chore: update quality badges

- Coverage: 83%
- Core coverage: 95%

[skip ci]

README.md

@@ -5,8 +5,8 @@
 # bot-bottle
 
 [![test](https://gitea.dideric.is/didericis/bot-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
-[![coverage](https://img.shields.io/badge/coverage-84%25-brightgreen)](https://coverage.readthedocs.io/)
-[![core coverage](https://img.shields.io/badge/core%20coverage-96%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
+[![coverage](https://img.shields.io/badge/coverage-83%25-brightgreen)](https://coverage.readthedocs.io/)
+[![core coverage](https://img.shields.io/badge/core%20coverage-95%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
 
 **Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.
 

bot_bottle/agent_provider.py

@@ -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.
 

bot_bottle/backend/docker/launch.py

@@ -37,7 +37,10 @@ from pathlib import Path
 from typing import Callable, Generator
 
 from ...egress import egress_resolve_token_values
-from ...git_gate import revoke_git_gate_provisioned_keys
+from ...git_gate import (
+    provision_git_gate_dynamic_keys,
+    revoke_git_gate_provisioned_keys,
+)
 from ...log import info, warn
 from . import network as network_mod
 from . import util as docker_mod
@@ -118,6 +121,11 @@ def launch(
 
         git_gate_plan = plan.git_gate_plan
         if git_gate_plan.upstreams:
+            git_gate_plan = provision_git_gate_dynamic_keys(
+                plan.manifest.bottle,
+                git_gate_plan,
+                git_gate_state_dir(plan.slug),
+            )
             git_gate_plan = dataclasses.replace(
                 git_gate_plan,
                 internal_network=internal_network,

bot_bottle/backend/macos_container/launch.py

@@ -28,7 +28,10 @@ from ...egress import (
     egress_resolve_token_values,
     egress_sidecar_env_entries,
 )
-from ...git_gate import revoke_git_gate_provisioned_keys
+from ...git_gate import (
+    provision_git_gate_dynamic_keys,
+    revoke_git_gate_provisioned_keys,
+)
 from ...log import die, info, warn
 from ...supervise import QUEUE_DIR_IN_CONTAINER, SUPERVISE_PORT
 from ...util import expand_tilde
@@ -98,6 +101,8 @@ def launch(
         egress_network = egress_network_name(plan.slug)
         _create_networks(internal_network, egress_network, stack)
 
+        plan = _provision_git_gate_keys(plan)
+
         sidecar_name = sidecar_container_name(plan.slug)
         container_mod.force_remove_container(sidecar_name)
         _start_sidecar_bundle(plan, sidecar_name, internal_network, egress_network)
@@ -241,6 +246,19 @@ def _stamp_agent_urls(
     )
 
 
+def _provision_git_gate_keys(
+    plan: MacosContainerBottlePlan,
+) -> MacosContainerBottlePlan:
+    if not plan.git_gate_plan.upstreams:
+        return plan
+    git_gate_plan = provision_git_gate_dynamic_keys(
+        plan.manifest.bottle,
+        plan.git_gate_plan,
+        git_gate_state_dir(plan.slug),
+    )
+    return dataclasses.replace(plan, git_gate_plan=git_gate_plan)
+
+
 def _stage_git_gate(plan: MacosContainerBottlePlan, sidecar_name: str) -> None:
     gp = plan.git_gate_plan
     if not gp.upstreams:

bot_bottle/backend/smolmachines/launch.py

@@ -41,7 +41,10 @@ from ..docker.git_gate import (
     GIT_GATE_ENTRYPOINT_IN_CONTAINER,
     GIT_GATE_HOOK_IN_CONTAINER,
 )
-from ...git_gate import revoke_git_gate_provisioned_keys
+from ...git_gate import (
+    provision_git_gate_dynamic_keys,
+    revoke_git_gate_provisioned_keys,
+)
 from ...log import info, warn
 from ...bottle_state import (
     egress_state_dir,
@@ -174,6 +177,7 @@ def _start_bundle(
 ) -> SmolmachinesBottlePlan:
     """Build the BundleLaunchSpec, resolve token env, start the
     sidecar bundle container, and register teardown."""
+    plan = _provision_git_gate_keys(plan)
     bundle_spec = _bundle_launch_spec(plan, network, loopback_ip)
     token_env = _resolve_token_env(plan, dict(os.environ))
     _bundle.ensure_bundle_image(bundle_spec.image)
@@ -182,6 +186,19 @@ def _start_bundle(
     return plan
 
 
+def _provision_git_gate_keys(
+    plan: SmolmachinesBottlePlan,
+) -> SmolmachinesBottlePlan:
+    if not plan.git_gate_plan.upstreams:
+        return plan
+    git_gate_plan = provision_git_gate_dynamic_keys(
+        plan.manifest.bottle,
+        plan.git_gate_plan,
+        git_gate_state_dir(plan.slug),
+    )
+    return dataclasses.replace(plan, git_gate_plan=git_gate_plan)
+
+
 def _discover_urls(
     plan: SmolmachinesBottlePlan,
     loopback_ip: str,

bot_bottle/cli/start.py

@@ -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}); "

bot_bottle/contrib/claude/agent_provider.py

@@ -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")

bot_bottle/contrib/codex/agent_provider.py

@@ -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")

bot_bottle/contrib/pi/agent_provider.py

@@ -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")

bot_bottle/git_gate.py

@@ -30,7 +30,6 @@ backend-specific and lives on concrete subclasses (see
 
 from __future__ import annotations
 
-import dataclasses
 from abc import ABC
 from dataclasses import dataclass
 from pathlib import Path
@@ -53,6 +52,7 @@ from .git_gate_render import (
     _gitconfig_validate_value,
 )
 from .git_gate_provision import (
+    provision_git_gate_dynamic_keys,
     revoke_git_gate_provisioned_keys,
     _provision_dynamic_key,
     _resolve_identity_file,
@@ -93,20 +93,14 @@ class GitGate(ABC):
         entrypoint, pre-receive hook, and access-hook scripts (mode
         600) under `stage_dir`. Pure host-side, no docker subprocess.
 
-        For `gitea` key entries, also generates and registers
-        a fresh deploy key via the forge API and writes the private key
-        + key ID to `stage_dir`.
+        For `gitea` key entries, the returned upstream intentionally
+        has an empty identity file. Backend launch fills that in after
+        the operator confirms the preflight.
 
         Returned plan is incomplete: the launch step must fill
         `internal_network` / `egress_network` via `dataclasses.replace`
         before passing the plan to `.start`."""
-        upstreams_list = list(git_gate_upstreams_for_bottle(bottle))
-        for i, entry in enumerate(bottle.git):
-            upstreams_list[i] = dataclasses.replace(
-                upstreams_list[i],
-                identity_file=_resolve_identity_file(entry, slug, stage_dir),
-            )
-        upstreams = tuple(upstreams_list)
+        upstreams = git_gate_upstreams_for_bottle(bottle)
         entrypoint = stage_dir / "git_gate_entrypoint.sh"
         entrypoint.write_text(git_gate_render_entrypoint(upstreams))
         entrypoint.chmod(0o600)
@@ -162,6 +156,7 @@ __all__ = [
     "git_gate_render_entrypoint",
     "git_gate_render_hook",
     "git_gate_render_access_hook",
+    "provision_git_gate_dynamic_keys",
     "revoke_git_gate_provisioned_keys",
     "_gitconfig_validate_value",
     "_provision_dynamic_key",

bot_bottle/git_gate_provision.py

@@ -9,10 +9,16 @@ imported (`deploy_key_provisioner`) to keep its cost off the host path.
 from __future__ import annotations
 
 import os
+import dataclasses
 from pathlib import Path
+from typing import TYPE_CHECKING
 
 from .log import info
 from .manifest import ManifestBottle, ManifestGitEntry
+from .git_gate_render import GitGateUpstream
+
+if TYPE_CHECKING:
+    from .git_gate import GitGatePlan
 
 def _provision_dynamic_key(
     entry: ManifestGitEntry,
@@ -95,8 +101,45 @@ def _resolve_identity_file(entry: ManifestGitEntry, slug: str, stage_dir: Path)
     return entry.IdentityFile
 
 
+def provision_git_gate_dynamic_keys(
+    bottle: ManifestBottle,
+    plan: "GitGatePlan",
+    stage_dir: Path,
+) -> "GitGatePlan":
+    """Provision dynamic git-gate keys and return an updated plan.
+
+    This runs during backend launch, after the operator confirms the
+    preflight. Plan preparation intentionally stays side-effect-light:
+    dry-runs and aborted launches must not create remote deploy keys.
+    """
+    if not plan.upstreams:
+        return plan
+
+    upstreams_by_name: dict[str, GitGateUpstream] = {
+        upstream.name: upstream for upstream in plan.upstreams
+    }
+    updated: list[GitGateUpstream] = []
+    for entry in bottle.git:
+        upstream = upstreams_by_name.get(entry.Name)
+        if upstream is None:
+            continue
+        if entry.Key.provider == "gitea":
+            identity_file = _provision_dynamic_key(entry, plan.slug, stage_dir)
+            upstream = dataclasses.replace(upstream, identity_file=identity_file)
+        updated.append(upstream)
+
+    if len(updated) != len(plan.upstreams):
+        updated_names = {u.name for u in updated}
+        for upstream in plan.upstreams:
+            if upstream.name not in updated_names:
+                updated.append(upstream)
+
+    return dataclasses.replace(plan, upstreams=tuple(updated))
+
+
 __all__ = [
     "revoke_git_gate_provisioned_keys",
+    "provision_git_gate_dynamic_keys",
     "_provision_dynamic_key",
     "_resolve_identity_file",
 ]

bot_bottle/git_http_backend.py

@@ -16,11 +16,16 @@ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
 from urllib.parse import urlsplit
 
-from .git_gate import GIT_GATE_TIMEOUT_SECS
-
 
 DEFAULT_PORT = 9420
 
+# Mirrors git_gate_render.GIT_GATE_TIMEOUT_SECS. Duplicated rather than
+# imported: this module ships as a flat top-level sibling in the sidecar
+# bundle image (see Dockerfile.sidecars), not as part of the bot_bottle
+# package, so `bot_bottle.git_gate` and its dependency chain aren't
+# available at runtime.
+GIT_GATE_TIMEOUT_SECS = 15
+
 # Bound memory use while still allowing ordinary git push packfiles.
 MAX_BODY_BYTES = 100 * 1024 * 1024
 

docs/research/monetization-positioning.md

@@ -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

tests/unit/test_cli_start_headless.py

@@ -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()

tests/unit/test_contrib_claude_provider.py

@@ -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()

tests/unit/test_contrib_codex_provider.py

@@ -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()

tests/unit/test_contrib_pi_provider.py

@@ -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()

tests/unit/test_docker_provision_git_user.py

@@ -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()

tests/unit/test_git_gate.py

@@ -14,6 +14,7 @@ from bot_bottle.git_gate import (
     git_gate_render_access_hook,
     git_gate_render_entrypoint,
     git_gate_render_hook,
+    provision_git_gate_dynamic_keys,
     revoke_git_gate_provisioned_keys,
     _resolve_identity_file,
     git_gate_upstreams_for_bottle,
@@ -371,6 +372,27 @@ class TestDynamicKeyProvisioning(unittest.TestCase):
             self.assertEqual("/tmp/provisioned-key", _resolve_identity_file(entry, "demo", self.stage))
         mock_provision.assert_called_once()
 
+    def test_prepare_defers_gitea_key_provisioning(self):
+        bottle = self._gitea_manifest().bottles["dev"]
+        with patch("bot_bottle.git_gate_provision._provision_dynamic_key") as mock_provision:
+            plan = _StubGate().prepare(bottle, "demo", self.stage)
+
+        mock_provision.assert_not_called()
+        self.assertEqual("", plan.upstreams[0].identity_file)
+
+    def test_launch_time_helper_provisions_gitea_keys(self):
+        bottle = self._gitea_manifest().bottles["dev"]
+        plan = _StubGate().prepare(bottle, "demo", self.stage)
+
+        with patch(
+            "bot_bottle.git_gate_provision._provision_dynamic_key",
+            return_value="/tmp/provisioned-key",
+        ) as mock_provision:
+            updated = provision_git_gate_dynamic_keys(bottle, plan, self.stage)
+
+        mock_provision.assert_called_once_with(bottle.git[0], "demo", self.stage)
+        self.assertEqual("/tmp/provisioned-key", updated.upstreams[0].identity_file)
+
     def test_revoke_skips_non_gitea_and_missing_id_file(self):
         revoke_git_gate_provisioned_keys(fixture_with_git().bottles["dev"], self.stage)
 

tests/unit/test_smolmachines_provision.py

@@ -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()