feat: serve Executions over A2A with a pre-approved /generate

Increment 7 of .scratch/solution-architect-agent/spec.md.

- app/assembly.py: composition root building the engine from settings
  and the provider bundle (roles, ADK runtime, MCP catalog, Terraform
  tools, checkpointer, recorder).
- app/a2a: a2a-sdk 1.1 JSON-RPC server (v0.3 compatible) mapping tasks to
  Executions; questions, Approvals and permissions pause as
  input-required; Approvals accepted only as structured data; completed
  tasks return the guide and code as artifacts; agent card derived from
  the dependency graph.
- POST /generate runs a pre-approved Execution with the legacy keys.
- Specialist exceptions are relayed to the user; Orchestrator exceptions
  fail the task. Engine accepts a caller-chosen execution id.
- Dockerfile installs checksum-verified Terraform and ships agents,
  providers and skills; add mcp and a2a-sdk requirements.
- 17 new tests; full suite 206 passed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-09-16 10:23:24 +01:00
parent ed104e5697
commit ad371b2ec4
19 changed files with 1116 additions and 3 deletions

View File

@@ -51,6 +51,7 @@ class Settings(BaseSettings):
# Cloud Provider Bundle (providers/<name>.yaml) & Remote MCP Servers
CLOUD_PROVIDER: str = "gcp"
MCP_ENABLED: bool = True
MCP_ENABLE_PREVIEW: bool = True
MCP_QUOTA_PROJECT: str | None = None # defaults to the ADC project
MCP_TIMEOUT_SECONDS: float = 30
@@ -61,6 +62,9 @@ class Settings(BaseSettings):
TF_PLUGIN_CACHE_DIR: str | None = None
# Hierarchical Execution Engine (LangGraph state, ReAct agents)
A2A_HOST: str = "0.0.0.0"
A2A_PORT: int = 8000
A2A_PUBLIC_URL: str | None = None # advertised in the agent card
ORCHESTRATOR_BUDGET: int = 40
SPECIALIST_BUDGET: int = 15
MAX_REVISIONS: int = 3