Plugs the orchestrator into Adam's existing memory store at
~/.claude/projects/-Users-adammoussa-Documents-repositories/memory/. Every
run starts with a top-3 retrieval pass that is then surfaced in the CLI
output and injected as system context into the router and downstream agent.
- retriever.py: load *.md memories (skipping the MEMORY.md index), embed
with text-embedding-3-small, cache to .cache/embeddings.json keyed on
file mtime. Cosine similarity, top-k=3 default. Reads only — never
writes back to the memory store.
- state.py: add `retrieved: list[dict]` to OrchestratorState; relax to
total=False to match LangGraph's partial-update semantics.
- graph.py: new retriever_node wired as START -> retriever -> router.
router_node and connector_node now inject retrieved memories into their
SystemMessage. Retrieval failures are caught and the run continues with
empty memory context (logged).
- agents.py: make_agent_node injects retrieved memories into each agent's
system prompt.
- run.py: prints `[retrieved: name1, name2, name3]` (or `[retrieved: none]`)
before route/result for both --route-only and full-run modes, so bad
retrieval is visible at a glance.
- .gitignore: add .cache/, .pytest_cache/, .ruff_cache/.
Validated: golden-set still 21/21 passing; smoke tests retrieve plausible
memories ("Send a Slack message to ops about the new exec-aide deploy" ->
project_exec_aide, feedback_exec_aide_vip_management, project_seahaven_slack_bot).
22 lines
551 B
Python
22 lines
551 B
Python
from typing import Annotated, Literal
|
|
from typing_extensions import TypedDict
|
|
from langgraph.graph.message import add_messages
|
|
from langchain_core.messages import AnyMessage
|
|
|
|
|
|
class OrchestratorState(TypedDict, total=False):
|
|
messages: Annotated[list[AnyMessage], add_messages]
|
|
task: str
|
|
route: Literal[
|
|
"implementer",
|
|
"reviewer",
|
|
"researcher",
|
|
"cross_reviewer",
|
|
"scanner",
|
|
"fast_coder",
|
|
"connector",
|
|
"done",
|
|
"unknown",
|
|
]
|
|
result: str
|
|
retrieved: list[dict]
|