Executor plugins

Executors own the provider-specific LLM harness: tool loops, hook injection, session persistence, and telemetry normalisation. The runner orchestrates which executor to call; it never imports Anthropic/OpenAI SDK code directly.

Core interface (PhaseExecutorRuntime)

Method	Notes
executePhase(req)	Returns an async iterable of PhaseExecutorEvent chunks (assistant deltas, tool proposals, usage metrics)
listModels()	Emits ExecutorModelDescriptor rows for dashboards + alias validation
supports(modelId)	Guards unknown models before network I/O

Optional:

• calculateCost — Tenant-specific pricing adjustments.
• mcpServer() — Attach executor-local MCP (uncommon).
• chat(req) — Stateless conversational completion for surfaces that do not need tools, MCP, hooks, or subprocess agents (Coro plan mode on POST /intake/stream). Implementations should call the provider HTTP API directly. Request carries messages, optional systemPrompt, model, maxOutputTokens, and signal; result returns concatenated output plus normalised usage.

PhaseExecutionRequest highlights

Carries HookPolicy (allowedTools, writeRoots, onPreToolUse), resume handles, combined MCP server list, workflow-scoped subagents, and working-directory metadata.

Capability bits (ExecutorCapabilities)

Flag	Runner effect
supportsNativeSubagents	Lets YAML subagents use the executor’s native Task tooling; otherwise Coro registers run_subagent.
supportsClaudeMdNativeWalkUp	When true, executor loads .claude/CLAUDE.md hierarchies itself.
supportsNativeFileTools	Suppresses fallback file_* + shell tools if the SDK already exposes them.
supportsSessionResume	Claude-style sessionId persistence.
supportsConversationReplay	Stateless models replay conversationHistory.
supportsThinking	Surfaces reasoningEffort hints from llm.aliases.
supportsImageInput	Enables multimodal blocks.
maxContextTokens	Hard ceiling enforced before calling upstream APIs.

Exactly one resume strategy should be true for a given plugin build.

Reference packages

Package	Role
@coro-ai/llm-anthropic	Wraps @anthropic-ai/claude-agent-sdk — native Tasks + CLAUDE.md walk-up.
@coro-ai/llm-openai	OpenAI Responses / chat-completions style loop with conversation replay.

Executors must remain workflow-agnostic: no references to campaign, lane, or business guardrails beyond what the runner already encodes in hooks.