LLM-Anbieteradapter

Bietet einen einheitlichen Anwendungsvertrag für LLM-APIs und bewahrt notwendige Anbieterdetails für Wiederholung und Abrechnung.

llm-provider-adapters

Teammitglieder mit diesem Skill

AgentSelene

Entdecke, wie der Skill hilft

Wann ist der Skill hilfreich?

Nutze ihn beim Ergänzen eines Modellanbieters oder CLI-Backends ohne verteilte Herstellerspezifika in der Laufzeit.

Wobei hilft er dir?

Vereinheitlicht Inhaltsblöcke, Werkzeuge, Stoppgründe und Tokenverbrauch.
Bewahrt anbieterspezifische Denksignaturen und Streaming-Semantik.
Klassifiziert wiederholbare Fehler und beendet eingebundene CLI-Prozesse.

Das könntest du fragen

Ergänze einen Anbieter ohne verlorene Werkzeugergebnisse oder falschen Abschluss bei Tokenlimits. Spiele Werkzeugaufruf, Teilstream und Tokenlimit durch beide Adapter. Erhalte gleichwertige Nachrichtenidentität und kennzeichne unvollständige Ausgabe klar.

Ausführliche Dokumentation

Hier findest du die ursprüngliche Anleitung, Beispiele und Prüfschritte des Skills in ihrer Originalsprache.

Details…Weniger anzeigen

LLM Provider Adapters & Fallbacks

Isolate provider-specific wire formats, SDK quirks, and CLI flags behind a narrow, canonical internal interface so application workflows never depend on a single vendor's message schema or streaming protocol.

Canonical Internal Domain Model

Define a provider-neutral contract at the boundary of your LLM gateway:

Canonical Message & Content Blocks: Represent turns as ordered blocks (text, thinking / reasoning with opaque cryptographic signature preserved for multi-turn replay, tool_use, tool_result, and image / document attachments).
Canonical Tool Definition: JSON Schema inputSchema, description, and behavioral hints (strict, defer_loading, cache_control) translated by each provider adapter into its native format.
Canonical Stop Reasons: Normalize provider stop reasons (end_turn/stop, tool_use/tool_calls, max_tokens/length, content_filter/safety, pause_turn) so the runtime state machine handles every model uniformly.
Canonical Usage Ledger: Always normalize inputTokens, outputTokens, cacheReadInputTokens, cacheCreationInputTokens, and reasoningTokens into a single TokenUsage struct on every turn.

Provider-Specific Translation Pitfalls

Guard against subtle cross-provider incompatibilities inside the adapter layer:

Area	Anthropic Claude	OpenAI Responses / Chat	Google Gemini	Adapter Requirement
System Prompt	Top-level `system` array of blocks with `cache_control`	`developer` / `system` role items or `instructions`	`systemInstruction` content object	Keep system instructions separate from the `messages` array in the canonical request; let the adapter place them.
Tool Results	`user` message containing `tool_result` content blocks ordered before text	Dedicated `function_call_output` / `tool` role items per `call_id`	`functionResponse` parts grouped in a `user`/`function` turn	Enforce strict 1-to-1 pairing between `tool_use.id` and `tool_result.tool_use_id`; coalesce adjacent tool results when a provider requires a single turn.
Thinking / Reasoning Blocks	`thinking` & `redacted_thinking` blocks with `signature` must be echoed unmodified during tool loops	`reasoning` items with encrypted content or summary	`thought: true` parts with `thoughtSignature`	Store reasoning blocks verbatim in turn history; if switching providers mid-run, strip vendor-specific signatures and keep only plain-text summaries if permitted.
Strict JSON Schemas	Requires explicit `"additionalProperties": false` on objects	Strict mode requires all properties in `required` (use nullable types for optional fields)	Subset of OpenAPI/JSON Schema keywords supported	Run a schema normalizer per provider before sending tool or structured-output definitions.

Resilient Retries, Circuit Breakers & Model Fallbacks

Classify errors before retrying:
- Retryable transient: HTTP 408, 429 (respect Retry-After / x-ratelimit-reset-* headers), 500, 502, 503, 529 (overloaded), or mid-stream socket reset before irreversible side effects. Use exponential backoff with full jitter.
- Context window overflow (400 context_length_exceeded): Do not blind-retry or switch to a smaller model. Trigger emergency context compaction or tool-output truncation and retry once.
- Non-retryable client error (400 invalid_request, 401, 403): Fail immediately with a structured diagnostic error; inspect schema translation bugs.
Safe cross-model fallback:
- Maintain an ordered fallback chain (primaryModel $\rightarrow$ fallbackModels) with capability tags (supportsTools, supportsVision, supportsStructuredOutput, maxContextTokens).
- Only fall back to a model that satisfies all capabilities required by the current turn (e.g., never fall back to a model without tool support during an active tool loop).
- When switching providers mid-conversation, re-serialize the canonical transcript through the target provider's adapter so vendor-specific blocks (thinking signatures, cache markers, tool ID formats matching ^[a-zA-Z0-9_-]+$) are sanitized cleanly.
CLI Agent Wrappers: When wrapping headless CLI agents (e.g., Claude Code, Codex CLI, Gemini CLI), communicate via structured JSONL streams (--output-format stream-json), enforce process-group cleanup (kill(-pid)), isolate working directories, and parse exit codes and stderr into the same canonical AgentRunResult.

Enthaltene Dateien 1

SKILL.md