from available keys.

A missing key

The failure is written into the line.

the capital of japan is [OpenCues: no API key for the selected provider — set its key in ~/.cues/.env or your shell env, or change llm-provider: in ~/.cues/OPENCUES.md]

Whether no key is set at all or only the selected provider's key is missing, no model source can serve the _, and the failure is substituted into the line, selected, so cycling back restores the bare blank. The failure is also logged with the provider's own message (provider error: Invalid API Key for a rejected key). A key that is set but rejected behaves like the classified failures below.

Provider failures

Classified from the response; each class writes its own message into the line.

A classified, fixable failure is substituted into the line at the _ as a bracketed message naming the fix. The classes: rejected key (401/403), endpoint 404, a model the provider does not serve, out of credits, rate limit (429), network failure, bad request (400). Two of the messages, as shipped:

[OpenCues: API key rejected (401/403) — re-export the provider's API key in your shell env (or ~/.cues/.env)] [OpenCues: provider rate-limit hit (429) — wait a moment or switch `llm-provider:` in OPENCUES.md]

The message stays until you edit or cycle it away. Unclassified failures (a provider's own 5xx, malformed output) stay silent and retry on the next change, so a fixable failure names itself and a transient one never litters your text. A local Ollama gets its own messages: a missing model names the ollama pull command, an unreachable server names ollama serve.

Reasoning effort

max-thinking: on | off, default on.

on lets reasoning models use their configured effort ceiling. off reduces effort: answers are faster and cheaper, some are worse. The setting only lowers effort below the ceiling, never raises it, and models without a reasoning-effort parameter ignore it.

Routing through a Claude subscription

Provider value claude-code-cli.

With the claude CLI installed and signed in, a bucket set to claude-code-cli routes through an existing Claude Pro or Max subscription instead of an ANTHROPIC_API_KEY. Because routing is per bucket, word suggestions can stay on a faster provider while rewrites use the subscription.