nisse/nisse-review/src/nisse_review/build.py

"""Composition root: how nisse-review fits together, and the checks it makes
before it reviews anything."""

from dataclasses import dataclass
from pathlib import Path

from nisse_core.gitea import GiteaClient
from nisse_core.knowledge.handlers import Knowledge
from nisse_core.knowledge.memory import Memory
from nisse_core.knowledge.vault import Vault
from nisse_core.loop.driver import Driver
from nisse_core.loop.expert import ExpertDesk
from nisse_core.models.catalog import ModelCatalog
from nisse_core.models.context import BudgetedClient
from nisse_core.models.llm import LiteLLMClient
from nisse_core.oplog import OpLog
from nisse_core.state.cancel import Cancel
from nisse_review.access import AccessRefused, check, reviewed
from nisse_review.config import ReviewConfig
from nisse_review.review import Reviewer
from nisse_review.scheduler import Scheduler
from nisse_review.state import StateStore

AGENT = "nisse-review"
MEMORY_FOLDER = "memory/nisse-review"  # L10: its own, in the vault


class StartupError(RuntimeError):
    pass


@dataclass
class Built:
    scheduler: Scheduler
    account: str
    repositories: list[str]
    store: StateStore
    gitea: GiteaClient

    def close(self) -> None:
        self.gitea.close()
        self.store.close()


def check_access(
    gitea: GiteaClient, patterns: frozenset[str] | None, oplog: OpLog
) -> tuple[str, list[str]]:
    """Who it is and what it reviews (R1, R3): read only. An account that
    can push to, or administer, a repository it reviews is refused: its hard
    wall is that it can't change what it reviews. The scheduler checks again
    every round (``access``)."""
    account = gitea.whoami()
    try:
        repos = check(gitea, reviewed(gitea, patterns, oplog), oplog)
    except AccessRefused as exc:
        raise StartupError(str(exc)) from exc
    return account, repos


def llm_client(config: ReviewConfig) -> BudgetedClient:
    """The one route to the models, every request fitted to its window
    (L6), against what LiteLLM says the configured models are (L9)."""
    catalog = ModelCatalog.discover(config.llm_base_url, config.llm_token)
    pinned = config.roles.pinned()
    del pinned["classifier"]  # not one of nisse-review's roles
    catalog.validate(pinned)
    catalog.require_limits(pinned)

    def limits_for(model: str) -> tuple[int, int | None]:
        facts = catalog.facts(model)
        assert facts.max_input_tokens is not None  # require_limits checked
        return facts.max_input_tokens, facts.max_output_tokens

    tuning = config.tuning.context
    return BudgetedClient(
        LiteLLMClient(
            config.llm_base_url,
            config.llm_token,
            max_tokens=config.max_output_tokens,
            timeout_s=config.request_timeout_s,
        ),
        limits_for,
        max_output_tokens=config.max_output_tokens,
        keep_recent_turns=tuning.keep_recent_turns,
        safety_margin=tuning.safety_margin,
        enforces_tool_choice=lambda m: catalog.facts(m).supports_tool_choice is True,
    )


def build(
    config: ReviewConfig,
    *,
    gitea: GiteaClient | None = None,
    client: object | None = None,
    oplog: OpLog | None = None,
) -> Built:
    oplog = oplog or OpLog(AGENT)
    gitea = gitea or GiteaClient(config.gitea_url, config.gitea_token)
    account, repos = check_access(gitea, config.repositories, oplog)
    client = client if client is not None else llm_client(config)
    config.state_db.parent.mkdir(parents=True, exist_ok=True)
    store = StateStore(config.state_db, oplog=oplog)
    vault = (
        Vault(
            config.vault.root,
            config.vault.folders,
            agent=AGENT,
            ignore=config.vault.ignore,
        )
        if config.vault
        else None
    )
    memory = (
        Memory(vault, MEMORY_FOLDER)
        if vault and config.vault and config.vault.folders.get(MEMORY_FOLDER) == "rw"
        else None
    )
    tuning = config.tuning
    reviewer = Reviewer(
        store,
        gitea,
        Driver(client, config.roles.resolve("driver"), cancel=Cancel()),  # type: ignore[arg-type]
        account=account,
        gitea_url=config.gitea_url,
        oplog=oplog,
        knowledge=Knowledge(vault, memory, oplog),
        expert=ExpertDesk(
            client,  # type: ignore[arg-type]
            config.roles,
            budget=tuning.expert.consult_budget,
        ),
        max_turns=tuning.review.max_turns,
        diff_chars=tuning.review.diff_chars,
    )
    scratch = config.state_db.parent / "scratch"
    scratch.mkdir(exist_ok=True)
    scheduler = Scheduler(
        store,
        gitea,
        reviewer,
        oplog=oplog,
        scratch=Path(scratch),
        poll_s=tuning.review.poll_s,
        attempts=tuning.review.attempts,
        patterns=config.repositories,
    )
    return Built(scheduler, account, repos, store, gitea)