refactor(forge): address PR #318 review — PR/Issue split, sqlite state, drop footer

Addresses the five review comments on PR #318: - Split PullRequest from Issue and add a dedicated read_pr method on Forge/ScopedForge/GiteaForge (a PR carries merge state an issue does not); is_pr_open now derives from read_pr. - Replace the JSON-file forge state with a thin swappable CRUD interface (ForgeStateStore) backed by SQLite (SqliteForgeStateStore) at ~/.bot-bottle/bot-bottle.db. - Remove the provenance footer (provenance.py + its test): a mutable, unsigned PR comment is not an audit record. - Reword the PRD: provenance is exposed via an API, not surfaced in the PR; document the Issue/PullRequest split and the SQLite store. pyright clean (whole repo), pylint 10/10, 38 forge/resume unit tests pass; no remaining refs to the removed provenance module or old JSON state API. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WL77TgFxKbs3cidGMG9dz7
fix(tests): resolve pyright strict errors in forge test helpers
2026-07-01 08:37:25 -04:00 · 2026-07-01 07:58:55 -04:00 · 2026-06-30 19:39:49 -04:00 · 2026-06-30 19:19:01 -04:00 · 2026-06-30 17:46:59 -04:00 · 2026-06-30 17:39:33 -04:00
22 changed files with 1776 additions and 497 deletions
@@ -209,6 +209,15 @@ class AgentProvider(ABC):
        the supervise sidecar is reachable. No-op when
        `plan.supervise_plan is None`."""
    @abstractmethod
    def headless_prompt(self, prompt: str) -> list[str]:
        """Return the agent CLI args that deliver `prompt` as the
        initial task in a non-interactive (headless) session.
        Called only when ``--prompt`` is passed to
        ``./cli.py start --headless``; the returned args are appended
        after the provider's ``bypass_args`` and ``startup_args``."""
    def provision_ca(self, bottle: "Bottle", plan: "BottlePlan") -> None:
        """Install the egress MITM CA into the agent's trust store.
@@ -27,12 +27,34 @@ from .start import _launch_bottle
 def cmd_resume(argv: list[str]) -> int:
    parser = argparse.ArgumentParser(prog=f"{PROG} resume", add_help=True)
    parser.add_argument("--dry-run", action="store_true")
    parser.add_argument(
        "--headless",
        action="store_true",
        help=(
            "non-interactive rehydrate: deliver --prompt to the agent and "
            "skip the y/N preflight. For orchestrators / the freeze-rehydrate "
            "loop."
        ),
    )
    parser.add_argument(
        "--prompt",
        default=None,
        help="follow-up prompt delivered to the agent (required with --headless)",
    )
    parser.add_argument(
        "identity",
        help="bottle identity from a prior `start` (see its session-end output)",
    )
    args = parser.parse_args(argv)
    if args.prompt and not args.headless:
        die("--prompt is only valid with --headless")
    if args.headless and not args.prompt:
        die(
            "--headless requires --prompt: "
            "./cli.py resume <identity> --headless --prompt 'Address the review'"
        )
    metadata = read_metadata(args.identity)
    if metadata is None:
        die(
@@ -56,4 +78,6 @@ def cmd_resume(argv: list[str]) -> int:
        spec,
        dry_run=args.dry_run,
        backend_name=backend_name,
        assume_yes=args.headless,
        headless_prompt_text=args.prompt or "",
    )
@@ -2,6 +2,11 @@
 interactive claude-code session. The container is torn down when the
 session ends.
 `--headless` selects a non-interactive launch (agent/bottles/label from
 flags, no TUI selectors, no y/N prompt) for orchestrators,
 CI, and webhook dispatch. The agent still execs on the inherited
 stdio/PTY, so an orchestrator that allocates the PTY drives the session.
 The launch core is shared with `cli.py resume <identity>` through
 the private orchestrator `_launch_bottle`.
 """
@@ -16,7 +21,7 @@ import tempfile
 from pathlib import Path
 from typing import Callable
-from ..agent_provider import runtime_for
+from ..agent_provider import get_provider, runtime_for
 from ..backend import (
    Bottle,
    BottleSpec,
@@ -31,7 +36,7 @@ from ..bottle_state import (
    is_preserved,
    mark_preserved,
 )
-from ..log import info
+from ..log import info, die
 from ..manifest import Manifest, ManifestIndex
 from ._common import PROG, USER_CWD, read_tty_line
 from . import tui
@@ -50,6 +55,39 @@ def cmd_start(argv: list[str]) -> int:
            "or host auto-selection). Overrides the env var when set."
        ),
    )
    parser.add_argument(
        "--headless",
        action="store_true",
        help=(
            "non-interactive launch: take agent/bottles/label from flags, "
            "skip all prompts. For orchestrators, CI, and webhooks."
        ),
    )
    parser.add_argument(
        "--bottle",
        action="append",
        default=None,
        metavar="NAME",
        help=(
            "bottle to compose, repeatable (order = merge order). In "
            "--headless, defaults to the agent's own bottle when omitted."
        ),
    )
    parser.add_argument(
        "--label",
        default=None,
        help="bottle label / terminal title (--headless default: agent name)",
    )
    parser.add_argument(
        "--color",
        default=None,
        help="bottle color, one of the 16 ANSI color names (--headless default: none)",
    )
    parser.add_argument(
        "--prompt",
        default=None,
        help="initial task prompt delivered to the agent (required with --headless)",
    )
    parser.add_argument(
        "name",
        nargs="?",
@@ -61,6 +99,12 @@ def cmd_start(argv: list[str]) -> int:
    dry_run = args.dry_run or os.environ.get("BOT_BOTTLE_DRY_RUN") == "1"
    manifest = ManifestIndex.resolve(USER_CWD)
    backend_name: str | None = args.backend
    if args.headless:
        return _start_headless(
            manifest, args, dry_run=dry_run, backend_name=backend_name
        )
    agent_name: str | None = args.name
    if agent_name is None:
@@ -71,8 +115,6 @@ def cmd_start(argv: list[str]) -> int:
        if agent_name is None:
            return 0
    backend_name: str | None = args.backend
    # Bottle multiselect: always show after agent selection so operators
    # can compose bottles at launch time without editing agent manifests.
    available_bottles = manifest.all_bottle_names
@@ -109,6 +151,83 @@ def cmd_start(argv: list[str]) -> int:
    )
 # --- Headless launch -----------------------------------------------------
 def _start_headless(
    manifest: ManifestIndex,
    args: argparse.Namespace,
    *,
    dry_run: bool,
    backend_name: str | None,
 ) -> int:
    """Non-interactive launch path for orchestrators / CI / webhooks.
    Resolves agent, bottles, label, and color from flags + manifest
    defaults instead of the TUI selectors, and auto-confirms the
    preflight. Otherwise runs the same launch core as the interactive
    path, so the agent still execs on the inherited stdio/PTY — an
    orchestrator allocates that PTY and relays it to its
    desktop/mobile clients."""
    agent_name = args.name
    if not agent_name:
        die("--headless requires an agent name: ./cli.py start <agent> --headless")
    manifest.require_agent(agent_name)  # raises ManifestError if unknown
    prompt = args.prompt
    if not prompt:
        die(
            "--headless requires --prompt: "
            "./cli.py start <agent> --headless --prompt 'Do the thing'"
        )
    if args.bottle:
        bottle_names: tuple[str, ...] = tuple(args.bottle)
    else:
        default_bottle = _peek_agent_bottle(manifest, agent_name)
        if not default_bottle:
            die(
                f"--headless: agent '{agent_name}' has no default bottle; "
                f"pass one or more --bottle NAME"
            )
        bottle_names = (default_bottle,)
    label = _uniquify_label_headless(args.label or agent_name)
    spec = BottleSpec(
        manifest=manifest,
        agent_name=agent_name,
        copy_cwd=args.cwd,
        user_cwd=USER_CWD,
        label=label,
        color=args.color or "",
        bottle_names=bottle_names,
    )
    return _launch_bottle(
        spec,
        dry_run=dry_run,
        backend_name=backend_name,
        assume_yes=True,
        headless_prompt_text=prompt,
    )
 def _uniquify_label_headless(label: str) -> str:
    """Non-interactive analog of `_resolve_unique_label`: if the label's
    slug collides with a running bottle, append -2, -3, … until free,
    logging the chosen label. Orchestrators fire-and-forget many bottles,
    so silently picking a free name beats erroring on every collision."""
    active_slugs = {a.slug for a in enumerate_active_agents()}
    if docker_mod.slugify(label) not in active_slugs:
        return label
    n = 2
    while docker_mod.slugify(f"{label}-{n}") in active_slugs:
        n += 1
    chosen = f"{label}-{n}"
    info(f"label '{label}' already in use; using '{chosen}'")
    return chosen
 # --- Launch helpers ------------------------------------------------------
@@ -376,10 +495,19 @@ def _launch_bottle(
    *,
    dry_run: bool,
    backend_name: str | None = None,
    assume_yes: bool = False,
    headless_prompt_text: str = "",
 ) -> int:
    """Shared launch core for `start` and `resume`. Builds the plan,
    prints / dry-runs / prompts as appropriate, brings the bottle up,
-    attaches claude, and prints the resume hint on session end."""
+    attaches claude, and prints the resume hint on session end.
    `assume_yes` skips the interactive y/N confirmation (headless /
    orchestrator launches), where there is no human at the prompt.
    `headless_prompt_text` is passed to the provider's `headless_prompt`
    method and the resulting args are appended to startup_args so the
    agent receives the initial task without interactive input."""
    stage_dir = Path(tempfile.mkdtemp(prefix="bot-bottle-stage."))
    identity = ""
    try:
@@ -387,7 +515,7 @@ def _launch_bottle(
            spec,
            stage_dir=stage_dir,
            render_preflight=_text_render_preflight(),
-            prompt_yes=_text_prompt_yes,
+            prompt_yes=(lambda: True) if assume_yes else _text_prompt_yes,
            dry_run=dry_run,
            backend_name=backend_name,
        )
@@ -397,10 +525,17 @@ def _launch_bottle(
        backend = get_bottle_backend(backend_name)
        with backend.launch(plan) as bottle:
            agent_provider_template = getattr(plan, "agent_provider_template", "claude")
            extra_args: tuple[str, ...] = ()
            if headless_prompt_text:
                extra_args = tuple(
                    get_provider(agent_provider_template).headless_prompt(
                        headless_prompt_text
                    )
                )
            exit_code = attach_agent(
                bottle,
                agent_provider_template=agent_provider_template,
-                startup_args=plan.agent_provision.startup_args,
+                startup_args=plan.agent_provision.startup_args + extra_args,
            )
            info(
                f"session ended (exit {exit_code}); "
@@ -313,6 +313,9 @@ class ClaudeAgentProvider(AgentProvider):
                f"claude mcp add --scope user --transport http supervise {supervise_url}"
            )
    def headless_prompt(self, prompt: str) -> list[str]:
        return ["-p", prompt]
 def _exec(bottle: "Bottle", script: str, error: str) -> None:
    result = bottle.exec(script, user="root")
@@ -279,6 +279,9 @@ class CodexAgentProvider(AgentProvider):
                f"codex mcp add supervise --url {shlex.quote(supervise_url)}"
            )
    def headless_prompt(self, prompt: str) -> list[str]:
        return [prompt]
 def _exec(bottle: "Bottle", script: str, error: str) -> None:
    result = bottle.exec(script, user="root")
@@ -0,0 +1,165 @@
 """Forge abstraction (PRD forge-native-integration, chunk 3).
 The `Forge` abstract class is the provider-agnostic surface a forge
 sidecar dispatches to: read issues/comments, post comments, edit
 descriptions, and the membership / PR lookups the orchestrator needs.
 Each forge (Gitea first) implements it; the sidecar protocol and the
 agent prompt stay forge-agnostic.
 `signal_done` is deliberately *not* a `Forge` method — completion is a
 sidecar concept relayed to the orchestrator over a queue dir, not a
 forge API operation.
 `ScopedForge` enforces the PRD's **read-anywhere / write-scoped** model:
 reads pass through to any issue/PR for context; writes are rejected
 unless the target is the assigned issue or one of its PRs. This bounds
 the blast radius of a prompt-injected agent below repo-wide API-key
 permissions.
 """
 from __future__ import annotations
 import abc
 from collections.abc import Iterable
 from dataclasses import dataclass
@dataclass(frozen=True)
 class Issue:
    """A forge issue (not a PR — see `PullRequest`)."""
    number: int
    title: str
    body: str
    state: str  # "open" | "closed"
@dataclass(frozen=True)
 class PullRequest:
    """A forge pull request. Kept distinct from `Issue` even though some
    forges model PRs as issues on the wire: the domain objects carry
    different data (a PR has merge state) and are read through different
    methods (`read_pr` vs `read_issue`)."""
    number: int
    title: str
    body: str
    state: str  # "open" | "closed"
    merged: bool
@dataclass(frozen=True)
 class Comment:
    id: int
    user: str  # login of the comment author
    body: str
 class ForgeScopeError(PermissionError):
    """Raised by `ScopedForge` when a write targets an issue/PR outside
    the assigned scope."""
 class Forge(abc.ABC):
    """Provider-agnostic forge operations. Implementations wrap a
    per-provider HTTP client and translate to `Issue` / `Comment`."""
    @abc.abstractmethod
    def read_issue(self, number: int) -> Issue:
        """Read an issue body (read-anywhere)."""
    @abc.abstractmethod
    def read_pr(self, number: int) -> PullRequest:
        """Read a pull request, including its merge state (read-anywhere)."""
    @abc.abstractmethod
    def read_comments(self, number: int) -> list[Comment]:
        """Read a thread's comments (read-anywhere)."""
    @abc.abstractmethod
    def post_comment(self, number: int, body: str) -> None:
        """Post a comment to an issue or PR (write-scoped)."""
    @abc.abstractmethod
    def update_description(self, number: int, body: str) -> None:
        """Replace an issue or PR body (write-scoped)."""
    @abc.abstractmethod
    def is_org_member(self, org: str, username: str) -> bool:
        """Whether `username` is a member of `org`."""
    @abc.abstractmethod
    def get_pr_for_issue(self, number: int) -> int | None:
        """The PR number linked to an issue, or None when there is none."""
    @abc.abstractmethod
    def is_pr_open(self, number: int) -> bool:
        """Whether the given PR is still open."""
 class ScopedForge(Forge):
    """Read-anywhere / write-scoped wrapper around a concrete `Forge`.
    `post_comment` and `update_description` are rejected with
    `ForgeScopeError` unless the target number is the assigned issue or
    one of the assigned PRs. Every other method delegates unchanged, so
    reads, membership checks, and PR lookups work against any number for
    context.
    The writable set is fixed at construction. The sidecar reconstructs
    a `ScopedForge` when a PR is discovered (`get_pr_for_issue`) so the
    new PR becomes writable; this class does not mutate its own scope.
    """
    def __init__(
        self,
        inner: Forge,
        *,
        assigned_issue: int,
        assigned_prs: Iterable[int] = (),
    ) -> None:
        self._inner = inner
        self._assigned_issue = assigned_issue
        self._writable = {assigned_issue, *assigned_prs}
    @property
    def writable(self) -> frozenset[int]:
        return frozenset(self._writable)
    def _check_write(self, number: int) -> None:
        if number not in self._writable:
            allowed = ", ".join(str(n) for n in sorted(self._writable))
            raise ForgeScopeError(
                f"write to #{number} denied: out of assigned scope "
                f"(writable: {allowed})"
            )
    # --- read-anywhere: pass through --------------------------------------
    def read_issue(self, number: int) -> Issue:
        return self._inner.read_issue(number)
    def read_pr(self, number: int) -> PullRequest:
        return self._inner.read_pr(number)
    def read_comments(self, number: int) -> list[Comment]:
        return self._inner.read_comments(number)
    def is_org_member(self, org: str, username: str) -> bool:
        return self._inner.is_org_member(org, username)
    def get_pr_for_issue(self, number: int) -> int | None:
        return self._inner.get_pr_for_issue(number)
    def is_pr_open(self, number: int) -> bool:
        return self._inner.is_pr_open(number)
    # --- write-scoped: check then delegate --------------------------------
    def post_comment(self, number: int, body: str) -> None:
        self._check_write(number)
        self._inner.post_comment(number, body)
    def update_description(self, number: int, body: str) -> None:
        self._check_write(number)
        self._inner.update_description(number, body)
@@ -0,0 +1,174 @@
 """Gitea HTTP client + `GiteaForge` (PRD forge-native-integration, chunk 3).
 `GiteaClient` is the thin stdlib-only HTTP transport (mirrors
 `deploy_key_provisioner.py`: `urllib.request`, bounded timeouts,
 structured error bodies). `GiteaForge` adapts it to the provider-agnostic
 `Forge` surface.
 Unlike the option-2 design, the token is held here (the sidecar process
 owns it) and passed to the client directly — there is no agent-side
 cred-proxy route, because the agent never makes forge calls. The HTTP
 client is the one piece shared with `GiteaDeployKeyProvisioner`; the two
 are deliberately *not* unified behind a common abstract base (see the
 deferral note in the PRD).
 """
 from __future__ import annotations
 import json
 import urllib.error
 import urllib.request
 from typing import Any
 from ..forge.base import Comment, Forge, Issue, PullRequest
 # Bound every Gitea call: a hung instance must not stall the sidecar.
 _API_TIMEOUT_SECS = 30
 class GiteaClient:
    """Thin authenticated HTTP client for one repo's Gitea API.
    `api_url` is the API base *including* `/api/v1` (matching the
    `FORGE_GITEA_API` env var), e.g. `https://gitea.example.com/api/v1`.
    """
    def __init__(self, *, api_url: str, owner: str, repo: str, token: str) -> None:
        self._api_url = api_url.rstrip("/")
        self._owner = owner
        self._repo = repo
        self._token = token
    # --- low-level request -------------------------------------------------
    def _request(
        self, method: str, path: str, *, body: dict[str, Any] | None = None
    ) -> tuple[int, Any]:
        """Issue an authenticated request. Returns `(status, parsed_json)`;
        parsed_json is None when the response has no body. Raises
        `RuntimeError` on any non-2xx except where callers special-case
        the HTTPError themselves (membership 404)."""
        url = f"{self._api_url}{path}"
        data = json.dumps(body).encode() if body is not None else None
        headers = {"Authorization": f"token {self._token}"}
        if data is not None:
            headers["Content-Type"] = "application/json"
        req = urllib.request.Request(url, data=data, headers=headers, method=method)
        with urllib.request.urlopen(req, timeout=_API_TIMEOUT_SECS) as resp:
            raw = resp.read()
            parsed = json.loads(raw) if raw else None
            return resp.status, parsed
    def _repo_path(self, suffix: str) -> str:
        return f"/repos/{self._owner}/{self._repo}{suffix}"
    # --- operations --------------------------------------------------------
    def is_org_member(self, org: str, username: str) -> bool:
        """GET /orgs/{org}/members/{username}: 2xx → member, 404 → not.
        Other errors propagate so a misconfigured token fails loudly."""
        url = f"{self._api_url}/orgs/{org}/members/{username}"
        req = urllib.request.Request(
            url, headers={"Authorization": f"token {self._token}"}, method="GET"
        )
        try:
            with urllib.request.urlopen(req, timeout=_API_TIMEOUT_SECS):
                return True
        except urllib.error.HTTPError as exc:
            if exc.code == 404:
                return False
            raise RuntimeError(
                f"org membership check failed for {org}/{username}: "
                f"HTTP {exc.code} — {_read_error_body(exc)}"
            ) from exc
    def get_issue(self, number: int) -> dict[str, Any]:
        _status, body = self._request("GET", self._repo_path(f"/issues/{number}"))
        return body or {}
    def get_comments(self, number: int) -> list[dict[str, Any]]:
        _status, body = self._request(
            "GET", self._repo_path(f"/issues/{number}/comments")
        )
        return body or []
    def post_comment(self, number: int, body: str) -> None:
        self._request(
            "POST",
            self._repo_path(f"/issues/{number}/comments"),
            body={"body": body},
        )
    def patch_issue_body(self, number: int, body: str) -> None:
        self._request(
            "PATCH", self._repo_path(f"/issues/{number}"), body={"body": body}
        )
    def get_pull(self, number: int) -> dict[str, Any]:
        _status, body = self._request("GET", self._repo_path(f"/pulls/{number}"))
        return body or {}
 class GiteaForge(Forge):
    """`Forge` over a `GiteaClient`."""
    def __init__(self, client: GiteaClient) -> None:
        self._client = client
    def read_issue(self, number: int) -> Issue:
        raw = self._client.get_issue(number)
        return Issue(
            number=int(raw.get("number", number)),
            title=str(raw.get("title", "")),
            body=str(raw.get("body", "") or ""),
            state=str(raw.get("state", "")),
        )
    def read_pr(self, number: int) -> PullRequest:
        raw = self._client.get_pull(number)
        return PullRequest(
            number=int(raw.get("number", number)),
            title=str(raw.get("title", "")),
            body=str(raw.get("body", "") or ""),
            state=str(raw.get("state", "")),
            merged=bool(raw.get("merged", False)),
        )
    def read_comments(self, number: int) -> list[Comment]:
        return [
            Comment(
                id=int(c.get("id", 0)),
                user=str((c.get("user") or {}).get("login", "")),
                body=str(c.get("body", "") or ""),
            )
            for c in self._client.get_comments(number)
        ]
    def post_comment(self, number: int, body: str) -> None:
        self._client.post_comment(number, body)
    def update_description(self, number: int, body: str) -> None:
        self._client.patch_issue_body(number, body)
    def is_org_member(self, org: str, username: str) -> bool:
        return self._client.is_org_member(org, username)
    def get_pr_for_issue(self, number: int) -> int | None:
        """Gitea models a PR as an issue with the same number, exposing a
        `pull_request` object on the issue. When the queried number is
        itself a PR, return it; otherwise None. (The orchestrator tracks
        the issue→PR mapping in forge state for the cross-number case.)"""
        raw = self._client.get_issue(number)
        if raw.get("pull_request"):
            return int(raw.get("number", number))
        return None
    def is_pr_open(self, number: int) -> bool:
        return self.read_pr(number).state == "open"
 def _read_error_body(exc: urllib.error.HTTPError) -> str:
    try:
        return exc.read().decode("utf-8", errors="replace")
    except Exception:  # pylint: disable=broad-exception-caught
        return ""
@@ -0,0 +1,171 @@
 """Forge state persistence (PRD forge-native-integration, chunk 2).
 The orchestrator tracks one record per forge-targeted issue so it can
 map an incoming webhook back to the bottle handling it, drive the
 freeze / rehydrate loop, and run the watchdog.
 State is stored in a local SQLite database in `~/.bot-bottle/`. Access
 goes through the thin `ForgeStateStore` CRUD interface so the backing
 store (location or engine) can be swapped without touching callers;
 `SqliteForgeStateStore` is the first implementation.
 """
 from __future__ import annotations
 import abc
 import json
 import sqlite3
 from dataclasses import dataclass, field
 from pathlib import Path
 from ...supervise import bot_bottle_root
 _DB_FILENAME = "bot-bottle.db"
 # Lifecycle: a bottle is launched (running), frozen on the done signal,
 # and destroyed when the PR closes.
 STATUS_RUNNING = "running"
 STATUS_FROZEN = "frozen"
 STATUS_DESTROYED = "destroyed"
@dataclass
 class ForgeState:
    """One forge-targeted issue's bottle lifecycle record."""
    owner: str
    repo: str
    issue_number: int
    slug: str
    agent_name: str
    bottle_names: list[str] = field(default_factory=list)
    backend_name: str = ""
    agent_git_user: str = ""
    pr_number: int | None = None
    status: str = STATUS_RUNNING
    last_checkin_at: str = ""
 class ForgeStateStore(abc.ABC):
    """Thin CRUD surface over forge state. Implementations back it with a
    concrete store; callers depend only on this interface so the storage
    location/engine is swappable."""
    @abc.abstractmethod
    def upsert(self, state: ForgeState) -> None:
        """Insert or replace the record keyed by (owner, repo, issue)."""
    @abc.abstractmethod
    def get(self, owner: str, repo: str, issue_number: int) -> ForgeState | None:
        """Fetch one record, or None when absent."""
    @abc.abstractmethod
    def delete(self, owner: str, repo: str, issue_number: int) -> None:
        """Remove a record. Missing is success (idempotent)."""
    @abc.abstractmethod
    def all(self) -> list[ForgeState]:
        """Every record, for the status table and the watchdog sweep."""
 def default_db_path() -> Path:
    return bot_bottle_root() / _DB_FILENAME
 class SqliteForgeStateStore(ForgeStateStore):
    """SQLite-backed `ForgeStateStore`. The database lives at
    `~/.bot-bottle/bot-bottle.db` by default; pass `db_path` to point at
    a different location (tests, alternate homes)."""
    def __init__(self, db_path: Path | None = None) -> None:
        self._db_path = db_path or default_db_path()
        self._db_path.parent.mkdir(parents=True, exist_ok=True)
        with self._connect() as conn:
            conn.execute(
                """
                CREATE TABLE IF NOT EXISTS forge_state (
                    owner           TEXT    NOT NULL,
                    repo            TEXT    NOT NULL,
                    issue_number    INTEGER NOT NULL,
                    slug            TEXT    NOT NULL,
                    agent_name      TEXT    NOT NULL,
                    bottle_names    TEXT    NOT NULL,
                    backend_name    TEXT    NOT NULL,
                    agent_git_user  TEXT    NOT NULL,
                    pr_number       INTEGER,
                    status          TEXT    NOT NULL,
                    last_checkin_at TEXT    NOT NULL,
                    PRIMARY KEY (owner, repo, issue_number)
                )
                """
            )
    def _connect(self) -> sqlite3.Connection:
        conn = sqlite3.connect(self._db_path)
        conn.row_factory = sqlite3.Row
        return conn
    def upsert(self, state: ForgeState) -> None:
        with self._connect() as conn:
            conn.execute(
                """
                INSERT OR REPLACE INTO forge_state (
                    owner, repo, issue_number, slug, agent_name,
                    bottle_names, backend_name, agent_git_user,
                    pr_number, status, last_checkin_at
                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
                """,
                (
                    state.owner,
                    state.repo,
                    state.issue_number,
                    state.slug,
                    state.agent_name,
                    json.dumps(state.bottle_names),
                    state.backend_name,
                    state.agent_git_user,
                    state.pr_number,
                    state.status,
                    state.last_checkin_at,
                ),
            )
    def get(self, owner: str, repo: str, issue_number: int) -> ForgeState | None:
        with self._connect() as conn:
            row = conn.execute(
                "SELECT * FROM forge_state "
                "WHERE owner = ? AND repo = ? AND issue_number = ?",
                (owner, repo, issue_number),
            ).fetchone()
        return _row_to_state(row) if row is not None else None
    def delete(self, owner: str, repo: str, issue_number: int) -> None:
        with self._connect() as conn:
            conn.execute(
                "DELETE FROM forge_state "
                "WHERE owner = ? AND repo = ? AND issue_number = ?",
                (owner, repo, issue_number),
            )
    def all(self) -> list[ForgeState]:
        with self._connect() as conn:
            rows = conn.execute(
                "SELECT * FROM forge_state ORDER BY owner, repo, issue_number"
            ).fetchall()
        return [_row_to_state(row) for row in rows]
 def _row_to_state(row: sqlite3.Row) -> ForgeState:
    return ForgeState(
        owner=row["owner"],
        repo=row["repo"],
        issue_number=row["issue_number"],
        slug=row["slug"],
        agent_name=row["agent_name"],
        bottle_names=json.loads(row["bottle_names"]),
        backend_name=row["backend_name"],
        agent_git_user=row["agent_git_user"],
        pr_number=row["pr_number"],
        status=row["status"],
        last_checkin_at=row["last_checkin_at"],
    )
@@ -315,6 +315,9 @@ class PiAgentProvider(AgentProvider):
    ) -> None:
        del plan, bottle, supervise_url
    def headless_prompt(self, prompt: str) -> list[str]:
        return ["-p", prompt]
 def _exec(bottle: "Bottle", script: str, error: str) -> None:
    result = bottle.exec(script, user="root")
@@ -0,0 +1,439 @@
 # PRD prd-new: Forge native integration
 - **Status:** Draft
 - **Author:** claude
 - **Created:** 2026-06-29
 - **Issue:** #317
 ## Summary
 Add a webhook-driven orchestration layer that lets Gitea issues and PR comments
 drive bot-bottle sessions end-to-end with no operator in the loop for the happy
 path. An issue assigned to a member of the configured agent org and labelled
 with an agent name triggers a headless bottle launch; the bottle processes the
 issue, opens a PR, and interacts with the forge through a **forge sidecar** —
 the agent never touches the Gitea API or its credentials directly. The agent
 calls `signal_done(status, summary)` on the sidecar when a work unit is
 complete; the sidecar relays that to the orchestrator over a queue dir (the same
 pattern as the supervise sidecar), so completion is an unambiguous in-band
 signal rather than a comment the orchestrator has to parse. The orchestrator
 freezes the bottle. Subsequent PR comments rehydrate the frozen bottle. The
 bottle is destroyed when the PR closes.
 The forge sidecar is backed by a `Forge` abstract class with per-provider
 implementations (Gitea first), so the agent's prompts and the sidecar protocol
 stay forge-agnostic. The sidecar logs forge operations semantically ("read PR
 description", "posted comment", "signalled done"), giving richer provenance than
 post-hoc egress-byte parsing, and enforces a **read-anywhere / write-scoped**
 permission model: the agent may read for context but may only write to the
 issue and PRs it was assigned.
 Run provenance is exposed through a **provenance API** (the sidecar's structured
 operation log plus the run's metadata), not posted back into the forge. We do
 not surface a provenance footer in the PR — the audit record lives behind the
 API where it can be retained and queried, rather than as an editable comment.
 The separation of concerns across the two layers: bot-bottle owns the headless
 launch primitives, the forge sidecar + `Forge` abstraction, and forge state.
 `bot-bottle-orchestrator` (separate binary) owns the webhook listener, bottle
 lifecycle loop, and monitoring dashboard; it calls into bot-bottle via
 `./cli.py orchestrate`, a thin wrapper command. This PRD covers bot-bottle's
 side of that contract.
 ## Problem
 Today an operator must open the TUI, select an agent and bottle, confirm the
 preflight, and type prompts interactively. This blocks "issue → PR" automation
 and produces no durable audit record of what the agent did. The security model
 already provides the right isolation and egress controls, and `start --headless`
 (#315) already gives `bot-bottle-orchestrator` a non-interactive launch path.
 The missing pieces are a headless `resume` counterpart for rehydrating frozen
 bottles, a forge-interaction surface the agent uses to read context, post
 comments, and signal completion, and the provenance trail that makes the audit
 story legible to reviewers on every PR.
 That forge-interaction surface could be built two ways: (2) give the agent the
 Gitea API directly with cred-proxy injecting the token, or (3) put a forge
 sidecar between the agent and the forge. This PRD takes **option 3**. The
 deciding factors: a sidecar `signal_done` call is an unambiguous completion
 signal where comment-parsing is a correctness risk that surfaces in production;
 the sidecar produces a semantic audit trail rather than HTTP bytes, which is
 load-bearing for provenance (the stated product priority); and the sidecar can
 enforce scope tighter than repo-wide API-key permissions, reducing blast radius
 for a prompt-injected agent. The costs — a second sidecar process per forge run,
 a new failure mode if it crashes, and per-forge implementation cost — are
 accepted as the price of those properties.
 ## Goals / Success Criteria
 1. Headless launch already exists: `./cli.py start <agent> --headless --prompt`
   (#315) runs non-interactively with no TUI selectors or y/N preflight. This
   PRD builds on it rather than re-introducing it. The remaining gap is a
   matching headless `resume` path (`./cli.py resume --headless`), since
   rehydrating a frozen bottle for a new prompt is required by the freeze /
   rehydrate loop and `resume` has no non-interactive entry point today.
 2. An issue assigned to a member of the configured org (`FORGE_ORG`, default
   `bot-bottle`) and labelled `bot-bottle:<agent-name>` is the trigger
   convention. Org membership is verified via the Gitea API at event time.
 3. Forge-targeted bottles run a **forge sidecar** that exposes a small,
   forge-agnostic API (comment/issue/PR CRUD plus `signal_done`) over the same
   queue-dir + HTTP/JSON-RPC machinery as the supervise sidecar. The agent calls
   the sidecar; it never sees the forge token or forge-specific endpoints.
 4. The sidecar is backed by a `Forge` abstract class. Gitea is the first
   concrete implementation; adding a forge means a new subclass, not changes to
   the agent prompt or sidecar protocol. The sidecar enforces a read-anywhere /
   write-scoped model: writes are limited to the assigned issue and its PRs;
   reads are unrestricted for context.
 5. The agent calls `signal_done(status, summary)` on the sidecar when a work
   unit is complete; the sidecar relays it to the orchestrator over a queue dir.
   This is the done signal — no comment parsing. A watchdog timeout
   (configurable, default 30 min) causes the orchestrator to treat the run as
   done-without-self-report if the agent exits without signalling.
 6. Run provenance (agent name, bottle name(s), slug, timing, exit code,
   gitleaks result, egress summary, and the sidecar's semantic operation log)
   is available through a provenance API. It is **not** surfaced as a PR footer
   or any other forge comment.
 7. Forge state (issue → slug, status) is persisted in a local SQLite database
   under `~/.bot-bottle/` and survives orchestrator restarts.
 8. `./cli.py orchestrate status` lists active forge-managed bottles and their
   issue/PR URLs.
 9. Unit tests cover: label parsing, org-membership check path, forge state
   store CRUD (SQLite), headless launch arg construction, forge env var
   injection, sidecar request dispatch through the `Forge` abstraction,
   write-scope enforcement (reject writes outside the assigned issue/PRs), and
   `signal_done` queue relay.
 ## Non-goals
 - Webhook signature verification (HMAC-SHA256). Added as a follow-up.
 - The `bot-bottle-orchestrator` binary itself — this PRD covers bot-bottle's
  side of the interface only. The orchestrator is a separate project.
 - GitHub or GitLab support.
 - Multiple simultaneous forge bottles per issue.
 - Automatic retry on agent error exit.
 - Bottle destruction on issue close (PR close only; issue close is ambiguous).
 - Concurrent multi-issue handling (one blocking run per orchestrator process).
 - A monitoring dashboard (orchestrator-side concern).
 - Folding `DeployKeyProvisioner` into the `Forge` abstraction. Deploy-key
  provisioning runs at bottle-provision time on the host; the forge sidecar runs
  inside the bottle at agent time. The two have different lifecycles and actors,
  so coupling them into one class is deferred to a follow-up. This PRD only
  shares the Gitea HTTP client between them.
 ## Design
 ### Targeting convention
 An issue is forge-targeted when **both** hold:
 - At least one assignee is a member of the Gitea org named by `FORGE_ORG`
  (default `bot-bottle`). Checked via `GET /api/v1/orgs/{org}/members/{user}`.
 - At least one label has the prefix `bot-bottle:`. The suffix names the agent
  manifest, e.g. `bot-bottle:implementer` → agent `implementer`.
 `FORGE_ORG` is read at orchestrate-command startup. It is not embedded in
 manifests or state files; the orchestrator stamps its value into log output for
 auditability.
 An optional label `bot-bottle-bottle:<name>` overrides bottle selection. When
 absent the agent's default bottle is used.
 ### `./cli.py orchestrate` — the thin wrapper
 ```
 ./cli.py orchestrate start  --agent AGENT [--bottle BOTTLE ...] --prompt PROMPT
                            [--label LABEL] [--backend BACKEND]
 ./cli.py orchestrate resume --slug SLUG --prompt PROMPT [--backend BACKEND]
 ./cli.py orchestrate status
 ```
 `orchestrate start` is a thin shim over the already-shipped `start --headless`
 (#315): it forwards agent / bottle / label / prompt and adds the forge-specific
 wiring (`forge_env`, sidecar launch). It does not re-implement headless launch.
 The caller (`bot-bottle-orchestrator`) manages freeze, state, and the forge
 sidecar's done signal around it.
 `orchestrate resume` is the shim over the new `resume --headless` (below).
 `orchestrate status` prints the forge state table.
 ### Headless primitives — what exists vs. what's new
 Headless **start** already shipped in #315 and this PRD reuses it as-is:
 - `./cli.py start <agent> --headless --prompt TEXT` — no TUI selectors, no y/N
  preflight. Internally `_start_headless()` calls the shared `_launch_bottle()`
  with `assume_yes=True` and `headless_prompt_text=prompt`.
 - The prompt is delivered through `AgentProvider.headless_prompt(prompt)` —
  claude `-p`, codex positional, pi `-p`. The orchestrator does **not** hand-roll
  agent args; it relies on this provider abstraction. (An earlier draft proposed
  `start_headless` / `attach_agent_headless` helpers that constructed
  `--no-interactive`/`-p` directly — those are dropped as redundant with, and
  divergent from, what #315 merged.)
 Two additions are needed on top of #315:
 **1. A `forge_env` hook on the headless launch path.** The orchestrator needs to
 pass forge context + token through to the forge sidecar launched alongside the
 agent. This is a parameter threaded into `_launch_bottle` (the same core
 `start --headless` already uses), not a parallel launch function. The agent
 process itself does not receive the token.
 **2. `resume --headless`** — new in `bot_bottle/cli/resume.py`, mirroring the
 `--headless` flag on `start`:
 ```
 ./cli.py resume <slug> --headless --prompt TEXT
 ```
 It rehydrates a frozen bottle and runs one headless prompt via the same
 `assume_yes` + `headless_prompt` path, returning the agent's exit code. `resume`
 has no non-interactive entry point today, so this is genuinely new work rather
 than a rename of an existing helper.
 ### Forge sidecar
 Forge-targeted bottles run a forge sidecar alongside the agent, mirroring the
 supervise sidecar: a per-bottle process that exposes an HTTP/JSON-RPC endpoint
 over a Unix socket and relays events to the orchestrator through a queue dir.
 The agent calls the sidecar; the sidecar holds the forge token and makes the
 actual forge API calls. The agent never receives the credential and never sees a
 forge-specific endpoint — swapping Gitea for another forge does not change the
 agent prompt or the sidecar protocol.
 The sidecar is configured at launch from the forge context (owner, repo, issue,
 PR) and the token, supplied by the orchestrator — not baked into the agent
 manifest. Because the sidecar owns the token, forge traffic does not need a
 cred-proxy egress route on the agent; the agent's egress policy is unchanged by
 forge targeting.
 **Sidecar protocol** (forge-agnostic; each method maps to a `Forge` call):
 | Method | Scope | Purpose |
 |---|---|---|
 | `read_issue(number)` | read-anywhere | Read an issue body for context |
 | `read_pr(number)` | read-anywhere | Read a PR (incl. merge state) for context |
 | `read_comments(number)` | read-anywhere | Read a thread for context |
 | `post_comment(number, body)` | write-scoped | Post to the assigned issue/PR |
 | `update_description(number, body)` | write-scoped | Edit the assigned issue/PR body |
 | `signal_done(status, summary)` | — | Relay completion to the orchestrator |
 Issues and PRs are distinct domain objects (`Issue` vs `PullRequest`) read
 through distinct methods; a PR carries merge state an issue does not.
 **Scope enforcement** is read-anywhere / write-scoped: read methods accept any
 issue/PR number for context; write methods are rejected unless the target is the
 assigned issue or one of its PRs. This is tighter than Gitea's repo-wide API-key
 permissions and bounds the blast radius of a prompt-injected agent. Rejections
 are logged semantically (operation, target, reason) so the audit trail records
 attempted out-of-scope writes, not just allowed ones.
 **Semantic audit**: every sidecar call is logged as a structured operation
 ("read PR #318 description", "posted comment to #317", "signalled done:
 success") rather than as opaque HTTP bytes. This log feeds provenance directly,
 with no post-hoc egress-log parsing.
 ### `Forge` abstraction — `bot_bottle/contrib/forge/`
 The sidecar dispatches to a `Forge` abstract class. Each provider implements the
 operations behind the sidecar protocol:
 ```python
 class Forge(abc.ABC):
    @abc.abstractmethod
    def read_issue(self, number: int) -> Issue: ...
    @abc.abstractmethod
    def read_pr(self, number: int) -> PullRequest: ...
    @abc.abstractmethod
    def read_comments(self, number: int) -> list[Comment]: ...
    @abc.abstractmethod
    def post_comment(self, number: int, body: str) -> None: ...
    @abc.abstractmethod
    def update_description(self, number: int, body: str) -> None: ...
    @abc.abstractmethod
    def is_org_member(self, org: str, username: str) -> bool: ...
    @abc.abstractmethod
    def get_pr_for_issue(self, number: int) -> int | None: ...
    @abc.abstractmethod
    def is_pr_open(self, number: int) -> bool: ...
 ```
 `Issue` and `PullRequest` are separate frozen dataclasses — a PR adds `merged`.
 `ScopedForge` wraps a concrete `Forge` to enforce the read-anywhere /
 write-scoped model (`post_comment` / `update_description` raise `ForgeScopeError`
 outside the assigned issue and PRs).
 `GiteaForge` is the first and only concrete implementation in this PRD. It wraps
 the Gitea HTTP client (below). Adding GitHub or GitLab later is a new subclass;
 the sidecar, protocol, and agent prompt are untouched.
 > **Deferred:** `DeployKeyProvisioner` is *not* folded into `Forge` here.
 > Deploy-key provisioning runs on the host at provision time; the sidecar runs
 > in the bottle at agent time. They have different lifecycles and actors, so a
 > shared abstract base would couple two unrelated auth contexts. For now they
 > only share the Gitea HTTP client; a later PRD can revisit unification.
 ### Forge env vars
 The orchestrator passes forge context to the **sidecar** (not the agent) at
 launch. The agent does not need owner/repo/issue env vars to construct API
 calls, since it only names issue/PR numbers to the sidecar:
 | Var | Example | Purpose |
 |---|---|---|
 | `FORGE_GITEA_API` | `https://gitea.dideric.is/api/v1` | Base URL the sidecar calls |
 | `FORGE_OWNER` | `didericis` | Repo owner |
 | `FORGE_REPO` | `bot-bottle` | Repo name |
 | `FORGE_ISSUE_NUMBER` | `317` | Assigned issue (defines write scope) |
 | `FORGE_PR_NUMBER` | `318` | Assigned PR (empty until PR exists) |
 The agent's forge-specific prompt instructs it to call `signal_done` on the
 sidecar when a work unit is complete, and to use the sidecar for any
 comment/description writes. The instruction is forge-agnostic and is part of the
 forge prompt overlay, not the base agent manifest, so non-forge runs are
 unaffected.
 ### Done signal and watchdog
 The agent calls `signal_done(status, summary)` on the sidecar when it finishes a
 work unit. The sidecar writes the event to its queue dir; the orchestrator reads
 it and:
 1. Reads the forge state for `(owner, repo, issue_number)`.
 2. If `status == "running"`, treats the event as the done signal: freezes the
   bottle and sets `status = "frozen"`. Provenance is recorded via the
   provenance API — no comment is posted to the forge.
 Because completion is an explicit `signal_done` call, the orchestrator does not
 parse comment text to detect "done", and intermediate comments the agent posts
 mid-run cannot be mistaken for completion.
 **Watchdog**: the orchestrator tracks `last_checkin_at` in forge state, updated
 on each sidecar event. A background thread wakes every minute. If
 `now - last_checkin_at > FORGE_WATCHDOG_TIMEOUT` (default 30 min, configurable
 via env) and `status == "running"`, the orchestrator treats the run as
 done-without-self-report and freezes the bottle, flagging the run as incomplete
 in the provenance record.
 **Sidecar-death failure mode**: if the forge sidecar crashes mid-run the agent
 loses forge access while the bottle is otherwise healthy. The orchestrator
 detects a dead sidecar (socket/queue gone) the same way it detects a stalled
 agent and falls back to the watchdog path.
 ### Forge state — `bot_bottle/contrib/gitea/forge_state.py`
 State is stored in a local SQLite database at `~/.bot-bottle/bot-bottle.db`.
 Access goes through a thin CRUD interface, `ForgeStateStore`, so the storage
 location/engine can be swapped without touching callers. `SqliteForgeStateStore`
 is the first implementation.
 The `forge_state` table is keyed by `(owner, repo, issue_number)` and carries:
 `slug`, `agent_name`, `bottle_names` (JSON), `backend_name`, `agent_git_user`,
 `pr_number` (nullable), `status`, `last_checkin_at`.
 `status`: `"running"` | `"frozen"` | `"destroyed"`.
 Store interface:
 ```python
 class ForgeStateStore(abc.ABC):
    def upsert(self, state: ForgeState) -> None: ...
    def get(self, owner: str, repo: str, issue_number: int) -> ForgeState | None: ...
    def delete(self, owner: str, repo: str, issue_number: int) -> None: ...
    def all(self) -> list[ForgeState]: ...
 class SqliteForgeStateStore(ForgeStateStore):
    def __init__(self, db_path: Path | None = None) -> None: ...
 ```
 `upsert` uses `INSERT OR REPLACE` so a re-run for the same issue overwrites in
 place. The schema is created on first open.
 ### Provenance API
 Run provenance — agent, bottle(s), slug, timing, exit code, gitleaks result,
 egress summary, watchdog-fired flag, and the sidecar's semantic operation log —
 is exposed through a **provenance API**, not posted into the forge. There is no
 provenance footer or run-summary comment.
 The rationale (per the monetization positioning): a PR comment is mutable by any
 maintainer, unsigned, and per-PR, so it is worthless as an audit record and
 invites false trust. The authoritative record therefore lives behind the API,
 where it can be retained, queried, and (eventually) signed. Whether any
 projection of it ever appears in the forge is a separate, out-of-scope decision;
 this PR does not build one.
 The API surface itself (schema, transport, signing, retention) is **out of scope
 for this PRD** and belongs with the orchestrator / control-plane work. bot-bottle
 here only produces the raw material: the sidecar's semantic operation log and the
 run metadata the orchestrator collects.
 ### Gitea HTTP client — `bot_bottle/contrib/gitea/client.py`
 `GiteaForge` (and the existing `GiteaDeployKeyProvisioner`) share one thin HTTP
 client. Unlike the option-2 design, the token is held by the sidecar process and
 passed to the client directly — there is no agent-side cred-proxy route to
 inject it, because the agent never makes forge calls.
 ```python
 class GiteaClient:
    def __init__(self, *, api_url: str, owner: str, repo: str, token: str) -> None: ...
    def is_org_member(self, org: str, username: str) -> bool: ...
    def get_issue(self, number: int) -> dict: ...
    def get_comments(self, number: int) -> list[dict]: ...
    def post_comment(self, number: int, body: str) -> None: ...
    def patch_issue_body(self, number: int, body: str) -> None: ...
    def get_pull(self, number: int) -> dict: ...
 ```
 `GiteaForge` adapts this client to the `Forge` surface (mapping raw JSON to
 `Issue` / `PullRequest` / `Comment`). Sharing only the HTTP client (not an
 abstract base) is the deliberate boundary between the sidecar and the deploy-key
 provisioner — see the deferral note under the `Forge` abstraction.
 ### Implementation chunks
 1. **Headless additions on top of #315** — thread a `forge_env` parameter into
   the existing `_launch_bottle` core (the one `start --headless` already uses);
   add a `--headless` path to `cli/resume.py` reusing `assume_yes` +
   `headless_prompt`. No new `start_headless`/`attach_agent_headless` helpers.
   Tests: `forge_env` reaches the sidecar/`guest_env`; `resume --headless` skips
   the TUI and y/N preflight and returns the agent exit code.
 2. **Forge state** — `contrib/gitea/forge_state.py`: `ForgeState` dataclass,
   `ForgeStateStore` CRUD interface, `SqliteForgeStateStore`. Tests: round-trip,
   missing → None, `INSERT OR REPLACE` upsert, delete idempotent, `all()`
   ordering, persistence across store instances.
 3. **`Forge` abstraction + Gitea client** — `contrib/forge/base.py` (`Forge`
   ABC, `ScopedForge`, `Issue` / `PullRequest` / `Comment`) and
   `contrib/gitea/client.py` + `GiteaForge`: `is_org_member`, `read_issue`,
   `read_pr`, `read_comments`, `post_comment`, `update_description`,
   `get_pr_for_issue`, `is_pr_open`. Tests: mock `urllib.request.urlopen`,
   assert payloads and 404-as-false for membership; `ScopedForge` write-scope
   enforcement.
 4. **Forge sidecar** — sidecar process exposing the protocol over a Unix socket,
   queue-dir relay, write-scope enforcement, semantic op log, `signal_done`.
   Reuses the supervise sidecar bundle machinery. Tests: dispatch each method to
   the `Forge`, reject out-of-scope writes, `signal_done` writes a queue event,
   scope-rejection is logged.
 5. **`./cli.py orchestrate`** — `cli/orchestrate.py` with `start`, `resume`,
   `status` subcommands wired into `cli.py`; `start` launches the forge sidecar
   alongside the agent for forge-targeted runs. Tests: arg parsing, `start`
   delegates to `start --headless`, `resume` delegates to `resume --headless`.
 ## Provenance
 Run provenance is captured (sidecar semantic operation log + run metadata) and
 exposed through a provenance API. It is deliberately **not** surfaced in the
 forge — no footer, no run-summary comment. A mutable, unsigned PR comment is not
 an audit record; the authoritative record lives behind the API where it can be
 retained and signed. The `watchdog_fired` flag marks runs where the agent did
 not self-report completion so consumers of the API know the record may be
 incomplete.
 The provenance API's schema, transport, signing, and retention are out of scope
 for this PRD (control-plane work); bot-bottle here produces the raw material
 only.
@@ -1,490 +0,0 @@
 # Monetization & competitive positioning
 Where, if anywhere, bot-bottle has a paid wedge — given a 2026
 competitive field that has largely commoditized "sandbox a coding
 agent." Folds together the agent-provider-agnostic framing, the Fly
 remote-backend idea, the supervisor/egress-audit play, and the
 solo-dev/Linux brand instinct, then asks the only question that
 matters: is there a viable path to revenue that the competition does
 not already foreclose?
 Companion to
 [`agent-sandbox-landscape.md`](agent-sandbox-landscape.md) (the
 isolation-tech survey),
 [`built-in-supervisor-design.md`](built-in-supervisor-design.md) (the
 supervise surface this would extend), and
 [`secret-minimization-over-dlp.md`](secret-minimization-over-dlp.md)
 (why custody, not detection, is the real moat).
 Market data current as of June 2026.
 ## Summary
 **Verdict: a path exists, but it is narrow, and it is not the path the
 project is currently shaped for.** Every individual property bot-bottle
 leans on — isolation, BYO-image, egress filtering, OSS, self-hosting —
 is matched by some competitor, and several are now *free* from the agent
 vendors themselves. There is exactly one defensible position left: the
 **bundle** that no single competitor occupies —
 > uniform egress audit + secret custody + policy, across *heterogeneous
 > coding agents you don't trust*, on your infra or a managed pool.
 Monetization is viable **only** if the product is sold as cross-vendor
 **fleet governance + egress audit for teams**, not as solo-dev agent
 safety (which the labs give away free). The solo-dev/Linux/anti-corporate
 energy is real and worth using — but as a *distribution and trust*
 engine that drives bottom-up adoption into teams, never as the revenue
 positioning itself. Get those two wires crossed and the business dies:
 you'd be courting the lowest-willingness-to-pay audience on earth while
 repelling the only buyer who pays.
 Net: **viable, conditional, and unforgiving of positioning error.** Do
 Phase 1 (self-hostable egress-audit dashboard) regardless — it's
 low-risk and it's the demo that makes everything else legible. Gate the
 go/no-go on whether 5–10 teams confirm they'd pay for cross-vendor
 egress audit *before* building the hosted tier.
 ## The two axes of "agnostic"
 bot-bottle differentiates on two orthogonal axes, and conflating them
 muddies the pitch:
 1. **Agent-provider agnostic** — run Claude Code, Codex, Aider, a local
   model, behind one control layer. Already real in the code
   (`agent_provider.py`, Claude/Codex templates, BYO Dockerfile). This
   is the axis the labs *structurally cannot* match — Anthropic only
   runs Claude, OpenAI only their models. Durable.
 2. **Compute backend** — local (docker / Apple Container / smolmachines)
   today; a remote **Fly** backend would add a managed pool. This is the
   axis that makes "fleet" literal for orgs and opens metered billing.
   Fly is a strong first remote backend because it also subsumes remote
   spin-up (Machines API) and the tunnel problem (6PN/WireGuard) — but
   "provider-agnostic compute" should be *earned* after backend #2, not
   designed up front (premature generalization trap).
 ## Competitive field, by capability
 The field doesn't have one competitor; it has a different set on each
 capability bot-bottle touches. Five dimensions:
 | Capability | Who has it | bot-bottle's standing |
 | :-- | :-- | :-- |
 | **Isolation / sandbox** | Anthropic & OpenAI **native, free**; OSS devcontainer wrappers; E2B/Modal/Daytona/Northflank | Commoditized. Not a wedge. |
 | **Arbitrary BYO Docker image** | Sandbox PaaS (E2B/Modal/Daytona/Northflank) yes; **managed agents: ~none** (Codex = fixed `codex-universal` + setup scripts; Copilot "not supported"; Devin/Jules constrained) | Wedge **vs. managed agents** (structural: it's their infra). Table stakes vs. PaaS. |
 | **Egress audit + alerts** | LLM-observability tools (Braintrust/Langfuse/Phoenix/Helicone/Datadog) — but on *model calls*, wrong layer. Network-egress security (DeepInspect, AI gateways) — right layer, but decoupled from the agent, not cross-vendor. Sandbox PaaS = gateway/filter, not an audit surface. | **~Nobody in bot-bottle's exact shape** (per-agent egress, tied to the sandbox, with DLP context, cross-vendor). This is the wedge. |
 | **OSS / self-hosting** | Managed agents: ~none. Sandbox PaaS: ~half (E2B OSS+self-host; Northflank BYOC; Modal closed; **Daytona leaving OSS**). Devcontainer wrappers: ~all. Observability: several. | Real wedge **vs. managed agents only**. Table stakes vs. PaaS, zero differentiation vs. wrappers. |
 | **Cross-vendor uniformity** | Nobody — the labs won't, PaaS is agent-neutral infra not agent-aware control, wrappers are single-tool | Wedge. The connective tissue of the whole position. |
 The pattern: **isolation and OSS/self-host are commodity; BYO-image and
 cross-vendor are wedges only against the managed agents; egress-audit in
 the integrated form is the one thing genuinely unoccupied.**
 ## Where bot-bottle is alone vs. where it's table stakes
 - **Alone (the moat):** egress audit + secret custody + policy, *tied to
  the agent sandbox*, *with DLP context* (which secret, which host,
  which agent/task), *uniform across vendors*. No competitor bundles
  these. An enterprise *could* bolt DeepInspect-style egress monitoring
  onto a sandbox, so the defensibility is the **integration and
  per-agent context**, not "we can see egress."
 - **Table stakes (do not lead with these):** "we sandbox agents" (free
  from the labs), "we're open source" (E2B is; the wrapper crowd all
  is), "we self-host" (Northflank BYOC, E2B, every wrapper).
 ## The two existential competitive facts
 1. **The agent vendors ship good-enough sandboxing for free.** Claude
   Code now has Seatbelt/bubblewrap + a network proxy natively; Codex
   has its own sandbox + approvals. This compresses the *single-vendor,
   single-dev* market to ~zero willingness-to-pay. It is *why* the
   product must be cross-vendor fleet governance, not local agent
   safety.
 2. **Northflank is converging from the infra side.** It already ships
   dedicated egress gateways + proxy-based secret injection + BYOC.
   It is the nearest thing to bot-bottle's differentiator as a managed
   platform — but infra-first and agent-neutral, not agent-aware,
   cross-vendor, or audit-first. Watch it.
 ## Monetization path (sequenced)
 Open-core: **give away the sandbox, charge for the control plane.**
 - **Phase 0 — validate (1–2 wks, parallel).** Ask 5–10 teams running 2+
  agents: would you pay for one egress-audit + policy plane across
  Claude *and* Codex? Gate the rest on a yes.
 - **Phase 1 — the wedge (self-hostable, OSS).** Multi-bottle egress
  dashboard + web approval queue + exportable audit log, built over the
  existing `supervise_server.py` JSON-RPC and the egress event levels
  (`LOG_BLOCKS` / `LOG_FULL`). Low risk, half-built, and the 30-second
  demo that sells everything. The compliance hook (75% of enterprises
  rank auditability #1) lives here.
 - **Phase 2 — the paywall (hosted team tier).** Multi-tenant supervisor:
  SSO/RBAC, audit retention, alerting, **centralized policy push**
  (define egress allowlist + DLP once, enforce across all agents —
  the moat made concrete). Gate on team/compliance features, *never* on
  the core security.
 - **Phase 3 — Fly remote backend.** Managed agent pool → "fleet" becomes
  literal; metered (agent-hours) billing; subsumes remote spin-up +
  tunnel.
 - **Phase 4 — deepen.** Second agent provider done deeply (lean
  open-source/open-weight for rug-pull resistance); egress anomaly
  detection (the DLP stream becomes a product); SOC2/audit-export for
  larger buyers.
 **Do not build first:** the p2p mobile app (least monetizable, 6PN
 gives the tunnel free), a generic multi-cloud abstraction (premature),
 or the hosted SaaS before Phase 0.
 ## Brand vs. revenue: the solo-dev / Linux instinct
 The instinct to court Linux/hacker/solo-dev users and stay "not too
 corporate" is **right for distribution, dangerous as strategy.**
 - **Right:** it's how OSS infra gets discovered and trusted (HN, stars,
  word-of-mouth, security-circle vouching); authenticity is a real moat
  vs. the corporate players *because the architecture sincerely embodies
  it* (local-first, `$HOME` trust boundary, no phone-home); and it fits
  the founder.
 - **Dangerous:** that audience is the lowest-WTP cohort that exists
  (self-hosts the free thing, forks rather than pays), and "not too
  corporate" reads to a VP of Eng as "not enterprise-ready." Building an
  anti-SaaS brand and then shipping a paid tier invites the sell-out /
  rug-pull backlash — which **Daytona just triggered** going closed.
 **Resolution — be Tailscale, not a manifesto.** Use the developer-first,
 respects-you energy as the *funnel*; sell *through* the solo advocate,
 bottom-up, into the team that pays. Two guardrails:
 1. "Anti-corporate" must not mean "anti-team-features." SSO/RBAC/audit
   retention *are* the monetization; build them in a developer-respecting
   way (Tailscale has SSO and is still beloved). Tone is the brand; team
   features are the product.
 2. Set the open-core social contract publicly **on day one** — core
   sandbox open and self-hostable forever; hosted control plane is how
   the lights stay on. The communities that don't revolt are the ones
   told the deal upfront.
 Concrete: the README frames the Docker/**Linux** backend as "legacy."
 If courting the Linux crowd, make the Linux path (Docker+gVisor,
 libkrun/smolmachines) first-class in the docs, not the fallback.
 ## Individuals, mobile, and the Pi-ecosystem reality check
 "Individual devs won't pay" (above) is too blunt and needs refining.
 The accurate claim: individuals won't pay for **safety-as-insurance**
 (abstract risk reduction the labs give away free), but they *do* pay for
 **capability/convenience felt daily** — Claude Pro, Cursor, Tailscale
 Personal. "Drive my self-hosted agent from my phone" is capability, not
 insurance, so it has a real (low-priced, high-churn) WTP profile. The
 self-hoster/Linux crowd specifically pays for **sovereignty/control**,
 just not for enterprise insurance. So an individual "sovereign remote
 agent access" tier is *not* unreasonable in principle.
 **But the market has already run that experiment, in public, for free.**
 The Pi ecosystem (pi.dev) has commoditized every convenience layer an
 individual product would charge for:
 | Capability | Already free/OSS | bot-bottle differentiates? |
 | :-- | :-- | :-- |
 | Remote control from mobile | remote-pi, Paseo, TelePi | ❌ commoditized |
 | Multi-agent orchestration from mobile | Paseo, pi-agent-dashboard | ❌ commoditized |
 | **Launch** new agents from mobile | Paseo (`paseo run`) | ❌ commoditized |
 | Launch into a **sandboxed, egress-audited** env | nobody | ✅ the moat |
 Paseo (`getpaseo/paseo`, on the App Store) does the full thing an
 individual remote-control tier would charge for — launch *and* attach
 agents on a laptop/VM/dev-server, driven from mobile over an E2E relay —
 free and open source. It *orchestrates* agents; it does **not** sandbox them, run
 an egress chokepoint, DLP-scan, or audit. None of the Pi-ecosystem tools
 do. So the residue, yet again, is **isolation + governance**, not
 remote/launch convenience.
 Two takeaways:
 1. **Don't compete on orchestration/launch/remote UX** — it's a solved,
   free, fast-moving, App-Store-shipping space around Pi. You won't win
   it and it isn't the moat.
 2. **Be the safe runtime orchestrators launch *into*.** Launch-from-mobile
   is table stakes; *launch-into-a-sealed-egress-audited-bottle* is the
   differentiator. bot-bottle is the sandbox an orchestrator like Paseo
   would target, or that you wrap thin orchestration around — never the
   orchestrator itself.
 Capability layers commoditize fast: every individual/mobile angle
 probed in this analysis collapsed back to the same cross-vendor +
 sandbox + egress-audit + custody bundle. Mobile remote belongs as a
 *funnel delighter* on top of the team product, not a standalone paid
 line.
 ## Forge-native orchestration as the delivery vehicle
 The strongest concrete *product shape* for the moat is not a bespoke
 dashboard and not a Paseo competitor — it is **the git forge as the
 orchestrator, with bot-bottle as the safe runtime it launches into.**
 The forge already provides, for free, everything an orchestrator would
 otherwise have to build: identity (agent/bot users, signed commits),
 state (issues, labels, PRs/MRs, comments), triggers (webhooks, CI,
 comment commands), review (diffs, approvals, status checks), audit
 (commits/comments/reviews), and permissions (repo access, protected
 branches, token scopes). bot-bottle supplies the one thing the forge
 doesn't: **least-privilege, secret-isolated, audited execution of
 untrusted agents.** Same moat (custody + audit + policy), better
 vehicle — and it lands the product where teams already live, so it
 avoids building an agent dashboard before one is needed.
 The flow is essentially free to assemble:
 ```
 issue/PR/MR event → webhook → policy/router → assign agent user +
 branch/worktree → run agent in an isolated bottle (no ambient secrets)
 → commit as agent identity → open PR/MR → CI + human review + merge
 ```
 **Crowding (why this is less saturated than it looks):**
 | Layer | How crowded |
 | :-- | :-- |
 | Generic multi-agent orchestrators (worktree/TUI/dashboard) | very — 50–100+ |
 | Forge-native issue/PR/MR orchestration | moderate — ~10–30 serious |
 | Self-hostable, least-privilege, audited, forge-portable | **single digits** |
 The deeper you go toward *untrusted-agent safety + auditability +
 self-hostable + forge-portable*, the emptier it gets.
 **The GitHub/GitLab first-party trap → lead Gitea + sovereignty.**
 GitHub (Agentic Workflows, Copilot coding agent) and GitLab (Duo Agent
 Platform) are the forge *vendors* building native issue-to-PR agent
 orchestration with native identity/permissions/audit. On their turf you
 lose the integration-depth battle the same way single-vendor agent
 safety loses to Anthropic/OpenAI — the same "incumbent ships it free,
 deeper" dynamic, one layer up. So the durable opening is **Gitea +
 self-hosted** (no first-party agent platform exists — the open Gitea
 feature request for an AI code agent confirms the vacuum) plus
 **cross-forge *untrusted-agent* safety**, which no forge vendor will
 build because they want you running *their* agent, not arbitrary ones
 under uniform least-privilege across competitors' forges. Cross-vendor
 neutrality, applied to forges.
 **Buyer reconciliation.** The least-crowded opening (self-hosted Gitea)
 overlaps the lowest-WTP crowd (indie self-hosters), while the paying
 teams sit on GitHub/GitLab where first-party competition is fiercest.
 The intersection that resolves it: **orgs running self-hosted forges for
 sovereignty/compliance reasons** (regulated, air-gapped, security-
 conscious, on-prem). They have budget, they run self-hosted GitLab/Gitea,
 *and* shipping code to a cloud agent vendor is a non-starter — so "run
 untrusted agents sandboxed, least-privilege, fully audited, inside our
 forge, on our infra" is a procurement checkbox, not a nicety. That is
 where "least-crowded" finally meets "has money."
 **Separate moat-hard-parts from cost-hard-parts.** The orchestration
 "hard parts" are two different things, and conflating them oversells the
 fit:
 | Moat (your differentiated strength) | Undifferentiated cost (everyone faces) |
 | :-- | :-- |
 | permission isolation | idempotency / dedupe / run ledger |
 | secret handling under malicious prompts | concurrency, locks, cancellation |
 | run provenance | queueing / scheduling / cleanup |
 | policy language | merge-conflict handling (~27% agent-PR conflict rate) |
 The right column is generic distributed-systems plumbing that wins you
 nothing and that merge-conflict resolution especially is a *different
 competency* from sandbox/custody. Keep it thin in the MVP; do not build a
 policy DSL + durable ledger + conflict resolver before one org pays.
 **The killer feature: run provenance on every agent PR.** A check/comment
 answering — which agent, which model, which prompt, which base commit,
 which policy, which tools, which network egress, which test results —
 attached at the moment a human reviews. It renders the (invisible)
 custody + egress-audit work as a PR artifact the buyer sees at the exact
 trust-decision point. No forge vendor's first-party agent will show you
 "here is everything the untrusted agent could reach." Build this first.
 **MVP** (`@bot-bottle fix this`): create an isolated worktree/bottle →
 check out the issue branch → run the selected harness as a named agent
 user → deny ambient secrets by default → record prompt/model/tools/policy
 → commit with bot identity → open PR/MR → attach the run-provenance
 footer (log + tests + permission/egress summary) → require human merge.
 The security model *is* the product. This rides the headless launch
 primitive directly: webhook → `start --headless` into an isolated bottle
 → commit as agent identity → PR with provenance.
 Open-core line, refined in the next section: the trigger *convention*
 (label/assignee) stays open so anyone can adopt it, but the
 **orchestrator that receives webhooks and governs lifecycle is the paid
 control plane**; the runtime — and a signed-provenance emission API —
 stay free.
 ## The open/paid boundary, refined: orchestrator as the paid control plane
 The forge-native shape sharpens the open-core line past the rough
 "trigger free, execution paid" cut above. Working it through four
 constraints — value capture, provenance integrity, the sovereignty
 buyer, and what the forge *structurally cannot do* — yields a precise
 boundary.
 **The orchestrator is the control plane, and the control plane is the
 paid product.** With the forge supplying identity / state / triggers /
 review, bot-bottle's orchestrator (`bot-bottle-orchestrator`, already
 specced as a separate binary in the forge-native PRD) is where webhooks
 land and bottle lifecycle + governance live. That binary can stay
 **closed/private from day one** without breaking the open-core contract:
 the runtime stays OSS; the control plane is how the lights stay on. This
 is "give away the sandbox, charge for the control plane" made literal —
 the orchestrator *is* the control plane.
 **Charge for the moat, not the webhook.** Holding webhooks and managing
 bottle lifecycle is commodity — the forge vendors build it first-party,
 and it's the "undifferentiated cost" column above (idempotency, queueing,
 dispatch). If the pitch is "we catch the webhook," they out-build it
 free. The paid value is the two things the forge *cannot* do:
 1. **See inside the run** — which model / prompt / policy / tools / egress
   produced the diff, whether a secret nearly left. Runtime-level data
   only the bottle holds.
 2. **Aggregate and enforce across runs** — retain / search / export every
   run across every repo; push one egress/DLP/capability policy
   fleet-wide and detect drift.
 The explainable heuristic: **anything legible within a single run on a
 single node is free; anything requiring cross-run aggregation, central
 enforcement, or identity/fleet management is paid.** That is also the
 individual-vs-team line — individuals live in single runs, teams need the
 aggregate.
 **Provenance: emit free (signed), sell the product.** The forge is the
 wrong system of record for provenance — a markdown footer is mutable by
 any maintainer, unsigned, per-PR, with no aggregation, so a maintainer
 could simply edit it. The authoritative record therefore lives in the
 (paid) control plane. The *runtime* emits **signed** provenance through a
 **free API** — tamper-evident offline (edit it and the signature breaks;
 verify with no server), so on-prem teams can route it into their own
 SIEM. What's paid is the *product* over that stream: retention, search,
 cross-run, export, policy. Whether a copy also lands in the PR footer is
 an optional, off-by-default marketing dial — one consumer of the free
 API, not a free provenance surface, and never the audit record. The
 mutability "bug" becomes a paid feature: the control plane flags *"PR
 footer edited / doesn't match the signed run."* (Prometheus model:
 `/metrics` is free to scrape; managed retention + dashboards are the
 business.)
 **On-prem priority: self-hosted runners over self-hosted provenance.**
 The sovereignty buyer's *hard structural constraint* is where the agent
 **executes** against private code, secrets, and network — that's the
 runner, and it cannot leave the perimeter. Audit metadata is softer; many
 regulated orgs ship logs to SaaS while keeping the workload inside. So:
 - Self-hosted **runner** = baseline, always, for that buyer.
 - Self-hosted **provenance store** = premium tier of the strictest subset
  (air-gapped, hard data-residency) — and largely covered by the free
  emission API → their own SIEM, so it may never need to be a product you
  build.
 - Precision so you don't trip your own free tier: a single self-hosted
  runner *is the OSS runtime on their box* — free. What's paid is the
  **fleet control plane**: enrolling/managing many runners, central
  policy push, dispatch/identity/quota, health/scaling. You don't sell
  "a runner," you sell **running a governed fleet**.
 **Resulting tiers:**
 | Layer | What it is | Open/Paid | Deployment |
 | :-- | :-- | :-- | :-- |
 | **Runtime** | isolation + ephemeral bottles, cred-proxy, supervise, `start --headless`, signed-provenance emission API | Free / OSS | Always self-host |
 | **Single runner** | the OSS runtime on a box | Free / OSS | Self-host |
 | **Control plane** | cross-run audit retention/search/export, central policy push, SSO/RBAC dispatch, fleet management of runners, alerting | **Paid** | Hosted *or* self-host-licensed — same code |
 | **Capacity** | managed Fly runner pool, metered (agent-hours) | **Paid add-on** | Hosted only |
 Fly stays a **capacity/convenience line, not the moat** — it monetizes
 even solo hackers (capability, not insurance), but a managed runner pool
 is reselling compute against Fly/E2B/Northflank on price. It's a bundle
 attached to the governance, never the thing defended. Self-host is *not*
 a separate product: on-prem buyers get the same closed control plane,
 licensed, pointed at their own runners.
 ## Risks to the thesis
 - **Lab encroachment.** If Anthropic/OpenAI add cross-agent governance
  or open their managed egress logs, the wedge narrows. Mitigate by
  going deep on cross-vendor + custody + audit *now*, while they're
  single-vendor.
 - **Rug-pull dependency.** You run the labs' agents; they can restrict
  their agent to their own sandbox via ToS/tech. Hedge toward
  open-source/open-weight agents for durability.
 - **Northflank (or E2B) ships agent-aware audit.** Plausible from the
  infra side. Your defense is agent-awareness + the supervise approval
  loop + cross-vendor, not raw egress visibility.
 - **WTP may simply not be there.** The honest failure mode: teams like
  the audit but won't pay because "we already sandbox in CI." Phase 0
  exists to find this out cheaply before building Phase 2/3.
 - **Forge-vendor encroachment (forge-native path).** GitHub Agentic
  Workflows / Copilot and GitLab Duo are first-party and deepening.
  Defense: aim at self-hosted Gitea + sovereignty buyers where no
  first-party agent platform exists, and at cross-forge untrusted-agent
  neutrality the vendors won't build. Don't fight them GitHub-native.
 - **Orchestration-reliability scope creep.** The forge-native build
  drags in idempotency, queueing, concurrency, and merge-conflict
  handling — undifferentiated plumbing that isn't the moat. Keep it thin
  until a paying org forces it.
 ## Recommendation
 Build Phase 1 now — it's low-risk, half-built, and the proof artifact.
 Run Phase 0 in parallel. Treat a clear yes from 5–10 teams as the
 green light for the hosted tier; treat a soft maybe as a signal to stay
 an excellent OSS tool with a tip-jar/support model rather than a
 venture-shaped SaaS. The technology is not the risk — the codebase is
 exemplary and the architecture already supports the pivot. The risk is
 **positioning discipline**: sell cross-vendor fleet governance to teams,
 use the indie brand as the funnel, and never let the anti-corporate
 aesthetic veto the features that pay.
 ## Sources
 - Anthropic — Claude Code sandboxing:
  https://www.anthropic.com/engineering/claude-code-sandboxing
 - OpenAI Codex — cloud environments:
  https://developers.openai.com/codex/cloud/environments ;
  custom-image feature request:
  https://community.openai.com/t/feature-request-custom-docker-images/1265333
 - GitHub Copilot — custom container image (not supported), discussion
  #194105: https://github.com/orgs/community/discussions/194105
 - DeepInspect — AI egress monitoring:
  https://www.deepinspect.ai/blog/ai-egress-monitoring
 - Braintrust — AI agent observability/alerting:
  https://www.braintrust.dev/articles/best-ai-agent-observability-tools-2026
 - E2B (OSS, Apache-2.0): https://github.com/e2b-dev/e2b ;
  infra/self-host: https://github.com/e2b-dev/infra
 - Daytona going closed source:
  https://www.daytona.io/dotfiles/updates/daytona-is-going-closed-source
 - Northflank — BYOC / egress gateways:
  https://northflank.com/blog/what-is-byoc-in-cloud-computing ;
  https://northflank.com/blog/self-hostable-alternatives-to-e2b-for-ai-agents
 - Modal Sandboxes: https://modal.com/products/sandboxes
 - AI agent orchestration / enterprise governance (75% cite
  auditability):
  https://viston.tech/ai-agent-orchestration-in-2026-moving-from-pilots-to-enterprise-wide-execution/
 - Pi harness (provider-agnostic CLI): https://pi.dev/packages/remote-pi ;
  https://github.com/earendil-works/pi
 - Paseo (launch + attach agents from desktop/mobile, OSS):
  https://github.com/getpaseo/paseo ;
  https://apps.apple.com/us/app/paseo-remote-coding-agents/id6758887924
 - pi-agent-dashboard (mobile-first remote control via mDNS/zrok):
  https://github.com/BlackBeltTechnology/pi-agent-dashboard
 - TelePi (Telegram remote control for Pi):
  https://futurelab.studio/blog/telepi-telegram-remote-control-for-pi/
 - Forge-native landscape (provided via conversation, not independently
  re-verified):
  - awesome-agent-orchestrators (50+ generic orchestrators):
    https://github.com/andyrewlee/awesome-agent-orchestrators
  - GitHub Agentic Workflows (first-party repo automation):
    https://github.blog/ai-and-ml/automate-repository-tasks-with-github-agentic-workflows/
  - GitLab Duo Agent Platform GA:
    https://ir.gitlab.com/news/news-details/2026/GitLab-Announces-the-General-Availability-of-GitLab-Duo-Agent-Platform/default.aspx
  - ai-review (cross-forge review incl. Gitea):
    https://github.com/Nikita-Filonov/ai-review
  - Gitea feature request — AI code agent (the vacuum):
    https://github.com/go-gitea/gitea/issues/34527
  - Phoenix — safe GitHub issue resolution (label-based webhook state
    machine): https://arxiv.org/abs/2606.20243
  - AgenticFlict — ~27% merge-conflict rate in agent PRs:
    https://arxiv.org/abs/2604.03551
@@ -0,0 +1,75 @@
 """Unit: `cli.py resume --headless` non-interactive rehydrate path.
 The freeze / rehydrate loop needs a non-interactive `resume`: deliver a
 follow-up prompt and skip the y/N preflight, reusing the same launch
 core (`assume_yes` + `headless_prompt_text`) as `start --headless`.
 """
 from __future__ import annotations
 import unittest
 from typing import Any
 from unittest.mock import MagicMock, patch
 import bot_bottle.cli.resume as resume_mod
 from bot_bottle.log import Die
 def _metadata():
    md = MagicMock()
    md.agent_name = "implementer"
    md.copy_cwd = False
    md.cwd = "/repo"
    md.identity = "implementer-abc12"
    md.bottle_names = ["claude"]
    md.backend = "docker"
    return md
 class ResumeHeadlessTest(unittest.TestCase):
    def setUp(self) -> None:
        self._launch = patch.object(
            resume_mod, "_launch_bottle", return_value=0
        ).start()
        patch.object(
            resume_mod, "read_metadata", return_value=_metadata()
        ).start()
        manifest = MagicMock()
        manifest.require_agent = MagicMock(return_value=None)
        patch.object(
            resume_mod.ManifestIndex, "resolve", return_value=manifest
        ).start()
        self.addCleanup(patch.stopall)
    def _launch_kwargs(self) -> dict[str, Any]:
        self._launch.assert_called_once()
        return dict(self._launch.call_args.kwargs)
    def test_headless_passes_assume_yes_and_prompt(self):
        rc = resume_mod.cmd_resume(
            ["implementer-abc12", "--headless", "--prompt", "Address the review"]
        )
        self.assertEqual(0, rc)
        kwargs = self._launch_kwargs()
        self.assertTrue(kwargs["assume_yes"])
        self.assertEqual("Address the review", kwargs["headless_prompt_text"])
    def test_interactive_resume_unchanged(self):
        resume_mod.cmd_resume(["implementer-abc12"])
        kwargs = self._launch_kwargs()
        self.assertFalse(kwargs["assume_yes"])
        self.assertEqual("", kwargs["headless_prompt_text"])
    def test_headless_without_prompt_errors(self):
        with self.assertRaises(Die):
            resume_mod.cmd_resume(["implementer-abc12", "--headless"])
        self._launch.assert_not_called()
    def test_prompt_without_headless_errors(self):
        with self.assertRaises(Die):
            resume_mod.cmd_resume(["implementer-abc12", "--prompt", "hi"])
        self._launch.assert_not_called()
 if __name__ == "__main__":
    unittest.main()
@@ -0,0 +1,188 @@
 """Unit: `cli.py start --headless` non-interactive launch path.
 Headless is the keystone for orchestrators, CI, and webhook
 dispatch: agent/bottles/label come from flags + manifest defaults, no
 TUI selectors fire, and the preflight y/N is auto-confirmed
 (`assume_yes=True`). All actual launch work is stubbed so no container
 is created.
 """
 from __future__ import annotations
 import os
 import unittest
 from unittest.mock import MagicMock, patch
 import bot_bottle.cli.start as start_mod
 import bot_bottle.cli.tui as tui_mod
 from bot_bottle.backend import ActiveAgent
 from bot_bottle.log import Die
 from bot_bottle.manifest import ManifestError
 def _make_manifest(
    agent_names: list[str],
    bottle_names: list[str] | None = None,
    agent_bottle: str = "",
 ):
    manifest = MagicMock()
    manifest.agents = {name: MagicMock(bottle=agent_bottle) for name in agent_names}
    manifest.all_agent_names = sorted(agent_names)
    manifest.all_bottle_names = sorted(bottle_names or [])
    manifest.home_md = None  # eager mode so _peek_agent_bottle uses agents dict
    manifest.require_agent = MagicMock(return_value=None)
    return manifest
 def _active_agent(slug: str) -> ActiveAgent:
    return ActiveAgent(
        backend_name="docker",
        slug=slug,
        agent_name="demo",
        started_at="2026-01-01T00:00:00+00:00",
        services=(),
    )
 class TestCmdStartHeadless(unittest.TestCase):
    """Drive `cmd_start --headless` with launch + TUI stubbed out."""
    def setUp(self):
        self._manifest = _make_manifest(
            ["researcher", "implementer"], ["claude", "dev"], agent_bottle="claude"
        )
        patch(
            "bot_bottle.cli.start.ManifestIndex.resolve",
            return_value=self._manifest,
        ).start()
        self._launch_mock = patch(
            "bot_bottle.cli.start._launch_bottle", return_value=0
        ).start()
        # No bottles running by default → no label collision.
        patch(
            "bot_bottle.cli.start.enumerate_active_agents", return_value=[]
        ).start()
        # If any TUI picker fires in headless mode, that's a bug.
        self._agent_picker = patch.object(tui_mod, "filter_select").start()
        self._bottle_picker = patch.object(tui_mod, "filter_multiselect").start()
        self._modal = patch.object(tui_mod, "name_color_modal").start()
        patch.dict(os.environ, {}, clear=False).start()
        os.environ.pop("BOT_BOTTLE_BACKEND", None)
        self.addCleanup(patch.stopall)
    def _spec(self):
        self._launch_mock.assert_called_once()
        return self._launch_mock.call_args[0][0]
    # -- no TUI in headless --------------------------------------------
    def test_headless_fires_no_pickers(self):
        rc = start_mod.cmd_start(
            ["--headless", "researcher", "--bottle", "claude", "--prompt", "Do it"]
        )
        self.assertEqual(0, rc)
        self._agent_picker.assert_not_called()
        self._bottle_picker.assert_not_called()
        self._modal.assert_not_called()
    def test_headless_assume_yes_forwarded(self):
        start_mod.cmd_start(
            ["--headless", "researcher", "--bottle", "claude", "--prompt", "Do it"]
        )
        self.assertTrue(self._launch_mock.call_args[1]["assume_yes"])
    # -- prompt --------------------------------------------------------
    def test_headless_without_prompt_dies(self):
        with self.assertRaises(Die):
            start_mod.cmd_start(["--headless", "researcher", "--bottle", "claude"])
        self._launch_mock.assert_not_called()
    def test_headless_prompt_forwarded_to_launch(self):
        start_mod.cmd_start(
            ["--headless", "researcher", "--bottle", "claude",
             "--prompt", "Implement issue #42"]
        )
        self.assertEqual(
            "Implement issue #42",
            self._launch_mock.call_args[1]["headless_prompt_text"],
        )
    # -- bottle resolution ---------------------------------------------
    def test_explicit_bottles_forwarded_in_order(self):
        start_mod.cmd_start(
            ["--headless", "researcher", "--bottle", "dev", "--bottle", "claude",
             "--prompt", "Do it"]
        )
        self.assertEqual(("dev", "claude"), self._spec().bottle_names)
    def test_omitted_bottle_falls_back_to_agent_default(self):
        start_mod.cmd_start(["--headless", "implementer", "--prompt", "Do it"])
        self.assertEqual(("claude",), self._spec().bottle_names)
    def test_no_bottle_and_no_default_dies(self):
        manifest = _make_manifest(["researcher"], ["claude"], agent_bottle="")
        with patch(
            "bot_bottle.cli.start.ManifestIndex.resolve", return_value=manifest
        ):
            with self.assertRaises(Die):
                start_mod.cmd_start(
                    ["--headless", "researcher", "--prompt", "Do it"]
                )
        self._launch_mock.assert_not_called()
    # -- agent resolution ----------------------------------------------
    def test_missing_agent_name_dies(self):
        with self.assertRaises(Die):
            start_mod.cmd_start(["--headless"])
        self._launch_mock.assert_not_called()
    def test_unknown_agent_raises_manifest_error(self):
        self._manifest.require_agent.side_effect = ManifestError("agent 'x' not defined")
        with self.assertRaises(ManifestError):
            start_mod.cmd_start(
                ["--headless", "x", "--bottle", "claude", "--prompt", "Do it"]
            )
        self._launch_mock.assert_not_called()
    # -- label / color -------------------------------------------------
    def test_label_defaults_to_agent_name(self):
        start_mod.cmd_start(
            ["--headless", "researcher", "--bottle", "claude", "--prompt", "Do it"]
        )
        self.assertEqual("researcher", self._spec().label)
    def test_explicit_label_and_color_forwarded(self):
        start_mod.cmd_start(
            ["--headless", "researcher", "--bottle", "claude",
             "--label", "nightly", "--color", "green", "--prompt", "Do it"]
        )
        spec = self._spec()
        self.assertEqual("nightly", spec.label)
        self.assertEqual("green", spec.color)
    def test_label_collision_uniquifies(self):
        with patch(
            "bot_bottle.cli.start.enumerate_active_agents",
            return_value=[_active_agent("researcher")],
        ):
            start_mod.cmd_start(
                ["--headless", "researcher", "--bottle", "claude", "--prompt", "Do it"]
            )
        self.assertEqual("researcher-2", self._spec().label)
    # -- backend wiring ------------------------------------------------
    def test_backend_flag_forwarded(self):
        start_mod.cmd_start(
            ["--headless", "--backend=docker", "researcher", "--bottle", "claude",
             "--prompt", "Do it"]
        )
        self.assertEqual("docker", self._launch_mock.call_args[1]["backend_name"])
 if __name__ == "__main__":
    unittest.main()
@@ -343,5 +343,14 @@ class TestClaudeSuperviseMcp(unittest.TestCase):
        )
 class TestClaudeHeadlessPrompt(unittest.TestCase):
    def test_returns_p_flag_and_prompt(self):
        self.assertEqual(["-p", "Do the task"], ClaudeAgentProvider().headless_prompt("Do the task"))
    def test_preserves_prompt_text_verbatim(self):
        text = "Fix issue #42: the widget breaks on empty input"
        self.assertEqual(["-p", text], ClaudeAgentProvider().headless_prompt(text))
 if __name__ == "__main__":
    unittest.main()
@@ -314,5 +314,14 @@ class TestCodexSuperviseMcp(unittest.TestCase):
        )
 class TestCodexHeadlessPrompt(unittest.TestCase):
    def test_returns_prompt_as_positional_arg(self):
        self.assertEqual(["Do the task"], CodexAgentProvider().headless_prompt("Do the task"))
    def test_preserves_prompt_text_verbatim(self):
        text = "Fix issue #42: the widget breaks on empty input"
        self.assertEqual([text], CodexAgentProvider().headless_prompt(text))
 if __name__ == "__main__":
    unittest.main()
@@ -0,0 +1,107 @@
 """Unit: Forge abstraction + ScopedForge (PRD forge-native-integration)."""
 from __future__ import annotations
 import unittest
 from bot_bottle.contrib.forge.base import (
    Comment,
    Forge,
    ForgeScopeError,
    Issue,
    PullRequest,
    ScopedForge,
 )
 class _RecordingForge(Forge):
    """In-memory fake that records writes."""
    def __init__(self) -> None:
        self.comments: list[tuple[int, str]] = []
        self.descriptions: list[tuple[int, str]] = []
    def read_issue(self, number: int) -> Issue:
        return Issue(number=number, title="t", body="b", state="open")
    def read_pr(self, number: int) -> PullRequest:
        return PullRequest(
            number=number, title="pr", body="b", state="open", merged=False
        )
    def read_comments(self, number: int) -> list[Comment]:
        return [Comment(id=1, user="alice", body="hi")]
    def post_comment(self, number: int, body: str) -> None:
        self.comments.append((number, body))
    def update_description(self, number: int, body: str) -> None:
        self.descriptions.append((number, body))
    def is_org_member(self, org: str, username: str) -> bool:
        return username == "member"
    def get_pr_for_issue(self, number: int) -> int | None:
        return 99 if number == 17 else None
    def is_pr_open(self, number: int) -> bool:
        return True
 class TestScopedForgeReads(unittest.TestCase):
    def setUp(self) -> None:
        self.inner = _RecordingForge()
        self.scoped = ScopedForge(self.inner, assigned_issue=17, assigned_prs=[42])
    def test_reads_pass_through_to_any_number(self):
        # A number well outside the writable scope still reads fine.
        self.assertEqual(123, self.scoped.read_issue(123).number)
        self.assertEqual("alice", self.scoped.read_comments(500)[0].user)
    def test_read_pr_passes_through(self):
        pr = self.scoped.read_pr(999)
        self.assertIsInstance(pr, PullRequest)
        self.assertEqual(999, pr.number)
        self.assertFalse(pr.merged)
    def test_membership_and_pr_lookups_delegate(self):
        self.assertTrue(self.scoped.is_org_member("bot-bottle", "member"))
        self.assertFalse(self.scoped.is_org_member("bot-bottle", "stranger"))
        self.assertEqual(99, self.scoped.get_pr_for_issue(17))
        self.assertTrue(self.scoped.is_pr_open(8000))
 class TestScopedForgeWrites(unittest.TestCase):
    def setUp(self) -> None:
        self.inner = _RecordingForge()
        self.scoped = ScopedForge(self.inner, assigned_issue=17, assigned_prs=[42])
    def test_writable_set_is_issue_plus_prs(self):
        self.assertEqual(frozenset({17, 42}), self.scoped.writable)
    def test_write_to_assigned_issue_allowed(self):
        self.scoped.post_comment(17, "done")
        self.assertEqual([(17, "done")], self.inner.comments)
    def test_write_to_assigned_pr_allowed(self):
        self.scoped.update_description(42, "new body")
        self.assertEqual([(42, "new body")], self.inner.descriptions)
    def test_comment_outside_scope_rejected(self):
        with self.assertRaises(ForgeScopeError) as ctx:
            self.scoped.post_comment(500, "spam")
        self.assertIn("500", str(ctx.exception))
        self.assertEqual([], self.inner.comments)
    def test_description_outside_scope_rejected(self):
        with self.assertRaises(ForgeScopeError):
            self.scoped.update_description(500, "tamper")
        self.assertEqual([], self.inner.descriptions)
    def test_scope_error_is_permission_error(self):
        # Sidecars can catch the stdlib base type.
        self.assertIn(PermissionError, ForgeScopeError.__mro__)
 if __name__ == "__main__":
    unittest.main()
@@ -0,0 +1,145 @@
 """Unit: GiteaClient + GiteaForge (PRD forge-native-integration)."""
 from __future__ import annotations
 import json
 import unittest
 import urllib.error
 from io import BytesIO
 from unittest.mock import MagicMock, patch
 from bot_bottle.contrib.gitea.client import GiteaClient, GiteaForge
 def _client() -> GiteaClient:
    return GiteaClient(
        api_url="https://gitea.example.com/api/v1",
        owner="didericis",
        repo="bot-bottle",
        token="test-token",
    )
 def _resp(body: object, status: int = 200) -> MagicMock:
    resp = MagicMock()
    resp.read.return_value = json.dumps(body).encode() if body is not None else b""
    resp.status = status
    resp.__enter__ = lambda s: s  # type: ignore
    resp.__exit__ = MagicMock(return_value=False)
    return resp
 def _http_error(code: int, body: str = "") -> urllib.error.HTTPError:
    return urllib.error.HTTPError(
        url="http://x", code=code, msg="err", hdrs=None,  # type: ignore[arg-type]
        fp=BytesIO(body.encode()),
    )
 _URLOPEN = "bot_bottle.contrib.gitea.client.urllib.request.urlopen"
 class TestOrgMembership(unittest.TestCase):
    def test_member_returns_true_on_2xx(self):
        with patch(_URLOPEN, return_value=_resp(None, 204)) as m:
            self.assertTrue(_client().is_org_member("bot-bottle", "alice"))
        req = m.call_args.args[0]
        self.assertIn("/orgs/bot-bottle/members/alice", req.full_url)
    def test_nonmember_returns_false_on_404(self):
        with patch(_URLOPEN, side_effect=_http_error(404)):
            self.assertFalse(_client().is_org_member("bot-bottle", "stranger"))
    def test_other_http_error_raises(self):
        with patch(_URLOPEN, side_effect=_http_error(403, "forbidden")):
            with self.assertRaises(RuntimeError) as ctx:
                _client().is_org_member("bot-bottle", "alice")
        self.assertIn("403", str(ctx.exception))
 class TestForgeReads(unittest.TestCase):
    def test_read_issue_maps_fields(self):
        raw = {"number": 17, "title": "Bug", "body": "broken", "state": "open"}
        with patch(_URLOPEN, return_value=_resp(raw)) as m:
            issue = GiteaForge(_client()).read_issue(17)
        self.assertEqual((17, "Bug", "broken", "open"),
                         (issue.number, issue.title, issue.body, issue.state))
        self.assertIn("/repos/didericis/bot-bottle/issues/17",
                      m.call_args.args[0].full_url)
    def test_read_issue_tolerates_null_body(self):
        raw = {"number": 17, "title": "T", "body": None, "state": "open"}
        with patch(_URLOPEN, return_value=_resp(raw)):
            self.assertEqual("", GiteaForge(_client()).read_issue(17).body)
    def test_read_comments_maps_user_login(self):
        raw = [
            {"id": 1, "user": {"login": "alice"}, "body": "hi"},
            {"id": 2, "user": {"login": "bob"}, "body": "yo"},
        ]
        with patch(_URLOPEN, return_value=_resp(raw)):
            comments = GiteaForge(_client()).read_comments(17)
        self.assertEqual(["alice", "bob"], [c.user for c in comments])
        self.assertEqual([1, 2], [c.id for c in comments])
 class TestForgeWrites(unittest.TestCase):
    def test_post_comment_payload_and_url(self):
        with patch(_URLOPEN, return_value=_resp(None, 201)) as m:
            GiteaForge(_client()).post_comment(17, "done ✓")
        req = m.call_args.args[0]
        self.assertEqual("POST", req.method)
        self.assertIn("/repos/didericis/bot-bottle/issues/17/comments", req.full_url)
        self.assertEqual("done ✓", json.loads(req.data)["body"])
    def test_update_description_patches_issue(self):
        with patch(_URLOPEN, return_value=_resp(None, 200)) as m:
            GiteaForge(_client()).update_description(17, "edited")
        req = m.call_args.args[0]
        self.assertEqual("PATCH", req.method)
        self.assertTrue(req.full_url.endswith("/issues/17"))
        self.assertEqual("edited", json.loads(req.data)["body"])
    def test_auth_header_sent(self):
        with patch(_URLOPEN, return_value=_resp(None, 201)) as m:
            GiteaForge(_client()).post_comment(17, "x")
        self.assertEqual("token test-token",
                         m.call_args.args[0].headers["Authorization"])
 class TestPRHelpers(unittest.TestCase):
    def test_get_pr_for_issue_returns_number_when_issue_is_pr(self):
        raw = {"number": 18, "pull_request": {"merged": False}}
        with patch(_URLOPEN, return_value=_resp(raw)):
            self.assertEqual(18, GiteaForge(_client()).get_pr_for_issue(18))
    def test_get_pr_for_issue_none_for_plain_issue(self):
        raw = {"number": 17, "pull_request": None}
        with patch(_URLOPEN, return_value=_resp(raw)):
            self.assertIsNone(GiteaForge(_client()).get_pr_for_issue(17))
    def test_is_pr_open_true_when_state_open(self):
        with patch(_URLOPEN, return_value=_resp({"state": "open"})):
            self.assertTrue(GiteaForge(_client()).is_pr_open(18))
    def test_is_pr_open_false_when_closed(self):
        with patch(_URLOPEN, return_value=_resp({"state": "closed"})):
            self.assertFalse(GiteaForge(_client()).is_pr_open(18))
    def test_read_pr_maps_fields_including_merged(self):
        raw = {"number": 18, "title": "Fix", "body": "patch",
               "state": "closed", "merged": True}
        with patch(_URLOPEN, return_value=_resp(raw)) as m:
            pr = GiteaForge(_client()).read_pr(18)
        self.assertEqual((18, "Fix", "patch", "closed", True),
                         (pr.number, pr.title, pr.body, pr.state, pr.merged))
        self.assertIn("/repos/didericis/bot-bottle/pulls/18",
                      m.call_args.args[0].full_url)
    def test_read_pr_merged_defaults_false(self):
        with patch(_URLOPEN, return_value=_resp({"number": 18, "state": "open"})):
            self.assertFalse(GiteaForge(_client()).read_pr(18).merged)
 if __name__ == "__main__":
    unittest.main()
@@ -0,0 +1,99 @@
 """Unit: SQLite forge state store (PRD forge-native-integration)."""
 from __future__ import annotations
 import tempfile
 import unittest
 from dataclasses import replace
 from pathlib import Path
 from bot_bottle.contrib.gitea.forge_state import (
    STATUS_FROZEN,
    STATUS_RUNNING,
    ForgeState,
    SqliteForgeStateStore,
 )
 def _state(**over: object) -> ForgeState:
    base = ForgeState(
        owner="didericis",
        repo="bot-bottle",
        issue_number=17,
        slug="implementer-abc12",
        agent_name="implementer",
        bottle_names=["claude"],
        backend_name="docker",
        agent_git_user="didericis-claude",
        pr_number=42,
        status=STATUS_FROZEN,
        last_checkin_at="2026-06-29T12:04:12-04:00",
    )
    return replace(base, **over)
 class ForgeStateStoreTest(unittest.TestCase):
    def setUp(self) -> None:
        tmp = Path(self.enterContext(tempfile.TemporaryDirectory()))  # pylint: disable=consider-using-with
        self.store = SqliteForgeStateStore(tmp / "sub" / "bot-bottle.db")
    def test_round_trip(self):
        self.store.upsert(_state())
        self.assertEqual(_state(), self.store.get("didericis", "bot-bottle", 17))
    def test_missing_returns_none(self):
        self.assertIsNone(self.store.get("nobody", "nope", 1))
    def test_creates_db_parent_dirs(self):
        # setUp pointed at a non-existent 'sub/' dir; init must create it.
        self.assertIsNone(self.store.get("x", "y", 1))  # no raise
    def test_upsert_replaces(self):
        self.store.upsert(_state(status=STATUS_RUNNING))
        self.store.upsert(_state(status=STATUS_FROZEN))
        got = self.store.get("didericis", "bot-bottle", 17)
        assert got is not None
        self.assertEqual(STATUS_FROZEN, got.status)
        # Still one row, not two.
        self.assertEqual(1, len(self.store.all()))
    def test_delete_is_idempotent(self):
        self.store.upsert(_state())
        self.store.delete("didericis", "bot-bottle", 17)
        self.store.delete("didericis", "bot-bottle", 17)  # no raise
        self.assertIsNone(self.store.get("didericis", "bot-bottle", 17))
    def test_all_lists_across_repos_sorted(self):
        self.store.upsert(_state(issue_number=18, slug="other"))
        self.store.upsert(_state(issue_number=17))
        self.store.upsert(_state(owner="acme", repo="widget", issue_number=3))
        states = self.store.all()
        self.assertEqual(3, len(states))
        self.assertEqual(
            [("acme", 3), ("didericis", 17), ("didericis", 18)],
            [(s.owner, s.issue_number) for s in states],
        )
    def test_all_empty(self):
        self.assertEqual([], self.store.all())
    def test_bottle_names_list_preserved(self):
        self.store.upsert(_state(bottle_names=["claude", "dev"]))
        got = self.store.get("didericis", "bot-bottle", 17)
        assert got is not None
        self.assertEqual(["claude", "dev"], got.bottle_names)
    def test_pr_number_nullable(self):
        self.store.upsert(_state(pr_number=None))
        got = self.store.get("didericis", "bot-bottle", 17)
        assert got is not None
        self.assertIsNone(got.pr_number)
    def test_persists_across_store_instances(self):
        self.store.upsert(_state())
        reopened = SqliteForgeStateStore(self.store._db_path)  # pylint: disable=protected-access
        self.assertEqual(_state(), reopened.get("didericis", "bot-bottle", 17))
 if __name__ == "__main__":
    unittest.main()
@@ -223,5 +223,14 @@ class TestPiDockerfile(unittest.TestCase):
        self.assertIn("chmod 1777 /tmp /var/tmp", dockerfile)
 class TestPiHeadlessPrompt(unittest.TestCase):
    def test_returns_p_flag_and_prompt(self):
        self.assertEqual(["-p", "Do the task"], PiAgentProvider().headless_prompt("Do the task"))
    def test_preserves_prompt_text_verbatim(self):
        text = "Fix issue #42: the widget breaks on empty input"
        self.assertEqual(["-p", text], PiAgentProvider().headless_prompt(text))
 if __name__ == "__main__":
    unittest.main()
@@ -38,6 +38,7 @@ class _Provider(AgentProvider):
    def provision_prompt(self, plan, bottle): ...  # type: ignore[override]
    def provision(self, plan, bottle): ...  # type: ignore[override]
    def provision_supervise_mcp(self, plan, bottle, supervise_url): ...  # type: ignore[override]
    def headless_prompt(self, prompt): return []  # type: ignore[override]
 _PROVIDER = _Provider()
@@ -49,6 +49,7 @@ class _Provider(AgentProvider):
    def provision_prompt(self, plan, bottle): ...  # type: ignore[override]
    def provision(self, plan, bottle): ...  # type: ignore[override]
    def provision_supervise_mcp(self, plan, bottle, supervise_url): ...  # type: ignore[override]
    def headless_prompt(self, prompt): return []  # type: ignore[override]
 _PROVIDER = _Provider()
Author	SHA1	Message	Date
didericis	42004d37fd	refactor(forge): address PR #318 review — PR/Issue split, sqlite state, drop footer lint / lint (push) Successful in 1m59s Details test / unit (pull_request) Successful in 48s Details test / integration (pull_request) Successful in 17s Details test / coverage (pull_request) Successful in 58s Details Addresses the five review comments on PR #318: - Split PullRequest from Issue and add a dedicated read_pr method on Forge/ScopedForge/GiteaForge (a PR carries merge state an issue does not); is_pr_open now derives from read_pr. - Replace the JSON-file forge state with a thin swappable CRUD interface (ForgeStateStore) backed by SQLite (SqliteForgeStateStore) at ~/.bot-bottle/bot-bottle.db. - Remove the provenance footer (provenance.py + its test): a mutable, unsigned PR comment is not an audit record. - Reword the PRD: provenance is exposed via an API, not surfaced in the PR; document the Issue/PullRequest split and the SQLite store. pyright clean (whole repo), pylint 10/10, 38 forge/resume unit tests pass; no remaining refs to the removed provenance module or old JSON state API. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WL77TgFxKbs3cidGMG9dz7	2026-07-01 08:37:25 -04:00
didericis	f211ece6bf	fix(tests): resolve pyright strict errors in forge test helpers lint / lint (push) Successful in 2m18s Details test / unit (pull_request) Successful in 1m1s Details test / integration (pull_request) Successful in 22s Details test / coverage (pull_request) Successful in 1m19s Details CI runs `pyright .` over the whole repo including tests; the earlier run only checked the source paths. The test helpers used `over` dict-splat into typed constructors, which pyright strict rejects. - forge_state: build a typed ForgeState base and dataclasses.replace(over) - provenance: explicit typed keyword params instead of a **over dict - resume: _launch_kwargs returns dict[str, Any] (copy call_args.kwargs) - forge_base: assert PermissionError in __mro__ (avoids always-true issubclass) - client: annotate _resp body param; type: ignore the mock __enter__ lambda pyright . now 0 errors; 47 tests still pass; pylint 9.97/10. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WL77TgFxKbs3cidGMG9dz7	2026-07-01 07:58:55 -04:00
didericis	a229a22d54	feat(forge): forge library layer for native integration (PRD chunks 1-3, 5) lint / lint (push) Failing after 2m9s Details test / unit (pull_request) Successful in 58s Details test / integration (pull_request) Successful in 21s Details test / coverage (pull_request) Successful in 1m23s Details Implements the bot-bottle side of the forge-native PRD that is self-contained in this repo (the forge sidecar and orchestrate command belong to the separate bot-bottle-orchestrator, a PRD non-goal): - contrib/forge/base.py: Forge ABC + ScopedForge enforcing the read-anywhere / write-scoped model (writes rejected outside the assigned issue/PRs via ForgeScopeError). - contrib/gitea/client.py: GiteaClient (stdlib-only HTTP, mirrors the deploy-key provisioner) + GiteaForge. Token held by the caller (the sidecar), not injected by cred-proxy. - contrib/gitea/forge_state.py: ForgeState dataclass + atomic read/write/delete/all under ~/.bot-bottle/forge/<owner>/<repo>/. - contrib/gitea/provenance.py: build_provenance_footer — collapsed markdown audit footer; watchdog/gitleaks/egress rendering. - cli/resume.py: `resume --headless --prompt` reusing the shipped assume_yes + headless_prompt launch core (the new half of chunk 1). 47 new unit tests; pylint 9.98/10, pyright clean. Forge sidecar (chunk 4), orchestrate command (chunk 6), and forge_env plumbing are deferred: their only consumer is the separate orchestrator and they are untestable in isolation here. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WL77TgFxKbs3cidGMG9dz7	2026-06-30 19:39:49 -04:00
didericis	738990b2df	Merge remote-tracking branch 'origin/main' into forge-native-integration	2026-06-30 19:19:01 -04:00
didericis	4cb106b48d	docs(prd): reconcile headless primitives with shipped start --headless #315 already merged `start --headless` (assume_yes on _launch_bottle + AgentProvider.headless_prompt). The PRD's proposed start_headless / attach_agent_headless helpers were redundant with it, and the latter diverged by hand-rolling --no-interactive/-p instead of using the headless_prompt provider abstraction. Drop them. Scope the remaining headless work to what's actually new: a forge_env hook threaded into the existing _launch_bottle core, and a `resume --headless` path (resume has no non-interactive entry point today). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WL77TgFxKbs3cidGMG9dz7	2026-06-30 17:46:59 -04:00
didericis	ebad90bfa9	docs(prd): adopt forge sidecar (option 3) for native integration Flip the forge-native-integration PRD from option 2 (agent calls the Gitea API directly via cred-proxy; done signal parsed from comments) to option 3 per issue #317 comment 2715: a forge sidecar backed by a Forge abstract class. - signal_done(status, summary) replaces comment-parsing as the done signal - semantic audit trail from the sidecar feeds provenance directly - read-anywhere / write-scoped enforcement, tighter than repo-wide API keys - forge-agnostic agent prompts and sidecar protocol - DeployKeyProvisioner subsumption deferred; share the HTTP client only Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WL77TgFxKbs3cidGMG9dz7	2026-06-30 17:39:33 -04:00
didericis	b93fe58523	feat(cli): add headless launch mode for orchestrators test / unit (pull_request) Successful in 47s Details test / integration (pull_request) Successful in 16s Details test / coverage (pull_request) Successful in 1m4s Details lint / lint (push) Successful in 2m0s Details test / unit (push) Successful in 48s Details test / integration (push) Successful in 18s Details test / coverage (push) Successful in 57s Details Update Quality Badges / update-badges (push) Successful in 57s Details `--headless` is a non-interactive launch path for `cli.py start`: agent, bottles, label, and color come from flags + manifest defaults with no TUI selectors and no y/N preflight (auto-confirmed via a new `assume_yes` param threaded into the shared `_launch_bottle` core). - `--bottle` (repeatable) defaults to the agent's own `bottle:`; `--label` defaults to the agent name and auto-uniquifies on slug collision; `--color` defaults to none. - `--prompt TEXT` is required in headless mode and is delivered to the agent via a new `headless_prompt(prompt)` method on `AgentProvider`, implemented for claude (`-p`), codex (positional), and pi (`-p`). - The agent still execs on inherited stdio/PTY, so whatever allocates the PTY drives the live session; only the launch chrome is headless. - `--headless --dry-run` previews the resolved plan without launching. Adds unit coverage in tests/unit/test_cli_start_headless.py and headless_prompt tests for each provider. Also stubs headless_prompt on the in-test AgentProvider subclasses so the unit suite collects cleanly. Closes #315. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WL77TgFxKbs3cidGMG9dz7	2026-06-30 15:08:14 -04:00
didericis-claude	1789deaf73	docs: update forge PRD — orchestrator split, done signal, org targeting, forge env vars	2026-06-29 12:39:02 -04:00
didericis-claude	b607d68a0e	docs: add PRD for forge native integration	2026-06-29 12:10:41 -04:00