Use when adding or updating Spark AI provider models or their compact and preflight metrics, especially baidu-oneapi, Grok, Claude, GPT, DeepSeek, OneAPI, context windows, output budgets, prices, thinking maps, or transports.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Owner: packages/spark-llm-providers. Catalog, gateway rewrites, and measured windows live
in baidu-oneapi.ts. Do not guess vendor ids, context, or prices.
contextWindow.packages/spark-llm-providers/README.md.grok-4.6, not grok-4-6).contextWindow is the prompt+output ceiling Spark compact/preflight uses.
On Baidu, measured provider input beats advertised vendor context.maxTokens is Spark's output budget, not always the vendor max. If the
vendor lists no output cap, keep the same-family budget unless measurement
says otherwise.cost is USD per million tokens:
{ input, output, cacheRead, cacheWrite }. Use headline rates (Baidu/Spark
do not model xAI ≥200k 2× long-context pricing). If the vendor has no
cache-write fee, set cacheWrite to the input rate like existing Grok rows.thinkingLevelMap only remaps Spark levels that differ from the transport.
Confirm whether xhigh is real, aliased to high, or invalid.anthropic-messages. GPT-5.6 and Grok →
openai-responses (BAIDU_ONEAPI_OPENAI_RESPONSES_MODEL_IDS).claude-opus-5 → Opus 5). GPT/Grok
are currently 1:1.GATEWAY_MODEL_BY_ID plus the models[] row.enabledModels is the current
frontier only: when a successor ships (grok-4.5 → grok-4.6), replace the
old id in DEFAULT_SPARK_ENABLED_MODEL_PATTERNS with the new one. Do not leave
both enabled, and do not use baidu-oneapi/*.baidu-oneapi/*) as a legacy set
that migrates onto the new list. A user's custom scope, such as
baidu-oneapi/* alone, must not be rewritten.enabledModelIds, old
id out. Do not freeze the whole catalog as the scope contract.Changing only windows or prices still needs tests and README notes. Do not advertise a round number (1M, 256k) when the gateway hard-fails earlier.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when Spark engineering knowledge must be placed, deduplicated, migrated, or validated across AGENTS, Notes, Roles, Skills, and Workflows.
The English summary is being prepared. Showing the original description.
Use when a Spark change needs its authoritative owner, affected boundaries, risks, acceptance criteria, and smallest verifiable slice established before implementation or review.
The English summary is being prepared. Showing the original description.
Use when a Spark implementation needs an evidence-based review for correctness, ownership, compatibility, failure handling, maintainability, and unnecessary complexity.
The English summary is being prepared. Showing the original description.
Use when designing a Spark feature or writing or materially revising a design proposal that needs repository-first research, user input on unresolved key choices, and an owner-aligned implementation plan before code changes.
The English summary is being prepared. Showing the original description.
Use when a working Spark implementation should be simplified without changing its observed behavior, ownership, compatibility, or public contract.
The English summary is being prepared. Showing the original description.
Use when a running Spark or DSH web service needs real-browser verification — page load, client-plugin boot errors, console errors, failed requests, or onboarding/dialog rendering — with the repository's own Playwright chromium.
The English summary is being prepared. Showing the original description.