菜单
External prompt-provider abstraction (Langfuse today). Use when fetching prompts at runtime, adding a new prompt provider, or wiring agent config from a managed prompt.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
| name | echo-sdk-prompts |
| description | External prompt-provider abstraction (Langfuse today). Use when fetching prompts at runtime, adding a new prompt provider, or wiring agent config from a managed prompt. |
BasePromptProvider in prompts/base.py — abstract; declares fetch(name, label=..., version=..., variables=...) -> FetchedPrompt.LangfuseProvider in prompts/langfuse_provider.py — concrete implementation.get_prompt_provider() in prompts/factory.py — singleton factory with reset.FetchedPrompt — has compiled prompt string + ready-to-use AgentConfig.prompts/templates/ — load_template(name) used internally (e.g., skill_mechanism).get_prompt_provider() returns the configured singleton; use reset() only in tests.FetchedPrompt.agent_config is pre-compiled — pass it straight into GenericAgent(agent_config=...). Don't rebuild it.variables= dict at fetch time.langfuse is an extra (echo[langfuse]). Guard imports with try/except ImportError.label (e.g., "production") over pinning to a version for deploys; pin versions for evals.→ Use [[echo-sdk-adding-a-provider]]. Implement BasePromptProvider, register in factory.py, add optional-deps extra.
FetchedPrompt → it's frozen-by-convention; treat as immutable.langfuse at module top → optional dep, guard it.[[echo-sdk-agents]] for how AgentConfig is consumed.[[python-optional-deps]]Router for any non-trivial echo-sdk task. Maps user intent to the right module skill and diagram. Invoke FIRST for any change to src/echo/ before reaching for a specific module skill.
Recipe for adding a new provider (LLM, transcriber, eval, prompt). Use whenever adding Cohere, Mistral, Deepgram, Phoenix, Promptlayer, etc. — anything that plugs into an existing get_*() factory.
End-to-end recipe for defining a Skill bundle and wiring it into a GenericAgent with the right activation mode and tool registry. Use when extending agent capability via swappable skills rather than baking tools in.
Building agents with BaseAgent / GenericAgent, including skill registration, activation modes (llm vs manual), and system-prompt composition. Use when editing src/echo/agents/ or building a new agent subclass.
Audio transcription provider abstraction (Gemini, EkaCare). Use when transcribing audio, adding a new transcriber, or shaping AudioInput.
Postgres support — asyncpg client, schema-aware binder, PgQueryTool surface. Use when querying postgres from a tool, modifying the binder, or adding a new DB engine.