data/Halcyon Shared Drive/  ->  Indexing API  ->  Search API  ->  Chat API  ->  {answer, sources, diagnostics}

poetry config virtualenvs.in-project true   # keeps the venv at ./.venv
poetry install
cp .env.example .env      # then fill in the tokens

poetry run python -m glean_chat_bot     # the MCP server, on stdio
poetry run glean-index --dry-run        # extract and report, send nothing
poetry run glean-index                  # extract and bulk-push
poetry run glean-index --process-now    # ask Glean to process immediately (1 per 3h)
poetry run pytest                       # contract tests: no network, no tokens
poetry run pytest -m live               # the eval set, against real Glean

{
  "mcpServers": {
    "glean-company-docs": {
      "command": "/absolute/path/to/glean-chat-bot/.venv/bin/python",
      "args": ["-m", "glean_chat_bot"],
      "env": {
        "GLEAN_INSTANCE": "support-lab",
        "GLEAN_CLIENT_TOKEN": "...",
        "GLEAN_ACT_AS": "you@example.com",
        "GLEAN_DATASOURCE": "interviewds3"
      }
    }
  }
}

glean_chat_bot/
  __main__.py      `python -m glean_chat_bot`, the MCP server: one tool over query.ask.ask()
  client.py        indexing and query client factories, the ActAs header
  extraction.py    one adapter per file type, path signals, walk
  indexing.py      the whole write path, behind the `glean-index` command
  models.py        Passage, Source, Answer, ExtractedDoc (pydantic)
  query/           search.py (search -> Passage, the relevance floor)
                   chat.py (chat -> answer + resolved citations)
                   ask.py (ask() — the single orchestration function)
  utils/           config.py (env loading, one Settings, two constructors)
                   logging.py (log format, timing wrapper on every Glean call)
data/              the corpus
docs/              extraction notes
tests/             test_contract.py (the invariants, offline)
                   eval_cases.py + test_eval_live.py (the eval set, `-m live`)