Directories
¶
| Path | Synopsis |
|---|---|
|
Package agent wraps the Google ADK runner with sensible defaults (streaming mode, in-memory session service, app name) so consumers hit the same shape regardless of whether they're driving the agent from a one-shot CLI, a REPL, or an HTTP handler.
|
Package agent wraps the Google ADK runner with sensible defaults (streaming mode, in-memory session service, app name) so consumers hit the same shape regardless of whether they're driving the agent from a one-shot CLI, a REPL, or an HTTP handler. |
|
Package agentenv parses the optional .agents/env.yaml (or .env.json) manifest and produces a Resolver that agent-bundle loaders can use to interpolate ${env:VAR} references in AGENTS.md, skill files, and mcp.json values.
|
Package agentenv parses the optional .agents/env.yaml (or .env.json) manifest and produces a Resolver that agent-bundle loaders can use to interpolate ${env:VAR} references in AGENTS.md, skill files, and mcp.json values. |
|
Package attach implements live-tail + inject over HTTP/SSE for headless core-agent deployments.
|
Package attach implements live-tail + inject over HTTP/SSE for headless core-agent deployments. |
|
Package auth defines the per-caller identity primitive used by the multi-session attach layer.
|
Package auth defines the per-caller identity primitive used by the multi-session attach layer. |
|
Package config defines the on-disk schema for `.agents/config.json` and the rules for discovering, parsing, and merging it with built-in defaults.
|
Package config defines the on-disk schema for `.agents/config.json` and the rules for discovering, parsing, and merging it with built-in defaults. |
|
Package digest consolidates the digesting primitives core-agent uses to keep large tool responses out of the parent context.
|
Package digest consolidates the digesting primitives core-agent uses to keep large tool responses out of the parent context. |
|
Package eventlog is the durable, append-only audit log that backs agent.Agent's session.Service.
|
Package eventlog is the durable, append-only audit log that backs agent.Agent's session.Service. |
|
Package hooks dispatches shell commands on agent-side event boundaries.
|
Package hooks dispatches shell commands on agent-side event boundaries. |
|
Package instruction loads project + user "agent memory" files (typically AGENTS.md) into the system prompt.
|
Package instruction loads project + user "agent memory" files (typically AGENTS.md) into the system prompt. |
|
Package mcp wires user-configured Model Context Protocol servers into the agent loop.
|
Package mcp wires user-configured Model Context Protocol servers into the agent loop. |
|
Package models is the adapter layer between core-agent's configuration and concrete LLM backends.
|
Package models is the adapter layer between core-agent's configuration and concrete LLM backends. |
|
anthropic
Package anthropic implements models.Provider for Anthropic / Claude.
|
Package anthropic implements models.Provider for Anthropic / Claude. |
|
gemini
Package gemini implements models.Provider for the Gemini family, covering both the public Gemini API (API-key auth) and Vertex AI (Application Default Credentials + GCP project).
|
Package gemini implements models.Provider for the Gemini family, covering both the public Gemini API (API-key auth) and Vertex AI (Application Default Credentials + GCP project). |
|
mock
Package mock ships two credential-free LLM providers and a recording wrapper that pair for offline testing of agent flows:
|
Package mock ships two credential-free LLM providers and a recording wrapper that pair for offline testing of agent flows: |
|
Package modeltier classifies LLM model IDs into capability tiers (frontier / mid / small) used to tune behavior whose right setting depends on how powerfully the model reasons.
|
Package modeltier classifies LLM model IDs into capability tiers (frontier / mid / small) used to tune behavior whose right setting depends on how powerfully the model reasons. |
|
Package permissions implements the central permission gate that decides whether each tool invocation may proceed.
|
Package permissions implements the central permission gate that decides whether each tool invocation may proceed. |
|
Package recording wraps an adkmodel.LLM with a JSONL transcript recorder for offline observability and scripted-replay testing.
|
Package recording wraps an adkmodel.LLM with a JSONL transcript recorder for offline observability and scripted-replay testing. |
|
Package runner drives the agent through a real conversation — either a single one-shot prompt (Headless) or a multi-turn stdin REPL (REPL).
|
Package runner drives the agent through a real conversation — either a single one-shot prompt (Headless) or a multi-turn stdin REPL (REPL). |
|
Package session writes session transcripts to disk on exit.
|
Package session writes session transcripts to disk on exit. |
|
Package skills loads SKILL.md bundles from .agents/skills/<name>/ and exposes them as an ADK Toolset the agent can invoke.
|
Package skills loads SKILL.md bundles from .agents/skills/<name>/ and exposes them as an ADK Toolset the agent can invoke. |
|
Package telemetry initializes OpenTelemetry for the agent loop.
|
Package telemetry initializes OpenTelemetry for the agent loop. |
|
Package tools provides ADK-side helpers for wiring tools into the agent.
|
Package tools provides ADK-side helpers for wiring tools into the agent. |
|
Package usage tracks token + cost accounting for the agent loop.
|
Package usage tracks token + cost accounting for the agent loop. |
Click to show internal directories.
Click to hide internal directories.