dsh-model-modes
适用于 DeepSeek Harness 网页编辑器的能力感知推理控制和提供商原生快速模式
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:DTSFO/dsh-model-modes#d2637fb7d5d94af262b020c101ed8bc39e387f38Model Modes 以 dsh-model-modes 发布，当前版本为 0.1.3。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
点击下方 Badge 复制 Markdown，粘贴到 README 即可。
验证 package.json 声明的 GitHub 仓库，即可管理这个公开页面。认领后，Hub 会优先安排当前版本的安全扫描，并在通过后公开展示结果。
认领这个 Plugin →Capability-aware reasoning profiles and provider-native Fast mode for the DeepSeek Harness web composer.
reasoningProfiles.provider: '*' to every llm-pi-ai provider that actually contains the exact model id; no myself hardcoding.Max and Ultra as independent choices for gpt-5.6.ModelDirectory; unsupported routes are visibly unavailable and rejected by the Host.Max + Fast and Ultra + Fast are both supported combinations.
Fast is orthogonal to reasoning. It never selects a cheaper reasoning effort, a flash/turbo sibling model, or another DSH provider. Injection happens at the final llm-pi-ai Models.streamSimple() boundary and is isolated per concurrent session with AsyncLocalStorage.
| DSH provider | pi-ai API | Fast wire parameter | Default policy |
|---|---|---|---|
openai | OpenAI Responses / Chat Completions | service_tier: "fast" | Exact official model allowlist |
openai-codex | openai-codex-responses | service_tier: "fast" | Exact Codex allowlist: GPT-5.6 Luna/Sol/Terra, GPT-5.5, and GPT-5.4 |
xai | OpenAI Responses / Chat Completions | service_tier: "priority" | All text models on this exact provider |
google | google-generative-ai | config.serviceTier: "priority" | Exact Gemini Developer API allowlist |
openrouter | OpenAI-compatible text APIs | service_tier: "fast" | All models on this exact provider; upstream may fall back to Standard |
minimax / minimax-cn | anthropic-messages | service_tier: "priority" | Exact MiniMax model allowlist |
vercel-ai-gateway | anthropic-messages | providerOptions.gateway.speed: "fast" plus allowFallbackFromFast: false | Exact live Fast-model intersection; fast-or-fail, with no silent Standard fallback |
fireworks | anthropic-messages / openai-completions | service_tier: "priority" | Exact nine-model allowlist; request-level Priority, not a Fireworks *-fast router/model switch |
azure-openai-responses | azure-openai-responses | service_tier: "priority" | Explicit opt-in only: deployment, API version, SKU, and region are not visible to the matcher |
google-vertex | google-vertex | X-Vertex-AI-LLM-Shared-Request-Type: priority | Explicit opt-in only: Priority PayGo requires a supported model and the global endpoint |
amazon-bedrock | bedrock-converse-stream | serviceTier: { type: "priority" } | Explicit opt-in only: support varies by model card, inference profile, and region |
Nested objects are merged immutably, preserving fields such as Google config.thinkingConfig, Bedrock siblings, existing OpenRouter routing configuration, and Vercel Gateway options such as only, order, and models.
The default OpenAI allowlist follows the current Fast table, including the GPT-5.6 family, supported GPT-5.x/GPT-4.x models, o3, o4-mini, and gpt-5.3-codex. The separate openai-codex route uses its own exact Codex allowlist and API contract. Google defaults only to the current Gemini Developer API text-model intersection and deliberately excludes gemini-3.7-flash; Vertex documents 3.7 separately but remains explicit opt-in. MiniMax defaults to its documented M2/M3 priority models.
Vercel AI Gateway Fast mode is configured as fast-or-fail: allowFallbackFromFast: false prevents an unavailable Fast route from silently becoming Standard. Its defaults are an exact intersection of pi-ai's catalog and Vercel's live Fast metadata; already-fast *-fast model slugs are excluded because choosing one would be a model change.
Fireworks exposes request-level Priority through service_tier: "priority". Fireworks also offers distinct Fast serving paths that require selecting a different router/model, but this plugin never changes the selected model or route. Consequently, the Composer's Fast switch means Provider-native Priority on the documented nine-model Fireworks allowlist, not an implicit switch to a *-fast model.
Capability is evaluated from the live llm-pi-ai route and the selected model's actual pi-ai API id. A matching name on another adapter, a wrong API, a bridge installation failure, or a route without a precise profile is shown as N/A and cannot be enabled.
These entries mean the request contract is known. Account entitlement, regional capacity, deployment support, fallback, and billing remain provider decisions.
The pi-ai 0.82.1 built-in provider set has 38 ids (37 static catalog providers plus the dynamic radius gateway), all classified by this release: nine have default profiles, three deployment-dependent providers are explicit opt-in only, and the remaining 26 are rejected by configuration validation. The rejected built-in ids are ant-ling, anthropic, cerebras, cloudflare-ai-gateway, cloudflare-workers-ai, deepseek, github-copilot, groq, huggingface, kimi-coding, mistral, moonshotai, moonshotai-cn, nvidia, opencode, opencode-go, qwen-token-plan, qwen-token-plan-cn, radius, together, xiaomi, xiaomi-token-plan-ams, xiaomi-token-plan-cn, xiaomi-token-plan-sgp, zai, and zai-coding-cn.
anthropic: native Fast requires speed: "fast" plus a Fast beta header. pi-ai 0.82.1 assembles other Anthropic beta tokens after the plugin header seam, so this version cannot safely preserve every token.mistral: its latency tier uses service_tier: "auto", not OpenAI fast or generic priority; the current serializer boundary is not proven safe for this field.groq: Performance Tier uses service_tier: "performance", with enterprise and model constraints; it is not the OpenAI Fast contract.cerebras: priority uses service_tier: "priority" only on eligible dedicated endpoints and is currently private preview.deepseek: its official API documents service_tier as ignored.These rejected built-in providers cannot be enabled by assigning them a generic OpenAI-style or custom strategy. Unknown or self-hosted providers remain unsupported by default and require an exact verified provider/model/API profile.
Built-in contracts are enabled by default. fastProfiles is an additive/override layer; later exact provider/model/API matchers win.
- id: dsh-model-modes
config:
includeDefaultFastProfiles: true
fastProfiles:
# A verified self-hosted gateway. Provider and API must be exact;
# use model: '*' only if every model on that route has the same contract.
- provider: your-gateway
model: gpt-5.6
api: openai-responses
strategy: openai-fast
# Vertex is explicit because the matcher cannot inspect endpoint location.
- provider: google-vertex
model: gemini-3.7-flash
api: google-vertex
strategy: vertex-priority
Known strategies:
openai-fastopenai-codex-fastservice-tier-priorityfireworks-prioritygoogle-priorityvertex-prioritybedrock-priorityopenrouter-fastvercel-gateway-fastcustomSet includeDefaultFastProfiles: false to use only explicit profiles.
Use custom only for a verified gateway-specific contract:
fastProfiles:
- provider: your-gateway
model: your-model
api: openai-responses
strategy: custom
body:
acceleration:
tier: turbo
headers:
X-Gateway-Fast: "1"
To keep Fast orthogonal, custom patches cannot modify model, provider, reasoning, reasoning_effort, thinking, thinkingConfig, effort, and related fields.
The default profile is:
reasoningProfiles:
- provider: '*'
model: gpt-5.6
efforts:
minimal: minimal
low: low
medium: medium
high: high
xhigh: xhigh
max: max
ultra: ultra
The provider wildcard expands to every llm-pi-ai provider that actually contains the exact gpt-5.6 model id, regardless of whether it is official, local, or user-defined; myself is not special-cased. An exact provider profile wins the same route. Unknown models, providers owned by another adapter, and providers without that model are left untouched.
DSH rc.6 exposes seven native transport effort ids. The plugin leaves every existing persisted native mapping intact, adding only profile-declared native keys that are missing, and appends Ultra to the public selector. Only an explicit Ultra request gets a request-local model clone whose temporary carrier maps to the configured Ultra wire value. Max, Off, Provider Default, and every ordinary request keep the original model and settings.
For the default gpt-5.6 profile:
| Official UI selection | Final provider wire value |
|---|---|
Max | max |
Ultra | ultra |
There is no persistent max -> ultra mapping: Max and Ultra are two independent public efforts and two independent final wire values. Version 0.1.2 also migrates the plugin's older generated max: ultra or off: ultra settings back to native mappings, so uninstalling or disabling the plugin cannot leave ordinary requests sending Ultra.
Existing manual reasoningEfforts remain authoritative for keys they already define. Profiles add only missing declared levels, so a provider-specific wire spelling is preserved while a route can gain an independent Ultra option. An exact provider/model profile may set overrideExisting: true to replace the complete map; wildcard provider profiles cannot, preventing accidental bulk takeover. Adapter-native capabilities remain authoritative unless an explicit model profile is needed.
dsh plugin --profile web add \
https://github.com/DTSFO/dsh-model-modes/archive/refs/tags/v0.1.3.tar.gz
Then run:
dsh web
Development:
pnpm install
pnpm run check
dsh plugin --profile web add /absolute/path/to/dsh-model-modes
0.82.1; unsafe seams fail closed rather than lowering effort or changing route.MIT