merge: update tests/unit/test_supervise_server.py from issue-277-coverage-ci

`container build` resolves -f relative to the current working directory,
not the build context, so builds failed from any cwd other than the repo
root. Anchor a relative Dockerfile to the context before passing it.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.coveragerc

@@ -0,0 +1,9 @@
+[run]
+branch = True
+source = .
+
+[report]
+omit =
+    bot_bottle/egress_addon.py
+    bot_bottle/cli/tui.py
+    tests/*

.gitea/workflows/test.yml

@@ -39,8 +39,14 @@ jobs:
         with:
           python-version: "3.12"
 
+      - name: Install dev requirements
+        run: python3 -m pip install -r requirements-dev.txt
+
       - name: Run unit tests
-        run: python3 -m unittest discover -t . -s tests/unit -v
+        run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
+
+      - name: Report unit coverage
+        run: python3 -m coverage report -m
 
   integration:
     runs-on: ubuntu-latest

.gitignore

@@ -22,3 +22,4 @@ venv/
 .pytest_cache/
 .mypy_cache/
 .ruff_cache/
+.coverage

bot_bottle/backend/__init__.py

@@ -72,9 +72,6 @@ class BottleSpec:
     identity: str = ""
     label: str = ""
     color: str = ""
-    # Ordered bottle names selected at launch (issue #269). When non-empty
-    # they are merged in order and replace the agent's `bottle:` field.
-    bottle_names: tuple[str, ...] = ()
 
 
 @dataclass(frozen=True)
@@ -132,11 +129,7 @@ class BottlePlan(ABC):
         info(f"provider        : {self.agent_provision.template}")
         print_multi("env             ", env_names)
         print_multi("skills          ", list(agent.skills))
-        effective_bottles = (
-            list(spec.bottle_names) if spec.bottle_names
-            else ([agent.bottle] if agent.bottle else [])
-        )
-        print_multi("bottle          ", effective_bottles)
+        info(f"bottle          : {agent.bottle}")
 
         identity = manifest.git_identity_summary()
         if identity:
@@ -370,7 +363,7 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         Returns the loaded Manifest for the selected agent. Subclasses with
         additional preconditions should override and call
         `super()._validate(spec)` first."""
-        manifest = spec.manifest.load_for_agent(spec.agent_name, spec.bottle_names)
+        manifest = spec.manifest.load_for_agent(spec.agent_name)
         self._validate_skills(manifest.agent.skills)
         self._validate_agent_provider_dockerfile(spec, manifest)
         return manifest
@@ -396,12 +389,9 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         if not path.is_absolute():
             path = Path(spec.user_cwd) / path
         if not path.is_file():
-            effective = (
-                ", ".join(spec.bottle_names) if spec.bottle_names else manifest.agent.bottle
-            )
             die(
                 f"agent_provider.dockerfile for bottle "
-                f"'{effective}' not found: {path}"
+                f"'{manifest.agent.bottle}' not found: {path}"
             )
 
     @abstractmethod

bot_bottle/backend/macos_container/util.py

@@ -68,6 +68,11 @@ def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
     _ensure_builder_dns()
     args = [_CONTAINER, "build", "-t", ref, "--dns", dns_server()]
     if dockerfile:
+        # `container build` resolves -f relative to the current working
+        # directory, not the build context. Anchor a relative Dockerfile to
+        # the context so builds work from any cwd.
+        if not os.path.isabs(dockerfile):
+            dockerfile = os.path.join(context, dockerfile)
         args.extend(["-f", dockerfile])
     args.append(context)
     subprocess.run(args, check=True)

bot_bottle/backend/resolve_common.py

@@ -63,7 +63,6 @@ def write_launch_metadata(
         backend=backend,
         label=spec.label,
         color=spec.color,
-        bottle_names=spec.bottle_names,
     ))
 
 

bot_bottle/bottle_state.py

@@ -112,10 +112,6 @@ class BottleMetadata:
     backend: str = ""
     label: str = ""
     color: str = ""
-    # Ordered bottle names selected at launch (issue #269). Empty tuple
-    # for state dirs written before this change; resume falls back to
-    # the agent's `bottle:` field in that case.
-    bottle_names: tuple[str, ...] = ()
 
 
 def metadata_path(identity: str) -> Path:
@@ -143,10 +139,6 @@ def read_metadata(identity: str) -> BottleMetadata | None:
     if not isinstance(raw, dict):
         return None
     raw_typed = cast(dict[str, object], raw)
-    raw_bottle_names = raw_typed.get("bottle_names", [])
-    bottle_names: tuple[str, ...] = ()
-    if isinstance(raw_bottle_names, list):
-        bottle_names = tuple(str(n) for n in raw_bottle_names if isinstance(n, str))
     return BottleMetadata(
         identity=str(raw_typed.get("identity", identity)),
         agent_name=str(raw_typed.get("agent_name", "")),
@@ -157,7 +149,6 @@ def read_metadata(identity: str) -> BottleMetadata | None:
         backend=str(raw_typed.get("backend", "")),
         label=str(raw_typed.get("label", "")),
         color=str(raw_typed.get("color", "")),
-        bottle_names=bottle_names,
     )
 
 

bot_bottle/cli/resume.py

@@ -50,7 +50,6 @@ def cmd_resume(argv: list[str]) -> int:
         copy_cwd=metadata.copy_cwd,
         user_cwd=metadata.cwd or USER_CWD,
         identity=metadata.identity,
-        bottle_names=tuple(metadata.bottle_names),
     )
     backend_name = metadata.backend or None
     return _launch_bottle(

bot_bottle/cli/start.py

@@ -74,20 +74,6 @@ def cmd_start(argv: list[str]) -> int:
 
     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
-    initial_bottle = _peek_agent_bottle(manifest, agent_name)
-    initial_bottles = [initial_bottle] if initial_bottle else []
-    selected_bottles = tui.filter_multiselect(
-        available_bottles,
-        title="Select bottles",
-        initial=initial_bottles,
-    )
-    if selected_bottles is None:
-        return 0
-    bottle_names = tuple(selected_bottles)
-
     label, color = tui.name_color_modal(default_label=agent_name)
     label, color = _resolve_unique_label(label, color)
 
@@ -98,7 +84,6 @@ def cmd_start(argv: list[str]) -> int:
         user_cwd=USER_CWD,
         label=label,
         color=color,
-        bottle_names=bottle_names,
     )
     return _launch_bottle(
         spec,
@@ -205,38 +190,6 @@ def _identity_from_plan(plan: object) -> str:
     return getattr(plan, "slug", "")
 
 
-def _peek_agent_bottle(manifest: ManifestIndex, agent_name: str) -> str:
-    """Return the `bottle:` value from the named agent's frontmatter without
-    fully parsing the agent file, or "" when absent or unreadable.
-
-    Used to pre-populate the bottle multiselect with the agent's default
-    bottle so operators who haven't removed `bottle:` from their manifests
-    don't need to re-select it every time."""
-    if manifest.home_md is None:
-        # Eager mode (from_json_obj): agent is pre-parsed.
-        if agent_name in manifest.agents:
-            return manifest.agents[agent_name].bottle
-        return ""
-
-    from ..manifest_loader import scan_agent_names
-    from ..yaml_subset import YamlSubsetError, parse_frontmatter
-
-    home_agents = scan_agent_names(manifest.home_md / "agents")
-    cwd_agents: dict[str, Path] = {}
-    if manifest.cwd_md is not None:
-        cwd_agents = scan_agent_names(manifest.cwd_md / "agents")
-    merged = {**home_agents, **cwd_agents}
-    path = merged.get(agent_name)
-    if path is None:
-        return ""
-    try:
-        fm, _ = parse_frontmatter(path.read_text())
-        bottle = fm.get("bottle", "")
-        return str(bottle) if isinstance(bottle, str) else ""
-    except (OSError, YamlSubsetError):
-        return ""
-
-
 def _resolve_unique_label(label: str, color: str) -> tuple[str, str]:
     """Re-prompt with a disclaimer until the label's slug is not already
     in use among running bottles.  Passes through unchanged when no

bot_bottle/cli/supervise.py

@@ -2,9 +2,8 @@
 act on them (approve / modify / reject).
 
 Curses-based TUI; modify-then-approve shells out to $EDITOR. The
-approval handler wires to PRD 0016 (capability-block), which rebuilds
-the bottle Dockerfile. Egress proposals are queued for operator review
-as full routes.yaml updates.
+Egress proposals are queued for operator review as full routes.yaml
+updates.
 """
 
 from __future__ import annotations
@@ -22,10 +21,6 @@ from pathlib import Path
 
 from .. import supervise as _supervise
 from ..bottle_state import read_metadata
-# from ..backend.docker.capability_apply import (
-#     CapabilityApplyError,
-#     apply_capability_change,
-# )
 from ..backend.docker.egress_apply import (
     EgressApplyError,
     applicator as _docker_applicator,
@@ -38,10 +33,6 @@ from ..backend.smolmachines.egress_apply import (
 )
 from ..log import Die, error, info
 
-
-class CapabilityApplyError(RuntimeError):
-    """Placeholder while capability_apply is disabled."""
-
 from ..supervise import (
     COMPONENT_FOR_TOOL,
     AuditEntry,
@@ -50,12 +41,10 @@ from ..supervise import (
     STATUS_APPROVED,
     STATUS_MODIFIED,
     STATUS_REJECTED,
-    TOOL_CAPABILITY_BLOCK,
     TOOL_EGRESS_ALLOW,
     TOOL_EGRESS_BLOCK,
     TOOL_GITLEAKS_ALLOW,
     TOOL_EGRESS_TOKEN_ALLOW,
-    archive_proposal,
     list_pending_proposals,
     render_diff,
     write_audit_entry,
@@ -83,7 +72,7 @@ class QueuedProposal:
 # Errors any remediation engine may raise. Caught by the TUI key
 # handlers and surfaced in the status line so a failed apply keeps
 # the proposal pending rather than crashing curses.
-ApplyError = (CapabilityApplyError, EgressApplyError)
+ApplyError = (EgressApplyError,)
 
 
 def apply_routes_change(slug: str, content: str) -> tuple[str, str]:
@@ -143,8 +132,6 @@ def _detail_lines(
 
 
 def _suffix_for_tool(tool: str) -> str:
-    if tool == TOOL_CAPABILITY_BLOCK:
-        return ".dockerfile"
     if tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
         return ".yaml"
     if tool in (TOOL_GITLEAKS_ALLOW, TOOL_EGRESS_TOKEN_ALLOW):
@@ -166,17 +153,6 @@ def approve(
     file_to_apply = final_file if final_file is not None else qp.proposal.proposed_file
 
     diff_before, diff_after = "", ""
-    # if qp.proposal.tool == TOOL_CAPABILITY_BLOCK:
-    #     _meta = read_metadata(qp.proposal.bottle_slug)
-    #     if _meta is not None and not _meta.compose_project:
-    #         raise CapabilityApplyError(
-    #             "capability-block remediation is not supported for smolmachines "
-    #             "bottles. Reject this proposal or handle the capability change "
-    #             "manually, then restart the bottle."
-    #         )
-    #     diff_before, diff_after = apply_capability_change(
-    #         qp.proposal.bottle_slug, file_to_apply,
-    #     )
     if qp.proposal.tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
         diff_before, diff_after = apply_routes_change(
             qp.proposal.bottle_slug,
@@ -194,9 +170,6 @@ def approve(
         qp, action=status, notes=notes,
         diff_before=diff_before, diff_after=diff_after,
     )
-    if qp.proposal.tool == TOOL_CAPABILITY_BLOCK:
-        archive_proposal(qp.queue_dir, qp.proposal.id)
-
 
 def reject(qp: QueuedProposal, *, reason: str) -> None:
     """Write a rejection response and an audit entry."""
@@ -346,7 +319,7 @@ def _list_once() -> int:
     return 0
 
 
-def _try_init_green() -> int:
+def _try_init_green() -> int:  # pragma: no cover
     """Initialise a green color pair and return its attr, or 0."""
     try:
         curses.start_color()
@@ -357,7 +330,7 @@ def _try_init_green() -> int:
         return 0
 
 
-def _main_loop(stdscr: "curses._CursesWindow") -> None:  # type: ignore
+def _main_loop(stdscr: "curses._CursesWindow") -> None:  # type: ignore  # pragma: no cover
     curses.curs_set(0)
     stdscr.timeout(_REFRESH_INTERVAL_MS)
     green_attr = _try_init_green()
@@ -447,7 +420,7 @@ def _render(
     status_line: str,
     *,
     green_attr: int = 0,  # noqa: F841 — unused, but required by interface
-) -> None:
+) -> None:  # pragma: no cover
     stdscr.erase()
     h, w = stdscr.getmaxyx()
     header = f"bot-bottle supervise  ({len(pending)} pending)"
@@ -498,7 +471,7 @@ def _detail_view(
     qp: QueuedProposal,
     *,
     green_attr: int = 0,
-) -> None:
+) -> None:  # pragma: no cover
     """Render the full proposal. Scrollable. Press q to return."""
     lines = _detail_lines(qp, green_attr=green_attr)
     offset = 0
@@ -550,7 +523,7 @@ def _detail_view(
             return
 
 
-def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None:  # type: ignore
+def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None:  # type: ignore  # pragma: no cover
     """Suspend curses, open $EDITOR on the proposed file, return edited content."""
     suffix = _suffix_for_tool(qp.proposal.tool)
     curses.endwin()
@@ -561,7 +534,7 @@ def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None:
     return edited
 
 
-def _prompt(stdscr: "curses._CursesWindow", label: str) -> str:  # type: ignore
+def _prompt(stdscr: "curses._CursesWindow", label: str) -> str:  # type: ignore  # pragma: no cover
     """One-line input at the bottom of the screen."""
     curses.curs_set(1)
     h, _ = stdscr.getmaxyx()

bot_bottle/cli/tui.py

@@ -17,42 +17,6 @@ import sys
 from typing import Any, Optional
 
 
-def filter_multiselect(
-    items: list[str],
-    *,
-    title: str = "",
-    initial: Optional[list[str]] = None,
-    tty_path: str = "/dev/tty",
-) -> Optional[list[str]]:
-    """Render a multi-select picker over *items*.
-
-    Returns the ordered list of selected items, or ``None`` if the user
-    cancelled (Esc / ``q`` / Ctrl-C / Ctrl-D with no items).
-
-    Press Space or Enter to toggle the item under the cursor.
-    Press Ctrl-D to confirm the current selection (returns even if empty).
-    Press Esc/q to cancel (returns None).
-
-    *initial* pre-populates the selection in insertion order. Items
-    added are appended; removed items leave the remaining order unchanged.
-    """
-    if not items:
-        return []
-
-    try:
-        tty_fd = open(tty_path, "r+b", buffering=0)
-    except OSError:
-        return None
-
-    try:
-        fd_dup = os.dup(tty_fd.fileno())
-        return _run_multiselect(
-            items, title=title, initial=list(initial or []), tty_fd=fd_dup
-        )
-    finally:
-        tty_fd.close()
-
-
 def filter_select(
     items: list[str],
     *,
@@ -257,258 +221,6 @@ def _addstr_safe(screen: Any, row: int, col: int, text: str, attr: int = curses.
         pass
 
 
-# ---------------------------------------------------------------------------
-# filter_multiselect internals
-# ---------------------------------------------------------------------------
-
-_KEY_SPACE = 32
-
-
-def _run_multiselect(
-    items: list[str], *, title: str, initial: list[str], tty_fd: int
-) -> Optional[list[str]]:
-    """Drive a curses multi-select session on *tty_fd*."""
-    os.environ.setdefault("TERM", "xterm-256color")
-
-    orig_stdin = sys.__stdin__
-    orig_stdout = sys.__stdout__
-
-    try:
-        import io
-        tty_text = io.TextIOWrapper(io.FileIO(tty_fd, mode='r+'), write_through=True)
-        sys.__stdin__ = tty_text   # type: ignore[assignment]
-        sys.__stdout__ = tty_text  # type: ignore[assignment]
-
-        screen = curses.initscr()
-        curses.noecho()
-        curses.cbreak()
-        screen.keypad(True)
-
-        try:
-            result = _multiselect_loop(screen, items, title=title, initial=initial)
-        finally:
-            screen.keypad(False)
-            curses.nocbreak()
-            curses.echo()
-            curses.endwin()
-    except Exception:  # noqa: W0718
-        return None
-    finally:
-        sys.__stdin__ = orig_stdin    # type: ignore[assignment]
-        sys.__stdout__ = orig_stdout  # type: ignore[assignment]
-
-    return result
-
-
-def _multiselect_loop(
-    screen: Any, items: list[str], *, title: str, initial: list[str]
-) -> Optional[list[str]]:
-    query = ""
-    cursor = 0
-    selected: list[str] = [s for s in initial if s in items]
-    # focus = "filter": navigate + toggle items in the filterable list
-    # focus = "order":  navigate + reorder items in the selected list
-    focus = "filter"
-    order_cursor = 0
-
-    while True:
-        filtered = _filter_items(items, query)
-
-        if not filtered:
-            cursor = 0
-        elif cursor >= len(filtered):
-            cursor = len(filtered) - 1
-
-        if not selected:
-            order_cursor = 0
-            if focus == "order":
-                focus = "filter"
-        elif order_cursor >= len(selected):
-            order_cursor = len(selected) - 1
-
-        try:
-            _render_multiselect(
-                screen, filtered, cursor,
-                query=query, title=title, selected=selected,
-                focus=focus, order_cursor=order_cursor,
-            )
-        except curses.error:
-            return None
-
-        try:
-            key = screen.getch()
-        except KeyboardInterrupt:
-            return None
-
-        if key in (_KEY_ESC, _KEY_CTRL_C, ord("q")):
-            return None
-
-        if key == _KEY_CTRL_D:
-            return list(selected)
-
-        # Tab toggles between filter and order focus.
-        if key == ord("\t"):
-            if focus == "filter" and selected:
-                focus = "order"
-                order_cursor = 0
-            else:
-                focus = "filter"
-            continue
-
-        if focus == "filter":
-            if key in (curses.KEY_ENTER, _KEY_ENTER_ALT, ord("\r"), _KEY_SPACE):
-                if filtered:
-                    item = filtered[cursor]
-                    if item in selected:
-                        selected.remove(item)
-                    else:
-                        selected.append(item)
-
-            elif key in (curses.KEY_UP, ord("k")):
-                if cursor > 0:
-                    cursor -= 1
-
-            elif key in (curses.KEY_DOWN, ord("j")):
-                if cursor < len(filtered) - 1:
-                    cursor += 1
-
-            elif key in (curses.KEY_BACKSPACE, _KEY_BACKSPACE_WIN, 127):
-                query = query[:-1]
-                new_filtered = _filter_items(items, query)
-                if cursor >= len(new_filtered):
-                    cursor = max(0, len(new_filtered) - 1)
-
-            elif 32 <= key <= 126 and key != _KEY_SPACE:
-                query += chr(key)
-                cursor = 0
-
-        else:  # focus == "order"
-            if key in (curses.KEY_UP, ord("k")):
-                if order_cursor > 0:
-                    order_cursor -= 1
-
-            elif key in (curses.KEY_DOWN, ord("j")):
-                if order_cursor < len(selected) - 1:
-                    order_cursor += 1
-
-            elif key == ord("K"):
-                # Move selected item up (earlier in order).
-                if order_cursor > 0:
-                    i = order_cursor
-                    selected[i - 1], selected[i] = selected[i], selected[i - 1]
-                    order_cursor -= 1
-
-            elif key == ord("J"):
-                # Move selected item down (later in order).
-                if order_cursor < len(selected) - 1:
-                    i = order_cursor
-                    selected[i], selected[i + 1] = selected[i + 1], selected[i]
-                    order_cursor += 1
-
-            elif key in (curses.KEY_ENTER, _KEY_ENTER_ALT, ord("\r"), _KEY_SPACE):
-                # Remove item from selection while in order mode.
-                del selected[order_cursor]
-                if order_cursor >= len(selected) and order_cursor > 0:
-                    order_cursor -= 1
-
-
-def _render_multiselect(
-    screen: Any,
-    filtered: list[str],
-    cursor: int,
-    *,
-    query: str,
-    title: str,
-    selected: list[str],
-    focus: str = "filter",
-    order_cursor: int = 0,
-) -> None:
-    screen.erase()
-    rows, cols = screen.getmaxyx()
-    min_rows = 7
-
-    if rows < min_rows:
-        raise curses.error("terminal too small")
-
-    sep = "─" * min(cols - 1, 40)
-    row = 0
-
-    if title and row < rows - 1:
-        _addstr_safe(screen, row, 0, title[:cols - 1], curses.A_BOLD)
-        row += 1
-
-    # Filter line — dim when focus is on the order panel.
-    filter_label = f"Filter: {query}"
-    filter_hint = "  [Tab: reorder]" if focus == "filter" and selected else ""
-    filter_attr = curses.A_DIM if focus == "order" else curses.A_NORMAL
-    if row < rows - 1:
-        _addstr_safe(screen, row, 0, (filter_label + filter_hint)[:cols - 1], filter_attr)
-        row += 1
-
-    if row < rows - 1:
-        _addstr_safe(screen, row, 0, sep)
-        row += 1
-
-    # Compute how many rows the bottom order panel needs.
-    # Cap the visible selected list to keep the filter list legible.
-    order_rows = min(len(selected), max(1, (rows - row) // 3)) if selected else 0
-    # Bottom reserved: sep + order_rows + sep + help = order_rows + 3
-    bottom_reserved = order_rows + 3
-
-    list_start = row
-    list_rows = rows - list_start - bottom_reserved
-    if list_rows < 1:
-        list_rows = 1
-
-    selected_set = set(selected)
-    filter_dim = focus == "order"
-    scroll = max(0, cursor - list_rows + 1)
-    visible = filtered[scroll: scroll + list_rows]
-
-    for idx, item in enumerate(visible):
-        abs_idx = scroll + idx
-        mark = "[*]" if item in selected_set else "[ ]"
-        prefix = "> " if (abs_idx == cursor and focus == "filter") else "  "
-        line = (prefix + mark + " " + item)[:cols - 1]
-        item_attr = curses.A_DIM if filter_dim else (
-            curses.A_REVERSE if abs_idx == cursor else curses.A_NORMAL
-        )
-        if row < rows - bottom_reserved:
-            _addstr_safe(screen, row, 0, line, item_attr)
-        row += 1
-
-    # Separator before the order panel.
-    if row < rows - (order_rows + 2):
-        _addstr_safe(screen, row, 0, sep)
-        row += 1
-
-    # Order panel.
-    order_scroll = max(0, order_cursor - order_rows + 1)
-    order_visible = selected[order_scroll: order_scroll + order_rows]
-    for idx, item in enumerate(order_visible):
-        abs_idx = order_scroll + idx
-        is_active = focus == "order" and abs_idx == order_cursor
-        prefix = "> " if is_active else "  "
-        line = (prefix + item)[:cols - 1]
-        attr = curses.A_REVERSE if is_active else curses.A_NORMAL
-        if row < rows - 2:
-            _addstr_safe(screen, row, 0, line, attr)
-        row += 1
-
-    if row < rows - 1:
-        _addstr_safe(screen, row, 0, sep)
-        row += 1
-
-    if focus == "filter":
-        help_line = "[↑↓/jk] move  [Space/Enter] toggle  [Tab] reorder  [Ctrl-D] done  [Esc/q] cancel"
-    else:
-        help_line = "[↑↓/jk] cursor  [K/J] reorder  [Space/Enter] remove  [Tab] back  [Ctrl-D] done"
-    if row < rows:
-        _addstr_safe(screen, min(rows - 1, row), 0, help_line[:cols - 1])
-
-    screen.refresh()
-
-
 # ---------------------------------------------------------------------------
 # name_color_modal — two-step label + color picker
 # ---------------------------------------------------------------------------

bot_bottle/manifest.py

@@ -215,65 +215,6 @@ def _merge_git_user(
     )
 
 
-def _resolve_effective_bottle_eager(
-    agent_name: str,
-    agent: "ManifestAgent",
-    bottle_names: "tuple[str, ...]",
-    bottles: "Mapping[str, ManifestBottle]",
-) -> "ManifestBottle":
-    """Return the effective ManifestBottle for the eager (from_json_obj) path.
-
-    When bottle_names is non-empty they are merged in order. When empty, falls
-    back to agent.bottle. Raises ManifestError when neither is set."""
-    from .manifest_extends import merge_bottles_runtime
-
-    if bottle_names:
-        resolved: list[ManifestBottle] = []
-        for bn in bottle_names:
-            if bn not in bottles:
-                available = ", ".join(sorted(bottles.keys())) or "(none)"
-                raise ManifestError(
-                    f"bottle '{bn}' not defined. Available: {available}"
-                )
-            resolved.append(bottles[bn])
-        return merge_bottles_runtime(resolved)
-
-    if not agent.bottle:
-        raise ManifestError(
-            f"agent '{agent_name}' has no 'bottle' field and no bottles were "
-            f"selected at launch. Select at least one bottle or add "
-            f"'bottle: <name>' to the agent manifest."
-        )
-    return bottles[agent.bottle]
-
-
-def _resolve_effective_bottle_lazy(
-    agent_name: str,
-    agent_bottle: str,
-    bottle_names: "tuple[str, ...]",
-    bottles_dir: "Path",
-) -> "ManifestBottle":
-    """Return the effective ManifestBottle for the lazy (from_md_dirs) path.
-
-    When bottle_names is non-empty they are resolved from disk and merged in
-    order. When empty, falls back to agent_bottle. Raises ManifestError when
-    neither is set."""
-    from .manifest_extends import merge_bottles_runtime
-    from .manifest_loader import load_bottle_chain_from_dir
-
-    if bottle_names:
-        resolved = [load_bottle_chain_from_dir(bn, bottles_dir) for bn in bottle_names]
-        return merge_bottles_runtime(resolved)
-
-    if not agent_bottle:
-        raise ManifestError(
-            f"agent '{agent_name}' has no 'bottle' field and no bottles were "
-            f"selected at launch. Select at least one bottle or add "
-            f"'bottle: <name>' to the agent manifest."
-        )
-    return load_bottle_chain_from_dir(agent_bottle, bottles_dir)
-
-
 @dataclass(frozen=True)
 class Manifest:
     """Single-agent/bottle value type. Returned by ManifestIndex.load_for_agent().
@@ -419,18 +360,6 @@ class ManifestIndex:
         }
         return cls(bottles=bottles, agents=agents)
 
-    @property
-    def all_bottle_names(self) -> list[str]:
-        """Sorted list of all discoverable bottle names.
-
-        In names-only mode (from resolve/from_md_dirs) this scans bottle
-        filenames without reading their content. In eager mode (from
-        from_json_obj) it returns the pre-parsed bottles' names."""
-        if self.home_md is not None:
-            from .manifest_loader import scan_bottle_names
-            return scan_bottle_names(self.home_md / "bottles")
-        return sorted(self.bottles.keys())
-
     @property
     def all_agent_names(self) -> list[str]:
         """Sorted list of all discoverable agent names.
@@ -447,18 +376,9 @@ class ManifestIndex:
             return sorted(home_names | cwd_names)
         return sorted(self.agents.keys())
 
-    def load_for_agent(
-        self,
-        agent_name: str,
-        bottle_names: "tuple[str, ...] | None" = None,
-    ) -> "Manifest":
+    def load_for_agent(self, agent_name: str) -> "Manifest":
         """Parse the named agent and its bottle; return a single-value Manifest.
 
-        `bottle_names` is an ordered list of bottles selected at launch time.
-        When non-empty they are resolved and merged in order (index 0 = base;
-        later entries override). When empty or None, falls back to the agent's
-        own `bottle:` field. Raises ManifestError when neither is set.
-
         In lazy mode (from resolve/from_md_dirs) the agent file and its
         bottle chain are read from disk for the first time here.  In eager
         mode (from_json_obj) the data is already parsed; this just filters
@@ -469,8 +389,6 @@ class ManifestIndex:
 
         Always raises ManifestError if the agent is unknown or invalid.
         Backends call this at preflight inside _validate."""
-        effective_bottle_names: tuple[str, ...] = bottle_names or ()
-
         if self.home_md is None:
             # Eager manifest (from_json_obj): data already parsed; filter to
             # the one requested agent and its bottle so the returned Manifest
@@ -481,14 +399,12 @@ class ManifestIndex:
                     f"agent '{agent_name}' not defined. Available: {available}"
                 )
             agent = self.agents[agent_name]
-            raw_bottle = _resolve_effective_bottle_eager(
-                agent_name, agent, effective_bottle_names, self.bottles
-            )
+            raw_bottle = self.bottles[agent.bottle]
             merged = _merge_git_user(agent.git_user, raw_bottle.git_user)
             bottle = raw_bottle if merged == raw_bottle.git_user else replace(raw_bottle, git_user=merged)
             return Manifest(agent=agent, bottle=bottle)
 
-        from .manifest_loader import scan_agent_names
+        from .manifest_loader import load_bottle_chain_from_dir, scan_agent_names
         from .manifest_schema import validate_agent_frontmatter_keys
         from .yaml_subset import YamlSubsetError, parse_frontmatter
 
@@ -515,31 +431,26 @@ class ManifestIndex:
 
         validate_agent_frontmatter_keys(agent_path, fm.keys())
 
-        # Determine the effective bottle name(s).
-        agent_bottle = fm.get("bottle") or ""
+        bottle_name = fm.get("bottle")
+        if not isinstance(bottle_name, str) or not bottle_name:
+            raise ManifestError(
+                f"agent '{agent_name}' must declare a 'bottle' field "
+                f"naming a defined bottle"
+            )
+
+        # Load the bottle chain (may raise ManifestError).
         bottles_dir = self.home_md / "bottles"
-        raw_bottle = _resolve_effective_bottle_lazy(
-            agent_name, str(agent_bottle), effective_bottle_names, bottles_dir
-        )
-        effective_bottle_name = (
-            effective_bottle_names[-1] if effective_bottle_names
-            else str(agent_bottle)
-        )
+        raw_bottle = load_bottle_chain_from_dir(bottle_name, bottles_dir)
 
         # Build and validate the full ManifestAgent.
         agent_dict: dict[str, object] = {
+            "bottle": bottle_name,
             "skills": fm.get("skills", []),
             "prompt": body.strip(),
         }
-        if agent_bottle:
-            agent_dict["bottle"] = agent_bottle
         if "git-gate" in fm:
             agent_dict["git-gate"] = fm["git-gate"]
-        # Pass the effective bottle name as the known-bottles set so agents
-        # that have bottle: set are validated; agents without bottle: pass {}
-        # since bottle_names were already resolved above.
-        known = {effective_bottle_name} if effective_bottle_name else set()
-        agent = ManifestAgent.from_dict(agent_name, agent_dict, known)
+        agent = ManifestAgent.from_dict(agent_name, agent_dict, {bottle_name})
 
         merged_user = _merge_git_user(agent.git_user, raw_bottle.git_user)
         bottle = raw_bottle if merged_user == raw_bottle.git_user else replace(raw_bottle, git_user=merged_user)

bot_bottle/manifest_agent.py

@@ -109,8 +109,7 @@ class ManifestAgentProvider:
 
 @dataclass(frozen=True)
 class ManifestAgent:
-    # Optional: when empty the operator selects bottles at launch time.
-    bottle: str = ""
+    bottle: str
     skills: tuple[str, ...] = ()
     prompt: str = ""
     # Per-agent git identity (issue #94). Overlays the referenced
@@ -130,20 +129,18 @@ class ManifestAgent:
                 f"allowed keys are {allowed}."
             )
 
-        bottle_raw = d.get("bottle")
-        bottle = ""
-        if bottle_raw is not None:
-            if not isinstance(bottle_raw, str) or not bottle_raw:
-                raise ManifestError(
-                    f"agent '{name}' bottle must be a non-empty string when declared"
-                )
-            if bottle_raw not in bottle_names:
-                available = ", ".join(sorted(bottle_names)) or "(none defined)"
-                raise ManifestError(
-                    f"agent '{name}' references bottle '{bottle_raw}', which is not defined. "
-                    f"Available: {available}"
-                )
-            bottle = bottle_raw
+        bottle = d.get("bottle")
+        if not isinstance(bottle, str) or not bottle:
+            raise ManifestError(
+                f"agent '{name}' must declare a 'bottle' field naming a "
+                f"defined bottle"
+            )
+        if bottle not in bottle_names:
+            available = ", ".join(sorted(bottle_names)) or "(none defined)"
+            raise ManifestError(
+                f"agent '{name}' references bottle '{bottle}', which is not defined. "
+                f"Available: {available}"
+            )
 
         skills: tuple[str, ...] = ()
         skills_raw = d.get("skills")

bot_bottle/manifest_extends.py

@@ -9,58 +9,6 @@ if TYPE_CHECKING:
     from .manifest_egress import ManifestEgressConfig
 
 
-def merge_bottles_runtime(bottles: "list[ManifestBottle]") -> "ManifestBottle":
-    """Merge an ordered list of pre-resolved ManifestBottle objects.
-
-    Index 0 is the base; each subsequent entry is applied on top using
-    the same field-merge rules as the file-based extends machinery:
-      env: dict merge, later wins; git_user: per-field overlay, later
-      wins on non-empty; git (repos): union by name, later wins; egress
-      routes: concatenate; agent_provider, supervise: later replaces.
-    """
-    if not bottles:
-        raise ValueError("merge_bottles_runtime requires at least one bottle")
-    result = bottles[0]
-    for override in bottles[1:]:
-        result = _merge_two_bottles_runtime(result, override)
-    return result
-
-
-def _merge_two_bottles_runtime(base: "ManifestBottle", override: "ManifestBottle") -> "ManifestBottle":
-    from .manifest import ManifestBottle, ManifestGitUser
-    from .manifest_egress import ManifestEgressConfig
-
-    merged_env = {**base.env, **override.env}
-
-    merged_git_user = ManifestGitUser(
-        name=override.git_user.name or base.git_user.name,
-        email=override.git_user.email or base.git_user.email,
-    )
-
-    # git repos: union keyed by Name, override wins per-name.
-    base_repos_by_name = {entry.Name: entry for entry in base.git}
-    override_repos_by_name = {entry.Name: entry for entry in override.git}
-    merged_repos_names = list(base_repos_by_name) + [
-        n for n in override_repos_by_name if n not in base_repos_by_name
-    ]
-    merged_git = tuple(
-        override_repos_by_name.get(n, base_repos_by_name[n])
-        for n in merged_repos_names
-    )
-
-    merged_routes = base.egress.routes + override.egress.routes
-    merged_egress = ManifestEgressConfig(routes=merged_routes, Log=override.egress.Log)
-
-    return ManifestBottle(
-        env=merged_env,
-        agent_provider=override.agent_provider,
-        git=merged_git,
-        git_user=merged_git_user,
-        egress=merged_egress,
-        supervise=override.supervise,
-    )
-
-
 def resolve_bottles(raws: dict[str, dict[str, object]]) -> dict[str, ManifestBottle]:
     """Apply `extends:` chains and return resolved ManifestBottle objects."""
     cache: dict[str, ManifestBottle] = {}

bot_bottle/manifest_loader.py

@@ -32,25 +32,6 @@ def check_stale_json(dir_path: Path, md_dir: Path, label: str) -> None:
         )
 
 
-def scan_bottle_names(bottles_dir: Path) -> list[str]:
-    """Scan `<bottles_dir>/*.md` for valid filenames and return sorted bottle names.
-
-    No file content is read. Invalid filenames are skipped with a warning."""
-    result: list[str] = []
-    if not bottles_dir.is_dir():
-        return result
-    for path in sorted(bottles_dir.glob("*.md")):
-        name = entity_name_from_path(path)
-        if name is None:
-            warn(
-                f"skipping {path}: filename must match "
-                f"[a-z][a-z0-9-]*.md (got {path.name!r})"
-            )
-            continue
-        result.append(name)
-    return result
-
-
 def scan_agent_names(agents_dir: Path) -> dict[str, Path]:
     """Scan `<agents_dir>/*.md` for valid filenames and return `{name: path}`.
 

bot_bottle/manifest_schema.py

@@ -18,8 +18,8 @@ _FILENAME_RX = re.compile(r"^[a-z][a-z0-9-]*$")
 BOTTLE_KEYS = frozenset(
     {"env", "extends", "agent_provider", "git-gate", "egress", "supervise"}
 )
-AGENT_KEYS_REQUIRED: frozenset[str] = frozenset()
-AGENT_KEYS_OPTIONAL = frozenset({"bottle", "skills", "git-gate"})
+AGENT_KEYS_REQUIRED = frozenset({"bottle"})
+AGENT_KEYS_OPTIONAL = frozenset({"skills", "git-gate"})
 
 # Claude Code subagent fields bot-bottle ignores at launch but does
 # not reject. This lets the same file double as

docs/prds/prd-new-separate-agent-bottle-selection.md

@@ -1,216 +0,0 @@
-# PRD prd-new: Separate agent and bottle selection
-
-- **Status:** Active
-- **Author:** claude
-- **Created:** 2026-06-25
-- **Issue:** #269
-
-## Summary
-
-Agents and bottles are two separate concerns: agents carry a system prompt and
-skills; bottles carry infrastructure configuration (egress, git-gate, env,
-agent provider). Today an agent's manifest file hard-codes a single `bottle:`
-reference, which prevents the same agent prompt from being reused across
-projects that need different bottle configurations. This PRD decouples them: at
-launch time, after choosing the agent, the operator picks an ordered list of
-bottles via a multi-select picker. The selected bottles are merged in order
-(later entries override earlier ones) to produce the effective bottle for the
-session.
-
-## Problem
-
-The current `bottle: <name>` field on an agent manifest file binds the agent
-permanently to one bottle. To use the same system prompt with a different bottle
-(e.g. `claude-implementer` at home vs. at a client site that needs a different
-egress policy), the operator must duplicate the agent file and change the
-`bottle:` field. Duplicate agent files drift out of sync.
-
-## Goals / Success Criteria
-
-1. `bottle:` in an agent's frontmatter becomes optional. Existing manifests with
-   `bottle:` continue to work unchanged (backward compat).
-2. After selecting an agent (via the existing single-select picker), a new
-   multi-select bottle picker appears showing all available bottles.
-3. The multi-select picker pre-populates with the agent's `bottle:` value when
-   present.
-4. Confirming with one or more bottles selected uses those bottles, merged in
-   selection order, as the effective bottle for the session.
-5. Confirming with an empty selection falls back to the agent's `bottle:` field.
-   If neither is set, a ManifestError is raised pointing the operator at the fix.
-6. The ordered bottle list is stored in launch metadata so `./cli.py resume`
-   uses the same bottles.
-7. The preflight summary (`y/N` screen) shows the effective bottle name(s).
-8. The multi-select picker supports incremental filtering, Space/Enter to toggle
-   selection, an ordered "Selected: ..." summary line, Ctrl-D to confirm, and
-   Esc/q to cancel the whole start operation.
-9. Unit tests cover: multi-select widget (filter, toggle, confirm, cancel),
-   the `cmd_start` bottle-picker step, and the manifest `load_for_agent`
-   runtime-bottle-merge path.
-
-## Non-goals
-
-- Reordering the selection list from within the picker (order = insertion order;
-  drag-and-drop is out of scope).
-- Storing bottle selection history / MRU.
-- Changes to `./cli.py edit`, `./cli.py list`, or `./cli.py info`.
-- Removing the `bottle:` key from the agent schema (it stays, now optional).
-
-## Design
-
-### `bot_bottle/cli/tui.py` — `filter_multiselect`
-
-```python
-def filter_multiselect(
-    items: list[str],
-    *,
-    title: str = "",
-    initial: list[str] | None = None,
-    tty_path: str = "/dev/tty",
-) -> list[str] | None:
-    """Multi-select variant of filter_select.
-
-    Returns the ordered list of selected items, or None on cancel.
-    Press Space/Enter to toggle the item under the cursor.
-    Press Ctrl-D to confirm. Press Esc/q to cancel.
-    """
-```
-
-Layout:
-
-```
-Select bottles
-Filter: _
-─────────────────────────────────────────
-> [*] claude
-  [ ] dev
-  [ ] codex
-─────────────────────────────────────────
-Selected (in order): claude
-─────────────────────────────────────────
-[↑↓/jk] move  [Space] toggle  [Ctrl-D] done  [Esc] cancel
-```
-
-`initial` pre-populates the ordered selection. `None` means no pre-selection.
-Items added are appended in insertion order; items removed leave the remaining
-order unchanged.
-
-### `bot_bottle/manifest_schema.py` — optional `bottle:`
-
-`bottle` moves from `AGENT_KEYS_REQUIRED` to `AGENT_KEYS_OPTIONAL`.
-
-### `bot_bottle/manifest_agent.py` — optional `bottle:`
-
-`ManifestAgent.bottle` changes from `str` (required) to `str = ""`.
-`from_dict` no longer requires the key to be present; the bottle-exists
-validation is skipped when the key is absent.
-
-### `bot_bottle/manifest_loader.py` — `scan_bottle_names`
-
-```python
-def scan_bottle_names(bottles_dir: Path) -> list[str]:
-    """Scan <bottles_dir>/*.md and return sorted bottle names."""
-```
-
-### `bot_bottle/manifest.py` — `ManifestIndex` changes
-
-**`all_bottle_names` property** — analogous to `all_agent_names`; scans
-`home_md / "bottles"` in lazy mode, returns `sorted(self.bottles.keys())` in
-eager mode.
-
-**`load_for_agent(agent_name, bottle_names: tuple[str, ...] = ())`** — new
-`bottle_names` parameter. When non-empty, the listed bottles are resolved and
-merged in order (index 0 is the base; each subsequent bottle is applied on top
-using the same field-merge rules as `extends:`). The result replaces the bottle
-that `agent.bottle` would have provided. When empty, falls back to `agent.bottle`.
-Raises ManifestError if neither `bottle_names` nor `agent.bottle` is set.
-
-### `bot_bottle/manifest_extends.py` — `merge_bottles_runtime`
-
-```python
-def merge_bottles_runtime(bottles: list[ManifestBottle]) -> ManifestBottle:
-    """Merge an ordered list of pre-resolved ManifestBottle objects.
-
-    Index 0 is the base; each subsequent entry overrides the previous using
-    the same rules as the file-based extends machinery:
-      - env: dict merge, later wins
-      - git_user: per-field overlay, later wins on non-empty
-      - git (repos): union by name, later wins per-name
-      - egress.routes: concatenate
-      - agent_provider, supervise: later bottle's value replaces earlier
-    """
-```
-
-This function operates on already-parsed `ManifestBottle` objects, so it does
-not need to touch the raw-dict path.
-
-### `bot_bottle/backend/__init__.py` — `BottleSpec` + `_validate`
-
-`BottleSpec` gains `bottle_names: tuple[str, ...] = ()`.
-
-`BottleBackend._validate` passes `spec.bottle_names` to `load_for_agent`:
-
-```python
-manifest = spec.manifest.load_for_agent(spec.agent_name, spec.bottle_names)
-```
-
-The preflight print updates `info(f"bottle: {agent.bottle}")` to display the
-effective bottle name(s). When `spec.bottle_names` is non-empty those are
-shown; when empty and `agent.bottle` is set, the agent's `bottle:` is shown.
-
-### `bot_bottle/bottle_state.py` — persist bottle names
-
-`BottleMetadata` gains `bottle_names: tuple[str, ...] = ()`. `read_metadata`
-reads this from JSON (default `()`). `write_launch_metadata` passes
-`spec.bottle_names` through.
-
-### `bot_bottle/cli/start.py` — bottle multiselect step
-
-After agent selection, before the name/color modal:
-
-```python
-available_bottle_names = manifest.all_bottle_names
-# Peek at agent's bottle default for pre-population
-initial_bottle = _peek_agent_bottle(manifest, agent_name)
-initial = [initial_bottle] if initial_bottle else []
-
-bottle_names_list = tui.filter_multiselect(
-    available_bottle_names,
-    title="Select bottles",
-    initial=initial,
-)
-if bottle_names_list is None:
-    return 0  # user cancelled
-bottle_names = tuple(bottle_names_list)
-```
-
-`_peek_agent_bottle` reads the agent file's frontmatter without full parsing,
-returning the `bottle:` value or `""` when absent.
-
-`BottleSpec` is built with `bottle_names=bottle_names`.
-
-### `bot_bottle/cli/resume.py` — bottle names from metadata
-
-```python
-spec = BottleSpec(
-    ...
-    bottle_names=tuple(metadata.bottle_names),
-)
-```
-
-## Implementation chunks
-
-1. **Schema + model** — `manifest_schema.py`, `manifest_agent.py` (optional
-   `bottle:`), `manifest_loader.py` (`scan_bottle_names`), `manifest.py`
-   (`all_bottle_names`, `load_for_agent` signature), `manifest_extends.py`
-   (`merge_bottles_runtime`), `bottle_state.py` (`bottle_names` field),
-   `resolve_common.py` (thread through).
-2. **Backend** — `BottleSpec.bottle_names`, `_validate`, preflight print.
-3. **TUI** — `filter_multiselect` in `tui.py` + unit tests.
-4. **CLI wiring** — `start.py` bottle picker step, `resume.py` metadata load.
-5. **Tests** — `test_cli_start_selector.py` bottle-picker cases,
-   `test_manifest_agent.py` optional-bottle cases, new
-   `test_manifest_bottle_merge.py` for `merge_bottles_runtime`.
-
-## Open questions
-
-None.

requirements-dev.txt

@@ -4,3 +4,4 @@
 
 pylint>=3.0.0
 pyright>=1.1.300
+coverage>=7.0.0

tests/integration/test_sandbox_escape.py

@@ -92,9 +92,9 @@ class TestSandboxEscape(unittest.TestCase):
                     "on PATH: curl -sSL https://smolmachines.com/install.sh | sh"
                 )
 
-        # Throwaway "identity file" for the git-gate's `identity` field.
-        # It need not be a real SSH key: test 5 reaches gitleaks before
-        # any SSH attempt anyway.
+        # Throwaway static key for the git-gate fixture. It need not
+        # be a real SSH key: test 5 reaches gitleaks before any SSH
+        # attempt anyway.
         fd, kp = tempfile.mkstemp(prefix="sandbox-test-key.")
         os.close(fd)
         cls._key_path = Path(kp)
@@ -123,7 +123,10 @@ class TestSandboxEscape(unittest.TestCase):
                     "git-gate": {"repos": {
                         "throwaway": {
                             "url": "ssh://git@unreachable.invalid:22/throwaway.git",
-                            "identity": str(cls._key_path),
+                            "key": {
+                                "provider": "static",
+                                "path": str(cls._key_path),
+                            },
                         },
                     }},
                 },

tests/integration/test_smolmachines_launch.py

@@ -198,6 +198,7 @@ class TestSmolmachinesLaunch(unittest.TestCase):
         # connect fails, which is the property chunk 3 will
         # preserve once egress is actually running.
         r = self.bottle.exec(
+            "env -u HTTPS_PROXY -u HTTP_PROXY -u https_proxy -u http_proxy "
             f"curl -s --show-error --max-time 3 http://{self.plan.bundle_ip}:9099 "
             "2>&1 || true"
         )

tests/unit/test_cli_start_selector.py

@@ -1,8 +1,7 @@
-"""Unit: cmd_start selector dispatch (PRD 0051, issue #269).
+"""Unit: cmd_start selector dispatch (PRD 0051).
 
 Tests that cmd_start calls filter_select only when the agent name is
-absent, shows the bottle multiselect after agent selection, and skips
-pickers when both are explicitly set.
+absent, skips it when the agent is explicit, and returns 0 on cancel.
 
 All actual launch work is stubbed so no container is created.
 """
@@ -18,16 +17,10 @@ import bot_bottle.cli.tui as tui_mod
 from bot_bottle.backend import ActiveAgent
 
 
-def _make_manifest(
-    agent_names: list[str],
-    bottle_names: list[str] | None = None,
-    agent_bottle: str = "",
-):
+def _make_manifest(agent_names: list[str]):
     manifest = MagicMock()
-    manifest.agents = {name: MagicMock(bottle=agent_bottle) for name in agent_names}
+    manifest.agents = {name: MagicMock() 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
     return manifest
 
 
@@ -35,27 +28,27 @@ class TestCmdStartSelector(unittest.TestCase):
     """Drive cmd_start with a minimal set of stubs."""
 
     def setUp(self):
-        self._manifest = _make_manifest(["researcher", "implementer"], ["claude", "dev"])
+        # Stub Manifest.resolve so no on-disk manifest is needed.
+        self._manifest = _make_manifest(["researcher", "implementer"])
         self._resolve_patch = patch(
             "bot_bottle.cli.start.ManifestIndex.resolve",
             return_value=self._manifest,
         )
         self._resolve_patch.start()
 
+        # Stub _launch_bottle so no real container work happens.
         self._launch_patch = patch(
             "bot_bottle.cli.start._launch_bottle",
             return_value=0,
         )
         self._launch_mock = self._launch_patch.start()
 
-        # Stub filter_select (agent picker) and filter_multiselect (bottle picker).
-        self._agent_picker_patch = patch.object(tui_mod, "filter_select")
-        self._agent_picker_mock = self._agent_picker_patch.start()
-
-        self._bottle_picker_patch = patch.object(tui_mod, "filter_multiselect")
-        self._bottle_picker_mock = self._bottle_picker_patch.start()
-        self._bottle_picker_mock.return_value = ["claude"]  # default: one bottle selected
+        # Stub filter_select to avoid opening /dev/tty.
+        self._tui_patch = patch.object(tui_mod, "filter_select")
+        self._tui_mock = self._tui_patch.start()
 
+        # Ensure BOT_BOTTLE_BACKEND is absent so omitted --backend
+        # flows through to the resolver default.
         self._env_patch = patch.dict(os.environ, {}, clear=False)
         self._env_patch.start()
         os.environ.pop("BOT_BOTTLE_BACKEND", None)
@@ -63,108 +56,50 @@ class TestCmdStartSelector(unittest.TestCase):
     def tearDown(self):
         self._resolve_patch.stop()
         self._launch_patch.stop()
-        self._agent_picker_patch.stop()
-        self._bottle_picker_patch.stop()
+        self._tui_patch.stop()
         self._env_patch.stop()
 
     # ------------------------------------------------------------------
-    # Agent explicit — agent picker skipped; bottle picker always shown
+    # Both explicit — no picker shown
     # ------------------------------------------------------------------
 
-    def test_explicit_agent_skips_agent_picker(self):
+    def test_both_explicit_skips_picker(self):
+        self._tui_mock.return_value = "researcher"
         rc = start_mod.cmd_start(["--backend=docker", "researcher"])
         self.assertEqual(0, rc)
-        self._agent_picker_mock.assert_not_called()
-        self._bottle_picker_mock.assert_called_once()
+        self._tui_mock.assert_not_called()
         self._launch_mock.assert_called_once()
-
-    def test_explicit_agent_bottle_picker_shows_available_bottles(self):
-        start_mod.cmd_start(["researcher"])
-        call_kwargs = self._bottle_picker_mock.call_args
-        self.assertEqual(["claude", "dev"], call_kwargs[0][0])
-        self.assertIn("bottle", call_kwargs[1]["title"].lower())
-
-    # ------------------------------------------------------------------
-    # Agent absent → agent picker fires; bottle picker always follows
-    # ------------------------------------------------------------------
-
-    def test_agent_absent_shows_agent_picker(self):
-        self._agent_picker_mock.return_value = "researcher"
-        rc = start_mod.cmd_start(["--backend=docker"])
-        self.assertEqual(0, rc)
-        self._agent_picker_mock.assert_called_once()
-        call_kwargs = self._agent_picker_mock.call_args
-        self.assertEqual(["implementer", "researcher"], call_kwargs[0][0])
-        self.assertIn("agent", call_kwargs[1]["title"].lower())
-        # Bottle picker must also fire after agent selection.
-        self._bottle_picker_mock.assert_called_once()
-
-    def test_agent_picker_cancel_skips_bottle_picker(self):
-        self._agent_picker_mock.return_value = None
-        rc = start_mod.cmd_start(["--backend=docker"])
-        self.assertEqual(0, rc)
-        self._bottle_picker_mock.assert_not_called()
-        self._launch_mock.assert_not_called()
-
-    def test_bottle_picker_cancel_returns_0(self):
-        self._bottle_picker_mock.return_value = None
-        rc = start_mod.cmd_start(["researcher"])
-        self.assertEqual(0, rc)
-        self._launch_mock.assert_not_called()
-
-    # ------------------------------------------------------------------
-    # Bottle selection is forwarded to BottleSpec
-    # ------------------------------------------------------------------
-
-    def test_selected_bottles_forwarded_to_spec(self):
-        self._bottle_picker_mock.return_value = ["claude", "dev"]
-        start_mod.cmd_start(["researcher"])
-        self._launch_mock.assert_called_once()
-        spec = self._launch_mock.call_args[0][0]
-        self.assertEqual(("claude", "dev"), spec.bottle_names)
-
-    def test_empty_bottle_selection_forwarded(self):
-        self._bottle_picker_mock.return_value = []
-        start_mod.cmd_start(["researcher"])
-        self._launch_mock.assert_called_once()
-        spec = self._launch_mock.call_args[0][0]
-        self.assertEqual((), spec.bottle_names)
-
-    # ------------------------------------------------------------------
-    # Agent default bottle pre-populates the picker
-    # ------------------------------------------------------------------
-
-    def test_agent_bottle_prepopulates_bottle_picker(self):
-        manifest = _make_manifest(
-            ["implementer"], ["claude", "dev"], agent_bottle="claude"
-        )
-        with patch(
-            "bot_bottle.cli.start.ManifestIndex.resolve", return_value=manifest
-        ):
-            start_mod.cmd_start(["implementer"])
-        call_kwargs = self._bottle_picker_mock.call_args
-        self.assertEqual(["claude"], call_kwargs[1]["initial"])
-
-    def test_no_agent_bottle_empty_initial(self):
-        manifest = _make_manifest(["researcher"], ["claude", "dev"], agent_bottle="")
-        with patch(
-            "bot_bottle.cli.start.ManifestIndex.resolve", return_value=manifest
-        ):
-            start_mod.cmd_start(["researcher"])
-        call_kwargs = self._bottle_picker_mock.call_args
-        self.assertEqual([], call_kwargs[1]["initial"])
-
-    # ------------------------------------------------------------------
-    # Backend wiring
-    # ------------------------------------------------------------------
-
-    def test_explicit_backend_forwarded(self):
-        start_mod.cmd_start(["--backend=docker", "researcher"])
         _, kwargs = self._launch_mock.call_args
         self.assertEqual("docker", kwargs["backend_name"])
 
-    def test_absent_backend_uses_default(self):
-        start_mod.cmd_start(["researcher"])
+    # ------------------------------------------------------------------
+    # Agent absent → agent picker fires; backend explicit
+    # ------------------------------------------------------------------
+
+    def test_agent_absent_shows_agent_picker(self):
+        self._tui_mock.return_value = "researcher"
+        rc = start_mod.cmd_start(["--backend=docker"])
+        self.assertEqual(0, rc)
+        self._tui_mock.assert_called_once()
+        call_kwargs = self._tui_mock.call_args
+        self.assertEqual(["implementer", "researcher"], call_kwargs[0][0])
+        self.assertIn("agent", call_kwargs[1]["title"].lower())
+
+    def test_agent_picker_cancel_returns_0(self):
+        self._tui_mock.return_value = None
+        rc = start_mod.cmd_start(["--backend=docker"])
+        self.assertEqual(0, rc)
+        self._launch_mock.assert_not_called()
+
+    # ------------------------------------------------------------------
+    # Agent explicit, backend absent → no picker
+    # ------------------------------------------------------------------
+
+    def test_backend_absent_uses_default_without_picker(self):
+        rc = start_mod.cmd_start(["researcher"])
+        self.assertEqual(0, rc)
+        self._tui_mock.assert_not_called()
+        self._launch_mock.assert_called_once()
         _, kwargs = self._launch_mock.call_args
         self.assertIsNone(kwargs["backend_name"])
 
@@ -175,21 +110,28 @@ class TestCmdStartSelector(unittest.TestCase):
         finally:
             os.environ.pop("BOT_BOTTLE_BACKEND", None)
         self.assertEqual(0, rc)
+        self._tui_mock.assert_not_called()
 
-    def test_both_absent_shows_agent_picker_then_bottle_picker(self):
-        self._agent_picker_mock.return_value = "researcher"
+    # ------------------------------------------------------------------
+    # Both absent → only agent picker
+    # ------------------------------------------------------------------
+
+    def test_both_absent_shows_only_agent_picker(self):
+        self._tui_mock.return_value = "researcher"
         rc = start_mod.cmd_start([])
         self.assertEqual(0, rc)
-        self._agent_picker_mock.assert_called_once()
-        self._bottle_picker_mock.assert_called_once()
+        self._tui_mock.assert_called_once()
+        title = self._tui_mock.call_args[1]["title"].lower()
+        self.assertIn("agent", title)
         self._launch_mock.assert_called_once()
+        _, kwargs = self._launch_mock.call_args
+        self.assertIsNone(kwargs["backend_name"])
 
-    def test_both_absent_agent_cancel_skips_bottle_and_launch(self):
-        self._agent_picker_mock.return_value = None
+    def test_both_absent_agent_cancel_skips_backend_picker(self):
+        self._tui_mock.side_effect = [None]
         rc = start_mod.cmd_start([])
         self.assertEqual(0, rc)
-        self._agent_picker_mock.assert_called_once()
-        self._bottle_picker_mock.assert_not_called()
+        self.assertEqual(1, self._tui_mock.call_count)
         self._launch_mock.assert_not_called()
 
 
@@ -207,13 +149,11 @@ class TestCmdStartLabelCollision(unittest.TestCase):
     """cmd_start re-prompts when the label's slug is already running."""
 
     def setUp(self):
-        self._manifest = _make_manifest(["researcher"], ["claude"])
+        self._manifest = _make_manifest(["researcher"])
         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()
-        # Stub the bottle picker to always return a selection.
-        patch.object(tui_mod, "filter_multiselect", return_value=["claude"]).start()
         self.addCleanup(patch.stopall)
 
     def test_no_collision_proceeds_without_reprompt(self):

tests/unit/test_cli_tui.py

@@ -1,4 +1,4 @@
-"""Unit tests for bot_bottle.cli.tui — filter_select and filter_multiselect.
+"""Unit tests for bot_bottle.cli.tui — filter_select internals.
 
 We test the pure-Python logic (_filter_items, cursor movement, confirm,
 cancel) by exercising the internal helpers directly, without spinning up
@@ -8,12 +8,8 @@ a real curses session (which requires a TTY).
 from __future__ import annotations
 
 import unittest
-from typing import Any, Optional
 
-from bot_bottle.cli.tui import _filter_items, _multiselect_loop, filter_multiselect, filter_select
-
-_KEY_ESC = 27
-_KEY_CTRL_D = 4
+from bot_bottle.cli.tui import _filter_items, filter_select
 
 
 class TestFilterItems(unittest.TestCase):
@@ -50,102 +46,5 @@ class TestFilterSelectEmptyItems(unittest.TestCase):
         self.assertIsNone(result)
 
 
-class TestFilterMultiselectEmptyItems(unittest.TestCase):
-    def test_returns_empty_list_for_empty_items(self):
-        # No TTY needed — short-circuits before opening tty.
-        result = filter_multiselect([], title="Select", tty_path="/dev/null")
-        self.assertEqual([], result)
-
-    def test_returns_none_when_tty_unavailable(self):
-        result = filter_multiselect(["a", "b"], tty_path="/nonexistent/tty")
-        self.assertIsNone(result)
-
-
-class TestMultiselectLoopReordering(unittest.TestCase):
-    """Exercise _multiselect_loop key handling without a real curses terminal.
-
-    We drive the loop via a fake screen that feeds a pre-recorded key sequence
-    and records what was drawn — we only need the return value, so the fake
-    screen's getch() raises StopIteration after the key list is exhausted, and
-    the loop is expected to return before that via Ctrl-D.
-    """
-
-    def _run(self, keys: list[int], items: list[str], initial: list[str]) -> Optional[list[str]]:
-        """Run _multiselect_loop with a synthetic screen feeding `keys`."""
-        key_iter = iter(keys)
-
-        class FakeScreen:
-            def erase(self) -> None: pass
-            def getmaxyx(self) -> tuple[int, int]: return (40, 80)
-            def refresh(self) -> None: pass
-            def getch(self) -> int: return next(key_iter)
-            def addstr(self, *a: Any) -> None: pass
-            def keypad(self, *a: Any) -> None: pass
-
-        return _multiselect_loop(FakeScreen(), items, title="", initial=initial)  # type: ignore[arg-type]
-
-    def test_ctrl_d_confirms_initial_selection(self):
-        result = self._run([_KEY_CTRL_D], ["a", "b", "c"], ["a", "b"])
-        self.assertEqual(["a", "b"], result)
-
-    def test_esc_cancels(self):
-        result = self._run([_KEY_ESC], ["a", "b"], ["a"])
-        self.assertIsNone(result)
-
-    def test_tab_then_K_moves_item_up(self):
-        # Start: selected = ["a", "b", "c"]
-        # Tab → order mode (order_cursor=0 on "a")
-        # ↓ → order_cursor=1 (on "b")
-        # K → swap b and a → ["b", "a", "c"], order_cursor=0
-        # Ctrl-D → confirm
-        DOWN = ord("j")
-        result = self._run(
-            [ord("\t"), DOWN, ord("K"), _KEY_CTRL_D],
-            ["a", "b", "c"],
-            ["a", "b", "c"],
-        )
-        self.assertEqual(["b", "a", "c"], result)
-
-    def test_tab_then_J_moves_item_down(self):
-        # selected = ["a", "b", "c"], focus order, cursor=0
-        # J → swap a and b → ["b", "a", "c"], cursor=1
-        # Ctrl-D → confirm
-        result = self._run(
-            [ord("\t"), ord("J"), _KEY_CTRL_D],
-            ["a", "b", "c"],
-            ["a", "b", "c"],
-        )
-        self.assertEqual(["b", "a", "c"], result)
-
-    def test_K_at_top_is_no_op(self):
-        # cursor already at 0, K should not change order
-        result = self._run(
-            [ord("\t"), ord("K"), _KEY_CTRL_D],
-            ["a", "b"],
-            ["a", "b"],
-        )
-        self.assertEqual(["a", "b"], result)
-
-    def test_J_at_bottom_is_no_op(self):
-        DOWN = ord("j")
-        result = self._run(
-            [ord("\t"), DOWN, ord("J"), _KEY_CTRL_D],
-            ["a", "b"],
-            ["a", "b"],
-        )
-        self.assertEqual(["a", "b"], result)
-
-    def test_tab_back_to_filter_then_confirm(self):
-        # Tab → order, Tab → filter, Ctrl-D confirms unchanged
-        result = self._run(
-            [ord("\t"), ord("\t"), _KEY_CTRL_D],
-            ["a", "b"],
-            ["a", "b"],
-        )
-        self.assertEqual(["a", "b"], result)
-
-
-
-
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_macos_container_util.py

@@ -73,6 +73,33 @@ resolver #2
         )
         self.assertTrue(run.call_args_list[-1].kwargs["check"])
 
+    def test_build_image_anchors_relative_dockerfile_to_context(self):
+        status = util.subprocess.CompletedProcess(
+            args=[],
+            returncode=0,
+            stdout=(
+                '[{"status":{"state":"running"},'
+                '"configuration":{"dns":{"nameservers":["9.9.9.9"]}}}]'
+            ),
+            stderr="",
+        )
+        with patch.object(util.subprocess, "run", return_value=status) as run, \
+             patch.object(util.os, "environ", {
+                 "BOT_BOTTLE_MACOS_CONTAINER_DNS": "9.9.9.9",
+             }):
+            util.build_image(
+                "bot-bottle-sidecars:latest",
+                "/repo",
+                dockerfile="Dockerfile.sidecars",
+            )
+        self.assertEqual(
+            [
+                "container", "build", "-t", "bot-bottle-sidecars:latest",
+                "--dns", "9.9.9.9", "-f", "/repo/Dockerfile.sidecars", "/repo",
+            ],
+            run.call_args_list[-1].args[0],
+        )
+
     def test_commit_container_execs_tar_and_builds_image(self):
         # stderr is bytes because subprocess.run uses stderr=PIPE without text=True
         completed = util.subprocess.CompletedProcess(

tests/unit/test_manifest_bottle_merge.py

@@ -1,200 +0,0 @@
-"""Unit: runtime bottle composition (issue #269).
-
-Tests for merge_bottles_runtime and ManifestIndex.load_for_agent with
-the new bottle_names parameter.
-"""
-
-from __future__ import annotations
-
-import os
-import shutil
-import tempfile
-import textwrap
-import unittest
-from pathlib import Path
-
-from bot_bottle.manifest import ManifestBottle, ManifestError, ManifestIndex
-from bot_bottle.manifest_extends import merge_bottles_runtime
-
-
-def _index(bottles: dict[str, object], agents: dict[str, object]) -> ManifestIndex:
-    return ManifestIndex.from_json_obj({"bottles": bottles, "agents": agents})
-
-
-def _bottle(**kwargs: object) -> ManifestBottle:
-    return ManifestBottle.from_dict("test", kwargs)
-
-
-class TestMergeBottlesRuntime(unittest.TestCase):
-    def test_single_bottle_returns_as_is(self):
-        b = _bottle(env={"FOO": "1"})
-        result = merge_bottles_runtime([b])
-        self.assertEqual({"FOO": "1"}, dict(result.env))
-
-    def test_env_later_wins(self):
-        base = _bottle(env={"FOO": "base", "ONLY_BASE": "x"})
-        override = _bottle(env={"FOO": "override", "ONLY_OVERRIDE": "y"})
-        result = merge_bottles_runtime([base, override])
-        self.assertEqual("override", result.env["FOO"])
-        self.assertEqual("x", result.env["ONLY_BASE"])
-        self.assertEqual("y", result.env["ONLY_OVERRIDE"])
-
-    def test_egress_routes_concatenated(self):
-        from bot_bottle.manifest_egress import ManifestEgressConfig, ManifestEgressRoute
-        r1 = ManifestEgressRoute(Host="api.a.com")
-        r2 = ManifestEgressRoute(Host="api.b.com")
-        base = ManifestBottle(egress=ManifestEgressConfig(routes=(r1,)))
-        override = ManifestBottle(egress=ManifestEgressConfig(routes=(r2,)))
-        result = merge_bottles_runtime([base, override])
-        hosts = [r.Host for r in result.egress.routes]
-        self.assertIn("api.a.com", hosts)
-        self.assertIn("api.b.com", hosts)
-
-    def test_supervise_later_wins(self):
-        base = _bottle(supervise=True)
-        override = _bottle(supervise=False)
-        result = merge_bottles_runtime([base, override])
-        self.assertFalse(result.supervise)
-
-    def test_three_bottles_merged_left_to_right(self):
-        b1 = _bottle(env={"A": "1", "B": "1", "C": "1"})
-        b2 = _bottle(env={"B": "2", "C": "2"})
-        b3 = _bottle(env={"C": "3"})
-        result = merge_bottles_runtime([b1, b2, b3])
-        self.assertEqual("1", result.env["A"])
-        self.assertEqual("2", result.env["B"])
-        self.assertEqual("3", result.env["C"])
-
-    def test_empty_list_raises(self):
-        with self.assertRaises(ValueError):
-            merge_bottles_runtime([])
-
-
-class TestLoadForAgentWithBottleNames(unittest.TestCase):
-    def test_bottle_names_override_agent_bottle(self):
-        idx = _index(
-            bottles={
-                "base": {"env": {"X": "base"}},
-                "override": {"env": {"X": "override"}},
-            },
-            agents={"impl": {"bottle": "base", "skills": [], "prompt": ""}},
-        )
-        m = idx.load_for_agent("impl", ("override",))
-        self.assertEqual("override", m.bottle.env["X"])
-
-    def test_bottle_names_merged_in_order(self):
-        idx = _index(
-            bottles={
-                "a": {"env": {"X": "a", "A": "only-a"}},
-                "b": {"env": {"X": "b", "B": "only-b"}},
-            },
-            agents={"impl": {"bottle": "a", "skills": [], "prompt": ""}},
-        )
-        m = idx.load_for_agent("impl", ("a", "b"))
-        self.assertEqual("b", m.bottle.env["X"])
-        self.assertEqual("only-a", m.bottle.env["A"])
-        self.assertEqual("only-b", m.bottle.env["B"])
-
-    def test_empty_bottle_names_uses_agent_bottle(self):
-        idx = _index(
-            bottles={"base": {"env": {"X": "base"}}},
-            agents={"impl": {"bottle": "base", "skills": [], "prompt": ""}},
-        )
-        m = idx.load_for_agent("impl", ())
-        self.assertEqual("base", m.bottle.env["X"])
-
-    def test_no_bottle_and_no_bottle_names_raises(self):
-        idx = _index(
-            bottles={"base": {}},
-            agents={"impl": {"skills": [], "prompt": ""}},
-        )
-        with self.assertRaises(ManifestError) as ctx:
-            idx.load_for_agent("impl", ())
-        self.assertIn("no 'bottle' field", str(ctx.exception))
-
-    def test_unknown_bottle_name_raises(self):
-        idx = _index(
-            bottles={"base": {}},
-            agents={"impl": {"bottle": "base", "skills": [], "prompt": ""}},
-        )
-        with self.assertRaises(ManifestError) as ctx:
-            idx.load_for_agent("impl", ("nonexistent",))
-        self.assertIn("nonexistent", str(ctx.exception))
-
-    def test_agent_without_bottle_works_with_bottle_names(self):
-        idx = _index(
-            bottles={"base": {"env": {"X": "base"}}},
-            agents={"impl": {"skills": [], "prompt": ""}},
-        )
-        m = idx.load_for_agent("impl", ("base",))
-        self.assertEqual("base", m.bottle.env["X"])
-
-
-class TestAllBottleNames(unittest.TestCase):
-    def test_eager_mode_returns_bottle_names(self):
-        idx = _index(
-            bottles={"alpha": {}, "beta": {}, "gamma": {}},
-            agents={"impl": {"bottle": "alpha", "skills": [], "prompt": ""}},
-        )
-        self.assertEqual(["alpha", "beta", "gamma"], idx.all_bottle_names)
-
-    def test_lazy_mode_scans_files(self):
-        home = Path(tempfile.mkdtemp(prefix="cb-home-"))
-        orig_home = os.environ.get("HOME")
-        os.environ["HOME"] = str(home)
-        try:
-            bottles_dir = home / ".bot-bottle" / "bottles"
-            agents_dir = home / ".bot-bottle" / "agents"
-            bottles_dir.mkdir(parents=True)
-            agents_dir.mkdir(parents=True)
-            (bottles_dir / "claude.md").write_text("---\n---\n")
-            (bottles_dir / "dev.md").write_text("---\n---\n")
-            (agents_dir / "impl.md").write_text("---\nbottle: claude\n---\n")
-            idx = ManifestIndex.resolve(str(home))
-            self.assertEqual(["claude", "dev"], idx.all_bottle_names)
-        finally:
-            if orig_home is None:
-                os.environ.pop("HOME", None)
-            else:
-                os.environ["HOME"] = orig_home
-            shutil.rmtree(home, ignore_errors=True)
-
-
-class TestAgentOptionalBottleMd(unittest.TestCase):
-    """Agent file without bottle: works when bottle_names are provided at launch."""
-
-    def setUp(self) -> None:
-        self.home = Path(tempfile.mkdtemp(prefix="cb-home-"))
-        self._orig_home = os.environ.get("HOME")
-        os.environ["HOME"] = str(self.home)
-
-    def tearDown(self) -> None:
-        if self._orig_home is None:
-            os.environ.pop("HOME", None)
-        else:
-            os.environ["HOME"] = self._orig_home
-        shutil.rmtree(self.home, ignore_errors=True)
-
-    def _write(self, rel: str, text: str) -> None:
-        p = self.home / ".bot-bottle" / rel
-        p.parent.mkdir(parents=True, exist_ok=True)
-        p.write_text(textwrap.dedent(text).lstrip("\n"))
-
-    def test_agent_without_bottle_resolves_with_bottle_names(self):
-        self._write("bottles/dev.md", "---\nenv:\n  X: dev\n---\n")
-        self._write("agents/impl.md", "---\n---\nimpl agent.\n")
-        idx = ManifestIndex.resolve(str(self.home))
-        m = idx.load_for_agent("impl", ("dev",))
-        self.assertEqual("dev", m.bottle.env["X"])
-
-    def test_agent_without_bottle_fails_without_bottle_names(self):
-        self._write("bottles/dev.md", "---\n---\n")
-        self._write("agents/impl.md", "---\n---\nimpl agent.\n")
-        idx = ManifestIndex.resolve(str(self.home))
-        with self.assertRaises(ManifestError) as ctx:
-            idx.load_for_agent("impl", ())
-        self.assertIn("no 'bottle' field", str(ctx.exception))
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_supervise_server.py

@@ -20,6 +20,7 @@ import supervise as _sv  # noqa: E402  # type: ignore
 
 from bot_bottle import supervise_server  # noqa: E402
 from bot_bottle.supervise_server import (
+    ERR_INTERNAL,
     ERR_INVALID_PARAMS,
     ERR_INVALID_REQUEST,
     ERR_METHOD_NOT_FOUND,
@@ -29,7 +30,9 @@ from bot_bottle.supervise_server import (
     PROPOSED_FILE_FIELD,
     ServerConfig,
     TOOL_DEFINITIONS,
+    _RpcClientError,
     _RpcError,
+    _RpcInternalError,
     _response_timeout_from_env,
     format_response_text,
     handle_initialize,
@@ -47,15 +50,15 @@ from bot_bottle.supervise_server import (
 
 
 class TestValidation(unittest.TestCase):
-    def test_capability_block_accepts_anything_nonempty(self):
-        validate_proposed_file(
-            _sv.TOOL_CAPABILITY_BLOCK,
-            "FROM python:3.13\nRUN apk add git\n",
-        )
-
     def test_empty_proposed_file_rejected_for_tools_with_file_field(self):
         with self.assertRaises(_RpcError):
-            validate_proposed_file(_sv.TOOL_CAPABILITY_BLOCK, "   \n\t")
+            validate_proposed_file(_sv.TOOL_EGRESS_ALLOW, "   \n\t")
+
+    def test_capability_block_rejected_as_unknown_tool(self):
+        with self.assertRaises(_RpcError) as cm:
+            validate_proposed_file("capability-block", "FROM python:3.13\n")
+        self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
+        self.assertIn("unknown tool", cm.exception.message)
 
     def test_egress_routes_yaml_is_validated(self):
         validate_proposed_file(
@@ -77,6 +80,65 @@ class TestValidation(unittest.TestCase):
         self.assertIn("must not change egress logging", cm.exception.message)
 
 
+# --- Error taxonomy --------------------------------------------------------
+
+
+class TestRpcErrorTaxonomy(unittest.TestCase):
+    def test_rpc_client_error_is_rpc_error(self):
+        e = _RpcClientError(ERR_INVALID_PARAMS, "bad param")
+        self.assertIsInstance(e, _RpcError)
+        self.assertEqual(ERR_INVALID_PARAMS, e.code)
+        self.assertEqual("bad param", e.message)
+
+    def test_rpc_internal_error_is_rpc_error(self):
+        e = _RpcInternalError("disk full")
+        self.assertIsInstance(e, _RpcError)
+        self.assertEqual(ERR_INTERNAL, e.code)
+        self.assertEqual("disk full", e.message)
+
+    def test_rpc_internal_error_preserves_cause(self):
+        cause = OSError("no space left on device")
+        try:
+            raise _RpcInternalError("failed to write") from cause
+        except _RpcInternalError as e:
+            self.assertIs(cause, e.__cause__)
+
+    def test_parse_error_is_client_error(self):
+        with self.assertRaises(_RpcClientError):
+            parse_jsonrpc(b"{bad json")
+
+    def test_validation_error_is_client_error(self):
+        with self.assertRaises(_RpcClientError):
+            validate_proposed_file(_sv.TOOL_EGRESS_ALLOW, "routes: nope\n")
+
+    def test_unknown_tool_in_tools_call_is_client_error(self):
+        config = ServerConfig(bottle_slug="dev", queue_dir=Path("/unused"))
+        with self.assertRaises(_RpcClientError) as cm:
+            handle_tools_call({"name": "no-such-tool", "arguments": {}}, config)
+        self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
+
+
+class TestRpcInternalErrorOnIoFailure(unittest.TestCase):
+    def test_write_proposal_os_error_raises_internal(self):
+        config = ServerConfig(
+            bottle_slug="dev",
+            queue_dir=Path("/dev/null/cannot-exist"),
+        )
+        with self.assertRaises(_RpcInternalError) as cm:
+            handle_tools_call(
+                {
+                    "name": _sv.TOOL_EGRESS_ALLOW,
+                    "arguments": {
+                        "routes_yaml": "routes:\n  - host: example.com\n",
+                        "justification": "x",
+                    },
+                },
+                config,
+            )
+        self.assertEqual(ERR_INTERNAL, cm.exception.code)
+        self.assertIsNotNone(cm.exception.__cause__)
+
+
 # --- JSON-RPC parsing ------------------------------------------------------
 
 
@@ -157,7 +219,6 @@ class TestHandleToolsList(unittest.TestCase):
         self.assertEqual(
             sorted([
                 _sv.TOOL_EGRESS_ALLOW,
-                _sv.TOOL_CAPABILITY_BLOCK,
                 _sv.TOOL_EGRESS_BLOCK,
                 _sv.TOOL_LIST_EGRESS_ROUTES,
             ]),
@@ -233,10 +294,10 @@ class TestHandleToolsCall(unittest.TestCase):
         try:
             result = handle_tools_call(
                 {
-                    "name": _sv.TOOL_CAPABILITY_BLOCK,
+                    "name": _sv.TOOL_EGRESS_BLOCK,
                     "arguments": {
-                        "dockerfile": "FROM python:3.13\n",
-                        "justification": "need git",
+                        "routes_yaml": "routes:\n  - host: example.com\n",
+                        "justification": "need example.com",
                     },
                 },
                 self.config,
@@ -273,9 +334,9 @@ class TestHandleToolsCall(unittest.TestCase):
         try:
             result = handle_tools_call(
                 {
-                    "name": _sv.TOOL_CAPABILITY_BLOCK,
+                    "name": _sv.TOOL_EGRESS_ALLOW,
                     "arguments": {
-                        "dockerfile": "FROM python:3.13\n",
+                        "routes_yaml": "routes:\n  - host: example.com\n",
                         "justification": "needed for tests",
                     },
                 },
@@ -297,20 +358,52 @@ class TestHandleToolsCall(unittest.TestCase):
         with self.assertRaises(_RpcError):
             handle_tools_call(
                 {
-                    "name": _sv.TOOL_CAPABILITY_BLOCK,
-                    "arguments": {"dockerfile": "FROM python:3.13\n"},
+                    "name": _sv.TOOL_EGRESS_ALLOW,
+                    "arguments": {"routes_yaml": "routes:\n  - host: example.com\n"},
                 },
                 self.config,
             )
 
+    def test_missing_name_raises(self):
+        with self.assertRaises(_RpcError) as cm:
+            handle_tools_call({"arguments": {}}, self.config)
+        self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
+
+    def test_arguments_must_be_object(self):
+        with self.assertRaises(_RpcError) as cm:
+            handle_tools_call(
+                {
+                    "name": _sv.TOOL_EGRESS_ALLOW,
+                    "arguments": [],
+                },
+                self.config,
+            )
+        self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
+        self.assertIn("must be an object", cm.exception.message)
+
+    def test_capability_block_call_raises_unknown_tool(self):
+        with self.assertRaises(_RpcError) as cm:
+            handle_tools_call(
+                {
+                    "name": "capability-block",
+                    "arguments": {
+                        "dockerfile": "FROM python:3.13\n",
+                        "justification": "need git",
+                    },
+                },
+                self.config,
+            )
+        self.assertEqual(ERR_INVALID_PARAMS, cm.exception.code)
+        self.assertIn("unknown tool", cm.exception.message)
+
     def test_archives_proposal_after_response(self):
         responder = self._respond_when_proposal_appears(_sv.STATUS_APPROVED)
         try:
             handle_tools_call(
                 {
-                    "name": _sv.TOOL_CAPABILITY_BLOCK,
+                    "name": _sv.TOOL_EGRESS_ALLOW,
                     "arguments": {
-                        "dockerfile": "FROM python:3.13\n",
+                        "routes_yaml": "routes:\n  - host: example.com\n",
                         "justification": "x",
                     },
                 },
@@ -332,10 +425,10 @@ class TestHandleToolsCall(unittest.TestCase):
         )
         result = handle_tools_call(
             {
-                "name": _sv.TOOL_CAPABILITY_BLOCK,
+                "name": _sv.TOOL_EGRESS_ALLOW,
                 "arguments": {
-                    "dockerfile": "FROM python:3.13\n",
-                    "justification": "need a capability",
+                    "routes_yaml": "routes:\n  - host: example.com\n",
+                    "justification": "need egress",
                 },
             },
             config,
@@ -350,6 +443,31 @@ class TestHandleToolsCall(unittest.TestCase):
 
 
 class TestHandleListEgressRoutes(unittest.TestCase):
+    def test_success_returns_body_text(self):
+        class _Resp:
+            def __enter__(self):
+                return self
+
+            def __exit__(self, exc_type: type[BaseException] | None, exc: BaseException | None, tb: object) -> bool:
+                return False
+
+            def read(self):
+                return b"[{\"host\": \"example.com\"}]"
+
+        class _Opener:
+            def open(self, *args, **kwargs):  # noqa: ANN001, ANN002, ANN003  # type: ignore
+                return _Resp()
+
+        with patch.object(supervise_server.urllib.request, "build_opener", return_value=_Opener()):
+            result = handle_list_egress_routes(
+                {},
+                ServerConfig(bottle_slug="dev", queue_dir=Path("/unused")),
+            )
+
+        self.assertFalse(result["isError"])  # type: ignore[index]
+        text = result["content"][0]["text"]  # type: ignore[index]
+        self.assertIn("example.com", text)
+
     def test_url_error_returns_tool_error(self):
         class _Opener:
             def open(self, *args, **kwargs):  # noqa: ANN001, ANN002, ANN003  # type: ignore
@@ -409,6 +527,13 @@ class TestFormatResponseText(unittest.TestCase):
         self.assertIn("the operator modified", text.lower())
 
 
+class TestFormatPendingResponseText(unittest.TestCase):
+    def test_formats_timeout_message(self):
+        text = supervise_server.format_pending_response_text(12.5)
+        self.assertIn("status: pending", text)
+        self.assertIn("12.5s", text)
+
+
 # --- End-to-end HTTP sanity ------------------------------------------------
 
 
@@ -459,7 +584,7 @@ class TestHttpEndToEnd(unittest.TestCase):
         self.assertEqual("2.0", result["jsonrpc"])
         self.assertEqual(1, result["id"])
         names = [t["name"] for t in result["result"]["tools"]]  # type: ignore[index]
-        self.assertIn(_sv.TOOL_CAPABILITY_BLOCK, names)
+        self.assertNotIn("capability-block", names)
         self.assertIn(_sv.TOOL_EGRESS_ALLOW, names)
         self.assertIn(_sv.TOOL_EGRESS_BLOCK, names)
 
@@ -469,6 +594,26 @@ class TestHttpEndToEnd(unittest.TestCase):
         )
         self.assertEqual(ERR_METHOD_NOT_FOUND, result["error"]["code"])  # type: ignore[index]
 
+    def test_internal_error_returns_err_internal_over_http(self):
+        with patch.object(
+            supervise_server._sv, "write_proposal",
+            side_effect=OSError("disk full"),
+        ):
+            result = self._post_jsonrpc({
+                "jsonrpc": "2.0",
+                "id": 99,
+                "method": "tools/call",
+                "params": {
+                    "name": _sv.TOOL_EGRESS_ALLOW,
+                    "arguments": {
+                        "routes_yaml": "routes:\n  - host: example.com\n",
+                        "justification": "x",
+                    },
+                },
+            })
+        self.assertIn("error", result)
+        self.assertEqual(ERR_INTERNAL, result["error"]["code"])  # type: ignore[index]
+
     def test_health_endpoint(self):
         conn = http.client.HTTPConnection("127.0.0.1", self.port, timeout=5)
         try: