Chat & Completions

Client correlation id; echoed back as x-codai-trace-id and persisted on the usage row.

Groups requests of one conversation for receipts, stickiness and prompt caching.

Test-time-compute effort tier. Wins over the reasoning_effort body field. max is a codai extension above OpenAI's high; none is accepted as an alias of minimal.

1/true enables extended thinking on models that support it (budget from x-codai-thinking-budget, default 16384 tokens).

Positive integer thinking-token budget used when x-codai-thinking is on. Also marks the request as caller-tuned so the effort planner does not override it.

1 keeps the full thinking budget on tool-continuation turns instead of the dampened budget the gateway applies by default.

0/false disables prompt caching for a DIRECT model id. Ignored (caching forced ON) for the codai / codai-* router aliases.

1/true opts this request out of task counting. Only valid on utility aliases; on codai the request is rejected with 400.

Client-chosen task correlation id. Requests sharing it are attributed to one task; echoed back as the x-codai-task-id response header when known within 150 ms.

pass or fail — self-reported outcome that closes the attached task. Honoured only for desktop/CLI surfaces (x-codai-client) and only together with a machine x-codai-task-evidence.

Evidence kind backing x-codai-task-outcome; only exec_verdict and reexec close a task.

Explicit client surface tag used for task attribution (desktop/<ver>, phone-android/<ver>, codai-cli/<ver>, hub/<ver>). Anything else is classified as proxy.

1 makes the turn fully stateless: no memory read, nothing persisted, no sticky routing.

1 skips reading prior memory but still persists this turn.

1 restricts memory recall to entries promoted to proven.

1 rotates to a fresh server-minted session namespace for this request, ignoring x-codai-session-id.

Repository scope hint (e.g. owner/name) used to select the session playbook; most IDE proxies cannot send it, so the gateway also infers scope from the transcript.

Caller-supplied agent identifier persisted with the usage event for per-agent analytics.

1 forbids delegate_to_model sub-agent fan-out and forces the native streaming path.

agent requests agent mode (server-side agent prompt + server tools). 403 when the key/plan is not entitled.

1/true enables gateway-side tools without full agent mode (agent mode implies it).

1/true opts into multi-model orchestration (fan-out to sub-tasks). Requires at least two models in the key allowlist.

verify opts into the FrugalGPT cascade (cheap draft, frontier verify). Result reported in x-codai-cascade-status.

Best-of-N sampling count (e.g. 3); 0/off explicitly disables the automatic best-of. Result in x-codai-best-of-status.

Judge depth for best-of-N.

Opt-in/out of the self-verification reflect pass (1/0). Result in x-codai-reflect-status.

Opt-in/out of step-level process verification (1/0). Result in x-codai-step-verify-status.

Opt-in/out of the long-horizon plan check (1/0). Result in x-codai-plan-status.

1 runs iterative consensus across all tiers (non-stream, router alias only). Result in x-codai-consensus-status.

Opt-in server-side transcript compaction (1). Savings reported in x-codai-compacted / x-codai-compact-saved-chars.

1/on enables relevance retrieval over the transcript before dispatch (x-codai-retrieval-reduced).

Opt-in/out of the learned-heuristics prompt injection (1/0).

Identity-preamble mode override (on / off / shadow).

Per-request playbook mode override; x-codai-no-playbook: 1 is the hard kill-switch.

1 disables session playbook injection for this request.

1 adds the full router decision trace as extra x-codai-router-* response headers.

Client correlation id; echoed back as x-codai-trace-id and persisted on the usage row.

Groups requests of one conversation for receipts, stickiness and prompt caching.

Anthropic-style API key header. Alternative to Authorization: Bearer; ignored when a Bearer header is present.

Test-time-compute effort tier. Wins over the body reasoning_effort. none is normalised to minimal; unknown values are ignored.

Enable extended thinking upstream (1 or true). Default budget 16384 tokens.

Thinking budget in tokens (positive integer). On adaptive-thinking models it is mapped to an effort level. Setting it also tells the compute allocator not to inject its own budget.

Prompt-caching opt-out (0 / false). Only honoured on direct model calls — caching is forced ON for the codai router alias.

Force (1) or suppress (0) server-side conversation compaction for this request.

1 disables sub-agent delegation for this request. Combined with stream: true and no tools this unlocks the native pass-through streaming path on sub-agent-capable tiers.

1 opts out of task counting. Only honoured for eligible utility aliases; on a full model the request is rejected with 400.

Best-of-N sampling on the buffered path (tier-gated; ignored when not entitled).

Sub-agent depth at which best-of applies on the buffered path.

Free-form client identifier recorded on the task opened for this turn.

Client correlation id; echoed back as x-codai-trace-id and persisted on the usage row.

Groups requests of one conversation for receipts, stickiness and prompt caching.

Effort tier; when present it wins and reasoning.effort from the body is not mapped.

0/false disables prompt caching for a direct model id (ignored for the codai alias). Forwarded to the inner chat-completions call.

Forwarded to the inner call; only valid on utility aliases (400 on codai).

Forwarded to the inner call — stateless turn, nothing persisted.

Forwarded to the inner call — client surface tag for task attribution.