docs(prd): add PRD 0049 — named/labelled agents

Draft PRD for prompting operators for a custom label and optional
ANSI color at agent launch time, storing both in metadata.json, and
surfacing the label (in color) in the dashboard's active-agents pane.

Closes #171

README.md

@@ -6,96 +6,26 @@
 
 [![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)
 
-Run multiple Claude Code agents on your own machine, each scoped to its own secrets, skills, and egress allowlist.
+**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.
 
-![pipelock and git-gate blocking exfil attempts against a live bottle](docs/demo.gif)
+**Solution:** Ephemeral, per agent "bottles" the agent cannot modify that scan all traffic for data exfiltration and limit capabilities and egress to only what the agent needs.
 
-Four prompts to the agent inside a real bottle:
+## Features
-claude replies to `hello there` — proof api.anthropic.com routes
-through pipelock's bumped TLS end-to-end;
-asked to GET a non-allowlisted host, the agent's curl gets 403 back
-from pipelock;
-asked to POST a credential-shaped body to an allowlisted host, the
-same 403 — pipelock's DLP body scanner caught it;
-asked to commit and push an AKIA-shaped key, git-gate's gitleaks
-pre-receive hook rejects the ref.
-Run it yourself with `bash scripts/demo.sh`.
 
-## Why "bot-bottle"?
+- **Per-bottle egress allowlist** — TLS-bumped HTTP/HTTPS chokepoint with a per-manifest host allowlist and request-body DLP scanner; DoH and arbitrary hosts blocked by default.
-
+- **Tokens the agent never sees** — host secrets live in a sidecar; the agent dials `http://sidecar:9099/<path>` and the proxy strips inbound `Authorization` and injects the real token before forwarding. `printenv` in the agent shows proxy URLs only.
-Each container is a bottle; Claude is the genie inside. The genie's
+- **Gitleaks-scanned push (git-gate)** — `bottle.git` remotes route through a per-bottle `git daemon` that gitleaks-scans incoming refs pre-receive and forwards clean refs upstream over SSH. The agent never holds the upstream credential.
-powers are exactly what the manifest grants it — a specific set of
+- **Manifest-scoped skills + secrets** — each bottle declares its skills, env, git identity, remotes, and egress routes; unknown keys die at load.
-skills, a specific set of secrets, and a specific set of hosts it can
+- **Trust boundary at `$HOME`** — bottles (credentials, egress, remotes) live only under `~/.bot-bottle/bottles/`. Repos may ship agents but not bottles, so a cloned repo can't redirect an env var to an attacker host.
-reach — nothing more. You uncork one bottle per agent
+- **Composable bottles (`extends:`)** — keep provider/runtime policy in one base bottle (e.g. `claude.md`) and overlay task bottles on top.
-(`./cli.py start <agent>`), many bottles run in parallel, and each is
+- **Parallel, isolated bottles** — each bottle is its own per-agent Docker `--internal` network; bottles don't share state or talk to each other.
-scoped to its task. When the session ends the bottle is destroyed and
+- **Provider templates (Claude, Codex)** — `Dockerfile.claude` / `Dockerfile.codex`, or a bottle-supplied Dockerfile. Claude auth via long-lived OAuth token; Codex via opt-in host device-auth forwarding.
-the genie does not persist.
+- **gVisor auto-detect** — on Linux hosts where `runsc` is registered with Docker, every bottle launches under it for a userspace syscall barrier; no manifest config required.
-
+- **Smolmachines backend (macOS)** — opt-in `BOT_BOTTLE_BACKEND=smolmachines` runs the agent in a libkrun micro-VM with the sidecar bundle still in Docker.
-## Goals
-
-- Scope each agent to the minimum credentials and network egress its task actually needs
-- Run multiple agents in parallel, isolated from each other
-- Keep code, credentials, and agent activity on infrastructure I control — no third-party agent runtime
-
-## Project status
-
-bot-bottle is a self-hosted secure runtime for AI coding agents.
-Each agent runs in an isolated container or micro-VM-backed bottle with
-scoped secrets, allowlisted egress, TLS-aware proxying, DLP checks, and
-a git-gate that withholds upstream credentials and scans pushes before
-forwarding. The project includes a documented threat model, PRD-driven
-development history, Docker and smolmachines backends, dashboard and
-remediation flows, and unit/integration tests covering exfiltration and
-sandbox escape scenarios.
-
-## Security model
-
-Each agent runs in its own bottle: its own container, its own internal
-Docker network, and its own pipelock sidecar. Bottles don't share
-state, don't talk to each other, and only get the env vars, skills,
-SSH identities, and egress hosts the manifest grants them — nothing
-more. Any one agent only has the access it needs to do its job.
-
-The bottle limits both what an agent can see and where it can send
-it. Each bottle gets only the secrets and SSH identities the manifest
-grants it — a Gitea token but not a GitHub token, a deploy key but
-not a personal SSH key — so even a compromised or misbehaving agent
-only handles credentials it was already trusted with for its job.
-Egress flows through pipelock, which constrains where those
-credentials can travel: an agent with a Gitea token can reach
-`gitea.dideric.is`, not arbitrary attacker-controlled hosts. The same
-constraint blocks DNS-over-HTTPS as an exfil channel — a DoH resolver
-like `cloudflare-dns.com` would have to be on the allowlist for the
-agent to reach it at all. The container itself adds a layer between
-the agent and the host, but the v1 design leans more on secret
-minimization and egress allowlisting than on the container as a
-hardened boundary. On Linux hosts where [gVisor](https://gvisor.dev/)
-is registered with Docker, bot-bottle auto-detects it and launches
-every bottle under `runsc` for a userspace syscall barrier — no
-manifest configuration required. The broader v2 discussion lives in
-`docs/research/stronger-isolation-alternatives.md`.
-
-The egress proxy and OAuth-token handling below are the load-bearing
-pieces of v1.
 
 ## Architecture
 
-A bottle is two containers per agent: an `agent` container, and a
+A bottle is two containers per agent: an `agent` container, and a `sidecars` container that bundles pipelock + cred-proxy + git-gate + supervise behind a Python init supervisor. They share a per-agent Docker `--internal` network; the agent has no default route off-box.
-`sidecars` container that bundles pipelock + egress + git-gate +
-supervise behind a Python init supervisor (PRD 0024). They share a
-per-agent Docker `--internal` network; the agent has no default
-route off-box. All HTTP and HTTPS egress funnels through pipelock,
-where the egress allowlist, TLS interception, and request-body DLP
-scanner enforce the manifest before any byte leaves the host. The
-only egress that doesn't traverse pipelock is git-gate's SSH
-push/fetch to `bottle.git` upstreams — pipelock can't proxy SSH,
-so git-gate is its own L4-style egress path with gitleaks doing
-the pre-receive scan.
-
-The agent dials the bundle by the legacy short names (`pipelock`,
-`egress`, `git-gate`, `supervise`); the renderer registers those as
-docker-network aliases on the bundle so existing HTTPS_PROXY URLs
-and MCP endpoints resolve without an agent-side change.
 
 ```
                             host  ( ./cli.py )
@@ -104,26 +34,21 @@ and MCP endpoints resolve without an agent-side change.
                                   ▼
    ┌─────────────────────────── bottle ──────────────────────────────────┐
    │                                                                     │
-   │   ┌──────────────────┐                                              │
+   │   ┌──────────────────┐                   ┌──────────────┐           │
-   │   │ agent image      │  HTTPS_PROXY                                 │
+   │   │ agent image      │   HTTP(S) proxy   │ cred-proxy   │           │
-   │   │ (claude-code,    │ ────────────────────────┐                    │
+   │   │ (claude-code,    │ ─────────────────►│ (strips/inj  │           │
-   │   │  built locally)  │                         │                    │
+   │   │  codex, etc)     │                   │  Authoriz.)  │           │
-   │   │                  │   plain HTTP            │                    │
+   │   │                  │                   └──────┬───────┘           │
-   │   │ skills, env,     │  (token injection) ┌────▼─────────┐          │
+   │   │ environ: URLs    │                          │                   │
-   │   │ ~/.gitconfig,    │ ──────────────────►│ cred-proxy   │          │
+   │   │ only, no real    │                          ▼                   │
-   │   │ ~/.npmrc, tea    │                    │ (strips/inj  │          │
+   │   │ tokens           │                  ┌────────────────┐          │  HTTPS to
-   │   │                  │                    │  Authoriz.)  │          │
-   │   │ environ: URLs    │                    └─────┬────────┘          │
-   │   │ only, no real    │     HTTPS_PROXY          │                   │
-   │   │ tokens           │                          ▼                   │
-   │   │                  │                  ┌────────────────┐          │  HTTPS to
    │   │                  │                  │ pipelock image │──────────┼──►  allowlisted
    │   │                  │                  │ (TLS bump, DLP │          │     hosts (incl.
    │   │                  │                  │  body scan,    │          │      cred-proxy
    │   │                  │                  │  allowlist)    │          │      upstreams)
    │   │                  │                  └────────────────┘          │
    │   │                  │                                              │
-   │   │                  │   git://         ┌────────────────┐          │  SSH push/fetch
+   │   │                  │    git proxy     ┌────────────────┐          │  SSH push/fetch
    │   │                  │ ────────────────►│ git-gate image │──────────┼──►  to bottle.git
    │   │                  │                  │ (gitleaks +    │          │      upstreams
    │   └──────────────────┘                  │  git daemon)   │          │     (direct — not
@@ -137,192 +62,25 @@ and MCP endpoints resolve without an agent-side change.
    └─────────────────────────────────────────────────────────────────────┘
 ```
 
-- **agent image** — built from the provider template Dockerfile
+When the agent exits, `cli.py` tears down every sidecar and both networks; nothing about a bottle persists between runs.
-  (`Dockerfile.claude` for Claude, `Dockerfile.codex` for Codex, or
-  `agent_provider.dockerfile`) on first run; runs the selected agent
-  CLI with the manifest-granted skills, env vars, and `~/.gitconfig`
-  (the latter for the git-gate's `insteadOf` rules when `bottle.git`
-  is set).
-- **pipelock image** — per-agent sidecar. Terminates the agent's
-  outbound HTTP/HTTPS, enforces the resolved allowlist, runs DLP
-  scanning. Design in `docs/prds/0001-per-agent-egress-proxy-via-pipelock.md`
-  and `docs/prds/0006-pipelock-tls-interception.md`.
-- **git-gate image** — per-agent sidecar built on `zricethezav/gitleaks`
-  (alpine + gitleaks + git-daemon + openssh-client). Runs
-  `git daemon` over `git://` as a bidirectional mirror of each
-  declared upstream. A pre-receive hook gitleaks-scans incoming
-  refs and forwards clean refs to the real upstream over SSH; an
-  access-hook runs `git fetch origin --prune` against the upstream
-  before every upload-pack so an agent fetch returns whatever the
-  upstream has *now* (fail-closed if unreachable). The agent's
-  `~/.gitconfig` rewrites the real URL to the gate via `insteadOf`,
-  so push, fetch, clone, and pull all route through. The agent
-  never sees the upstream credential. Brought up only when
-  `bottle.git` has entries. Design in `docs/prds/0008-git-gate.md`.
-- **cred-proxy image** — per-bottle sidecar (`python:3.13-alpine`
-  base, stdlib-only) that holds API tokens declared in
-  `bottle.cred_proxy.routes`. Each route names a `path`,
-  `upstream`, `auth_scheme`, and `token_ref` (host env var); the
-  agent dials `http://cred-proxy:9099<path>...` over plain HTTP
-  and the proxy strips any inbound `Authorization`, injects
-  `<auth_scheme> <token>` using the value held only in its own
-  container's environ, and forwards to the real upstream over
-  HTTPS. SSE responses stream back unbuffered. The cred-proxy's
-  outbound HTTPS routes through pipelock (it trusts pipelock's
-  per-bottle CA), so pipelock's egress allowlist + body scanner
-  apply to cred-proxy traffic the same way they apply to direct
-  agent traffic. Smart-HTTP push paths (`/git-receive-pack`,
-  `/info/refs?service=git-receive-pack`) are refused at the
-  proxy — push must go through `bottle.git` / git-gate where
-  gitleaks runs. Optional per-route `role` tags drive agent-side
-  rewrites: `anthropic-base-url`, `npm-registry`, `git-insteadof`,
-  `tea-login`. The agent's `printenv` shows only proxy URLs —
-  none of the real token values. Design in
-  `docs/prds/0010-cred-proxy.md`.
-
-When the agent exits, `cli.py` tears down every sidecar that was
-brought up and the two networks; nothing about a bottle persists
-between runs.
 
 ## Quickstart
 
-Requires Docker on the host and a long-lived Claude Code OAuth token in
+Requires Docker on the host and a long-lived Claude Code OAuth token (`claude setup-token`) exported as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`.
-your shell env.
 
 ```sh
 ./cli.py start <agent>   # builds the image on first run, drops you into claude
 ```
 
-The container is removed automatically when the session ends. If the script
-is killed with SIGKILL the exit trap won't fire and the container may be
-left running; remove it with `docker rm -f <container-name>`.
-
-### Smolmachines backend (experimental, macOS-only)
-
-A second backend runs the agent in a smolvm micro-VM (libkrun) with the
-sidecar bundle still in Docker. Selected via
-`BOT_BOTTLE_BACKEND=smolmachines ./cli.py start <agent>`. Requires
-`smolvm` on PATH (`curl -sSL https://smolmachines.com/install.sh | sh`).
-
-The integration tests run against whichever backend the env var
-selects and skip cleanly when its prerequisites are missing.
-
-**One-time sudo on first launch (macOS):** smolmachines bottles
-each reserve a loopback alias from a pool (`127.0.0.16` ..
-`127.0.0.31`) and bind their bundle's port-forwards to it; the
-first `./cli.py start` after each reboot prompts for sudo to add
-missing aliases via `ifconfig lo0 alias`. Aliases persist until
-reboot; subsequent launches don't prompt. The agent's TSI
-allowlist is the alias's `/32`, so each bottle can only reach
-its own bundle's published ports — not other bottles' ports,
-not other host loopback services (postgres, dev servers, etc.).
-
-This enforcement requires a workaround for a smolvm 0.8.0 bug:
-the CLI's `--allow-cidr` flag is silently dropped when combined
-with `--from <smolmachine>`. The launcher patches smolvm's
-persistent state DB
-(`~/Library/Application Support/smolvm/server/smolvm.db`)
-directly between `machine create` and `machine start` to set
-the allowlist. The hack falls away automatically when smolvm
-honors the flag upstream — see the `loopback_alias` module's
-docstring for the investigation trail.
-
 ## Manifest
 
-Bottles and agents live as Markdown files with YAML frontmatter under
+Bottles and agents are Markdown files with YAML frontmatter under `~/.bot-bottle/`. The Markdown body is the system prompt. Bottles live in `~/.bot-bottle/bottles/`; agents may also be shipped by a repo at `<repo>/.bot-bottle/agents/<name>.md`.
-`~/.bot-bottle/`. Each bottle is one file in `bottles/`, each agent
-is one file in `agents/`:
 
-```
+**Bottle** (`~/.bot-bottle/bottles/gitea-dev.md`):
-~/.bot-bottle/
-├── bottles/
-│   ├── dev.md
-│   └── gitea-dev.md
-└── agents/
-    ├── implementer.md
-    └── researcher.md
-```
-
-The filename (without `.md`) is the entity's name. Filenames must
-match `[a-z][a-z0-9-]*`; files that don't are skipped with a warning.
-
-A repo can ship its own agent files alongside its code at
-`<repo>/.bot-bottle/agents/<name>.md`. Those agents reference
-bottles defined in `~/.bot-bottle/bottles/` (the only place
-bottles can come from); a `bottles/` subdir in a repo is ignored
-with a warning. **This is the trust boundary**: bottle infrastructure
-— credentials, egress allowlists, git remotes — comes from your home
-directory only. A cloned repo cannot redirect a host env var to an
-attacker-named upstream because it has no way to declare a bottle.
-
-### Bottle composition with `extends:`
-
-A bottle can inherit from another via `extends: <bottle-name>` so
-operators don't have to duplicate a whole bottle file to vary one
-field (PRD 0025). The parent's resolved config is the base; the
-child's declared fields overlay. Merge rules:
-
-- `env:` — dict merge, child wins on key collision.
-- `git.user:` — per-field overlay (child's non-empty `name` /
-  `email` wins; empty falls through to parent).
-- `git.remotes:` — dict merge by host, child wins on host collision.
-  An explicit `git.remotes: {}` clears the parent's remotes; omitting
-  `git.remotes` inherits the parent's remotes.
-- `agent_provider:`, `egress:`, `supervise:` — full replace when the
-  child declares the field.
-
-```yaml
----
-extends: dev          # inherit everything from bottles/dev.md
-egress:
-  routes:
-    - host: staging.example.com
-      auth:
-        scheme: Bearer
-        token_ref: STAGING_TOKEN
----
-```
-
-Cycles (`A extends B extends A`), self-references, and missing
-parents die at parse with a clear pointer. Bottles remain
-`$HOME`-only — `extends:` preserves the trust boundary above.
-
-### Provider base bottles
-
-Keep provider/runtime policy in one home-owned base bottle, then have
-task bottles extend it. That keeps provider egress/auth in one place
-without hiding security-relevant routes behind `agent_provider.template`.
-
-For example, `~/.bot-bottle/bottles/claude.md` can hold the Claude
-provider selection and Anthropic API egress:
 
 ````markdown
 ---
-agent_provider:
+extends: claude          # inherit the Claude provider boundary
-  template: claude
-
-egress:
-  routes:
-    - host: api.anthropic.com
-      role: claude_code_oauth
-      auth:
-        scheme: Bearer
-        token_ref: BOT_BOTTLE_CLAUDE_OAUTH_TOKEN
-      pipelock:
-        tls_passthrough: true
----
-
-Common Claude provider boundary.
-````
-
-Task bottles can then inherit that provider boundary and add their own
-env/git configuration without repeating the Claude route.
-
-### Example bottle (`~/.bot-bottle/bottles/gitea-dev.md`)
-
-````markdown
----
-extends: claude
 
 env:
   GIT_AUTHOR_NAME: didericis
@@ -337,148 +95,7 @@ git:
       Upstream: ssh://git@gitea.dideric.is:30009/didericis/bot-bottle.git
       IdentityFile: /Users/didericis/.ssh/id_ed25519_gitea
       KnownHostKey: ssh-ed25519 AAAA...
----
 
-The `gitea-dev` bottle. Backs my work on personal projects: provider
-auth through egress and gitea.dideric.is over SSH.
-````
-
-For a Codex-backed base bottle, set `agent_provider.template: codex`.
-The Codex template expects ChatGPT/device login state instead of an
-`OPENAI_API_KEY` env var; no API-key placeholder is forwarded into the
-agent. To let bot-bottle read the host's current Codex ChatGPT access
-token and inject it from egress only for Codex's API calls, opt in
-explicitly:
-
-```yaml
-agent_provider:
-  template: codex
-  forward_host_credentials: true
-
-egress:
-  routes:
-    - host: auth.openai.com
-      path_allowlist:
-        - /api/accounts/deviceauth/
-```
-
-Run `codex login --device-auth` on the host before launch. The
-launcher reads `tokens.access_token` from the host's
-`~/.codex/auth.json`, verifies it is fresh user/device auth, and passes
-it to the sidecar's `EGRESS_TOKEN_N` env slot. The agent container gets
-a dummy `~/.codex/auth.json` that preserves the host auth-mode shape
-but replaces credential values with placeholders. It keeps the selected
-ChatGPT account id so Codex sends requests for the same account while
-egress owns the real bearer token. The agent never receives real access
-tokens, refresh tokens, or `OPENAI_API_KEY`. The effective egress table
-automatically adds or upgrades `api.openai.com` and `chatgpt.com` to
-authenticated routes when `forward_host_credentials` is true.
-
-The built-in Codex template uses `Dockerfile.codex`; set
-`agent_provider.dockerfile` to build the agent from a custom Dockerfile
-while keeping the bot-bottle sidecars in place.
-
-### Example agent (`~/.bot-bottle/agents/gitea-helper.md`)
-
-````markdown
----
-bottle: gitea-dev
-skills:
-  - init-prd
-git:
-  user:
-    name: gitea-helper
-    email: eric+gitea-helper@dideric.is
----
-
-You help maintain Gitea-hosted projects.
-````
-
-The agent's Markdown body is its system prompt (whitespace
-stripped). The frontmatter declares the bottle to launch in and any
-skills to mount. You can also include Claude Code subagent fields
-(`name`, `description`, `model`, `color`, `memory`) in the
-frontmatter — bot-bottle ignores them at launch but doesn't
-reject them, so the same file can drop into `~/.claude/agents/` as a
-Claude Code subagent.
-
-An agent may also declare `git.user` (`name` / `email`). It overlays
-the referenced bottle's `git.user` per-field — the agent's non-empty
-fields win, the rest fall through to the bottle — so two agents can
-share one bottle and still commit under distinct identities without
-an identity-only bottle (PRD 0027). Only `git.user` is allowed at the
-agent level; `git.remotes` stays bottle-only because it carries
-credentials and host trust. The launch preflight and `cli.py info`
-print the effective identity annotated `(agent)` / `(bottle)` so you
-can see where each field came from. Git authorship is not a
-credential — push auth is the bottle's remote key/token — so a
-repo-shipped agent setting its own identity grants no access; treat
-an agent identity as *claimed, not vouched*.
-
-Unknown top-level frontmatter keys die at load with a "did you mean"
-pointer; typos don't silently ghost into an empty config.
-
-The YAML subset the frontmatter accepts is bounded (flat keys,
-strings / ints / true-or-false bools / null / lists / one-level
-nested dicts). Anchors, multi-line block scalars, tags, and
-ambiguous bare strings (`yes` / `NO` / `2026-05-24` /
-`0x...`) all die with a clear pointer at the spec — quote your
-strings when in doubt. The full schema lives in
-`bot_bottle/yaml_subset.py` (~450 lines, stdlib-only, no PyYAML).
-
-Working examples live under `examples/`. Pipelock's design lives in
-`docs/prds/0001-per-agent-egress-proxy-via-pipelock.md` and the
-rationale in `docs/research/pipelock-assessment.md`. The trust
-boundary rationale lives in `docs/prds/0011-per-file-md-manifest.md`.
-
-## Auth: Claude OAuth token, not API key
-
-Bottles that use `agent_provider.template: claude` authenticate
-`claude` inside the container with the same Pro/Max subscription you
-already use on the host, via a long-lived OAuth token. No
-`ANTHROPIC_API_KEY` is needed.
-
-**Why a token instead of mounting `~/.claude.json`:** on macOS, Claude
-Code stores OAuth credentials in the encrypted Keychain, not in
-`~/.claude.json`. Mounting that file into a Linux container does not
-carry the credentials with it. Linux hosts keep credentials in
-`~/.claude/.credentials.json`, but to keep the launcher portable
-bot-bottle uses the env-var path on every host.
-
-**One-time setup on the host:**
-
-```sh
-claude setup-token   # browser login, prints a ~1-year OAuth token
-```
-
-Stash the token in your shell env (e.g. `~/.zshrc` or a secret manager)
-as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`:
-
-```sh
-export BOT_BOTTLE_CLAUDE_OAUTH_TOKEN="<token>"
-```
-
-The Claude bottle reaches the Anthropic API only through the cred-proxy
-sidecar. To let `claude` authenticate, declare an egress route with
-`role: claude_code_oauth` and
-`token_ref: BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`:
-
-```yaml
-egress:
-  routes:
-    - host: api.anthropic.com
-      role: claude_code_oauth
-      auth:
-        scheme: Bearer
-        token_ref: BOT_BOTTLE_CLAUDE_OAUTH_TOKEN
-      pipelock:
-        tls_passthrough: true
-```
-
-Routes that resolve to private or Tailscale addresses can opt into
-pipelock's SSRF destination allowlist explicitly:
-
-```yaml
 egress:
   routes:
     - host: gitea.dideric.is
@@ -486,38 +103,31 @@ egress:
         scheme: token
         token_ref: BOT_BOTTLE_GITEA_TOKEN
       pipelock:
-        ssrf_ip_allowlist:
+        ssrf_ip_allowlist: [100.78.141.42/32]
-          - 100.78.141.42/32
+---
-```
 
-At launch, `cli.py` reads `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN` from the host
+The `gitea-dev` bottle. Provider auth via the inherited Claude route;
-env and forwards it into the cred-proxy container's environ — never
+gitea over SSH for push, token over HTTPS for the API.
-into the agent's. The agent receives `ANTHROPIC_BASE_URL` pointing at
+````
-`http://cred-proxy:9099/anthropic` and a non-secret placeholder for
-`CLAUDE_CODE_OAUTH_TOKEN` (claude-code refuses to start without one;
-the proxy strips and replaces the header on every request). `printenv`
-inside the agent does not surface the real token, and the value is
-never written to disk or placed on argv on the host.
 
-A Claude bottle without a `claude_code_oauth` route has no path to the
+**Agent** (`~/.bot-bottle/agents/gitea-helper.md`):
-Anthropic API — there is no fallback that forwards the token directly
+
-to the agent. Caveats: the token is bound to your subscription tier
+````markdown
-(Pro/Max/Team/Enterprise), it does not work with `claude --bare`
+---
-(which only reads `ANTHROPIC_API_KEY`), and if it leaks, regenerate
+bottle: gitea-dev
-via `claude setup-token` again. Reference:
+skills:
-<https://code.claude.com/docs/en/authentication>.
+  - init-prd
+---
+
+You help maintain Gitea-hosted projects.
+````
+
+More examples in `examples/`. Full design lives under `docs/prds/`; the trust-boundary rationale is in `docs/prds/0011-per-file-md-manifest.md`.
 
 ## Trademarks
 
-bot-bottle is an independent project and is not affiliated with,
+bot-bottle is an independent project and is not affiliated with, endorsed by, or sponsored by Anthropic, PBC. "Claude" and "Claude Code" are trademarks of Anthropic, PBC; the project name uses "claude" descriptively to indicate that the tool runs Claude Code inside a sandbox.
-endorsed by, or sponsored by Anthropic, PBC. "Claude" and "Claude
-Code" are trademarks of Anthropic, PBC; the project name uses
-"claude" descriptively to indicate that the tool runs Claude Code
-inside a sandbox.
 
 ## License
 
-Copyright 2026 Eric Bauerfeld
+Copyright 2026 Eric Bauerfeld. Licensed under the Apache License, Version 2.0. See [LICENSE](LICENSE) for the full text.
-
-Licensed under the Apache License, Version 2.0. See [LICENSE](LICENSE)
-for the full text.

bot_bottle/agent_provider.py

@@ -3,18 +3,32 @@
 The manifest owns the user-facing AgentProvider shape. This module is
 the launch-time table that turns a provider template into an executable
 command, default image, and prompt/auth behavior.
+
+Per PRD 0050 the per-provider implementations live under
+`bot_bottle/contrib/<template>/agent_provider.py`. This module exposes:
+
+  - `AgentProvider` (ABC) — the contract each plugin implements.
+  - `get_provider(template)` — lazy-imported registry; the analogue
+    of `bot_bottle/deploy_key_provisioner.get_provisioner`.
+  - `AgentProvisionPlan` (+ helper dataclasses) — declarative shape
+    each provider produces and the backends consume unchanged.
+  - `agent_provision_plan` / `runtime_for` — thin wrappers around the
+    registry kept so existing callers keep working without per-call
+    edits.
 """
 
 from __future__ import annotations
 
-import json
+from abc import ABC, abstractmethod
-import os
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Literal
+from typing import TYPE_CHECKING, Literal
 
-from .codex_auth import codex_host_access_token, write_codex_dummy_auth_file
+from .egress import EgressRoute
-from .egress import CODEX_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
+
+
+if TYPE_CHECKING:
+    from .backend import Bottle, BottlePlan
 
 
 PROVIDER_CLAUDE = "claude"
@@ -96,35 +110,88 @@ class AgentProvisionPlan:
     provisioned_env: dict[str, str] = field(default_factory=dict)
 
 
-_REPO_ROOT = Path(__file__).resolve().parent.parent
+class AgentProvider(ABC):
+    """Per-template plugin: produces the provision plan and applies
+    the provider-specific in-guest setup steps (skills, prompt, the
+    declarative `dirs`/`files`/`pre_copy`/`verify` apply loop, and
+    supervise MCP registration). Concrete subclasses live under
+    `bot_bottle/contrib/<template>/agent_provider.py`."""
+
+    @property
+    @abstractmethod
+    def runtime(self) -> AgentProviderRuntime:
+        """The static command / image / prompt-mode table for this
+        template."""
+
+    @abstractmethod
+    def provision_plan(
+        self,
+        *,
+        dockerfile: str,
+        state_dir: Path,
+        guest_home: str,
+        guest_env: dict[str, str] | None = None,
+        auth_token: str = "",
+        forward_host_credentials: bool = False,
+        host_env: dict[str, str] | None = None,
+        trusted_project_path: str = "",
+    ) -> AgentProvisionPlan:
+        """Build the declarative AgentProvisionPlan for one launch.
+        Backends call this during `prepare` and consume the result as
+        before."""
+
+    @abstractmethod
+    def provision_skills(self, plan: "BottlePlan", bottle: "Bottle") -> None:
+        """Copy each of the agent's named skills from the host into
+        the guest. No-op when the agent has no skills. The in-guest
+        layout is provider-specific (claude-code's
+        `~/.claude/skills/` today; future providers may differ)."""
+
+    @abstractmethod
+    def provision_prompt(self, plan: "BottlePlan", bottle: "Bottle") -> str | None:
+        """Copy the prompt file into the guest, fix ownership/mode,
+        and return the in-guest path iff the agent has a non-empty
+        prompt (drives the `--append-system-prompt-file` flag).
+
+        The file is copied either way so the path always exists."""
+
+    @abstractmethod
+    def provision(self, plan: "BottlePlan", bottle: "Bottle") -> None:
+        """Apply the provider's declarative
+        `dirs`/`pre_copy`/`files`/`verify` steps from
+        `plan.agent_provision`. Was called `provision_provider_auth`
+        on `BottleBackend` before PRD 0050."""
+
+    @abstractmethod
+    def provision_supervise_mcp(
+        self,
+        plan: "BottlePlan",
+        bottle: "Bottle",
+        supervise_url: str,
+    ) -> None:
+        """Register the per-bottle supervise sidecar as an MCP server
+        in the provider's in-guest config. Called by the backend after
+        the supervise sidecar is reachable. No-op when
+        `plan.supervise_plan is None`."""
 
 
-_RUNTIMES = {
+def get_provider(template: str) -> AgentProvider:
-    PROVIDER_CLAUDE: AgentProviderRuntime(
+    """Resolve a provider template name to its plugin instance.
-        template=PROVIDER_CLAUDE,
+
-        command="claude",
+    Lazy-imports the contrib module so importing this module doesn't
-        image="bot-bottle-claude:latest",
+    pull provider-specific code paths in. Mirrors the contrib
-        dockerfile=str(_REPO_ROOT / "Dockerfile.claude"),
+    convention PRD 0048 established for deploy key provisioners."""
-        prompt_mode="append_file",
+    if template == PROVIDER_CLAUDE:
-        bypass_args=("--dangerously-skip-permissions",),
+        from .contrib.claude.agent_provider import ClaudeAgentProvider
-        resume_args=("--continue",),
+        return ClaudeAgentProvider()
-        remote_control_args=("--remote-control",),
+    if template == PROVIDER_CODEX:
-    ),
+        from .contrib.codex.agent_provider import CodexAgentProvider
-    PROVIDER_CODEX: AgentProviderRuntime(
+        return CodexAgentProvider()
-        template=PROVIDER_CODEX,
+    raise ValueError(f"unknown agent provider template: {template!r}")
-        command="codex",
-        image="bot-bottle-codex:latest",
-        dockerfile=str(_REPO_ROOT / "Dockerfile.codex"),
-        prompt_mode="read_prompt_file",
-        bypass_args=("--dangerously-bypass-approvals-and-sandbox",),
-        resume_args=("resume", "--last"),
-        remote_control_args=(),
-    ),
-}
 
 
 def runtime_for(template: str) -> AgentProviderRuntime:
-    return _RUNTIMES[template]
+    return get_provider(template).runtime
 
 
 def agent_provision_plan(
@@ -132,118 +199,24 @@ def agent_provision_plan(
     template: str,
     dockerfile: str,
     state_dir: Path,
-    guest_home: str = "/home/node",
+    guest_home: str,
     guest_env: dict[str, str] | None = None,
     auth_token: str = "",
     forward_host_credentials: bool = False,
     host_env: dict[str, str] | None = None,
     trusted_project_path: str = "",
 ) -> AgentProvisionPlan:
-    runtime = runtime_for(template)
+    """Back-compat shim — `prepare` callers stay the same; the work
-    resolved_guest_env = dict(guest_env or {})
+    now lives on the provider plugin."""
-    trusted_path = trusted_project_path or guest_home
+    return get_provider(template).provision_plan(
-    env_vars: dict[str, str] = {}
-    provisioned_env: dict[str, str] = {}
-    dirs: list[AgentProvisionDir] = []
-    files: list[AgentProvisionFile] = []
-    pre_copy: list[AgentProvisionCommand] = []
-    verify: list[AgentProvisionCommand] = []
-    egress_routes: list[EgressRoute] = []
-    hidden_env_names: frozenset[str] = frozenset()
-
-    if template == PROVIDER_CODEX:
-        env_vars["CODEX_CA_CERTIFICATE"] = "/etc/ssl/certs/ca-certificates.crt"
-        auth_dir = resolved_guest_env.get("CODEX_HOME", f"{guest_home}/.codex")
-        if forward_host_credentials:
-            env_vars["CODEX_HOME"] = auth_dir
-        dirs.append(AgentProvisionDir(auth_dir))
-        config_path = f"{auth_dir}/config.toml"
-        config_file = state_dir / "codex-config.toml"
-        toml_path = trusted_path.replace("\\", "\\\\").replace('"', '\\"')
-        config_file.write_text(
-            f'[projects."{toml_path}"]\n'
-            'trust_level = "trusted"\n'
-        )
-        config_file.chmod(0o600)
-        files.append(AgentProvisionFile(config_file, config_path))
-
-        for host in CODEX_HOST_CREDENTIAL_HOSTS:
-            egress_routes.append(EgressRoute(
-                host=host,
-                auth_scheme="Bearer" if forward_host_credentials else "",
-                token_ref=CODEX_HOST_CREDENTIAL_TOKEN_REF if forward_host_credentials else "",
-                tls_passthrough=True,
-            ))
-        if forward_host_credentials:
-            _host_env = host_env or dict(os.environ)
-            provisioned_env[CODEX_HOST_CREDENTIAL_TOKEN_REF] = codex_host_access_token(
-                _host_env,
-            )
-            auth_file = state_dir / "codex-auth.json"
-            write_codex_dummy_auth_file(auth_file, _host_env)
-            files.append(AgentProvisionFile(auth_file, f"{auth_dir}/auth.json"))
-            pre_copy.append(AgentProvisionCommand((
-                "find", auth_dir,
-                "-maxdepth", "1",
-                "-type", "f",
-                "(",
-                "-name", "*.sqlite",
-                "-o", "-name", "*.sqlite-*",
-                "-o", "-name", "*.codex-repair-*.bak",
-                ")",
-                "-delete",
-            ), "codex host credentials: could not reset runtime db files"))
-            verify.append(AgentProvisionCommand((
-                "runuser", "-u", "node", "--",
-                "env",
-                f"HOME={guest_home}",
-                f"CODEX_HOME={auth_dir}",
-                "codex", "login", "status",
-            ), (
-                "codex host credentials: dummy auth was copied into the "
-                "guest, but Codex did not accept it"
-            )))
-    if template == PROVIDER_CLAUDE:
-        env_vars["CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC"] = "1"
-        env_vars["DISABLE_ERROR_REPORTING"] = "1"
-        claude_config = state_dir / "claude.json"
-        claude_projects = {
-            guest_home: {"hasTrustDialogAccepted": True},
-        }
-        claude_projects[trusted_path] = {"hasTrustDialogAccepted": True}
-        claude_config.write_text(json.dumps({
-            "hasCompletedOnboarding": True,
-            "theme": "dark",
-            "bypassPermissionsModeAccepted": True,
-            "projects": claude_projects,
-        }, indent=2) + "\n")
-        claude_config.chmod(0o600)
-        files.append(AgentProvisionFile(claude_config, f"{guest_home}/.claude.json"))
-        egress_routes.append(EgressRoute(
-            host="api.anthropic.com",
-            auth_scheme="Bearer" if auth_token else "",
-            token_ref=auth_token,
-            tls_passthrough=True,
-        ))
-        if auth_token:
-            env_vars["CLAUDE_CODE_OAUTH_TOKEN"] = "egress-placeholder"
-            hidden_env_names = frozenset({"CLAUDE_CODE_OAUTH_TOKEN"})
-
-    return AgentProvisionPlan(
-        template=template,
-        command=runtime.command,
-        prompt_mode=runtime.prompt_mode,
-        image=runtime.image,
         dockerfile=dockerfile,
-        env_vars=env_vars,
+        state_dir=state_dir,
-        guest_env=resolved_guest_env,
+        guest_home=guest_home,
-        dirs=tuple(dirs),
+        guest_env=guest_env,
-        files=tuple(files),
+        auth_token=auth_token,
-        pre_copy=tuple(pre_copy),
+        forward_host_credentials=forward_host_credentials,
-        verify=tuple(verify),
+        host_env=host_env,
-        egress_routes=tuple(egress_routes),
+        trusted_project_path=trusted_project_path,
-        hidden_env_names=hidden_env_names,
-        provisioned_env=provisioned_env,
     )
 
 

bot_bottle/backend/__init__.py

@@ -39,7 +39,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, Generic, Sequence, TypeVar
 
-from ..agent_provider import AgentProvisionPlan
+from ..agent_provider import AgentProvisionPlan, get_provider
 from ..egress import EgressPlan
 from ..git_gate import GitGatePlan
 from ..log import die, info
@@ -76,6 +76,7 @@ class BottlePlan(ABC):
 
     spec: BottleSpec
     stage_dir: Path
+    guest_home: str
     git_gate_plan: GitGatePlan
     egress_plan: EgressPlan
     supervise_plan: SupervisePlan | None
@@ -312,37 +313,44 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
     def launch(self, plan: PlanT) -> AbstractContextManager[Bottle]:
         """Build/run the bottle and yield a handle; tear down on exit."""
 
-    def provision(self, plan: PlanT, target: str) -> str | None:
+    def provision(self, plan: PlanT, bottle: "Bottle") -> str | None:
         """Copy host-side files (CA cert, prompt, skills, .git) into
         the running bottle. Called from `launch` after the container
-        / machine is up. `target` identifies the running instance in
+        / machine is up. Returns the in-container prompt path if a
-        backend-specific terms (Docker: resolved container name; fly:
+        prompt was provisioned, else None — the Bottle handle uses it
-        machine id). Returns the in-container prompt path if a prompt
+        to decide whether to add provider-specific prompt args to the
-        was provisioned, else None — the Bottle handle uses it to
+        agent's argv.
-        decide whether to add provider-specific prompt args to the agent's
-        argv.
 
-        Default orchestration: ca → prompt → skills → workspace → git →
+        Default orchestration: ca → prompt → provider apply → skills
-        supervise. CA install runs first so the agent's trust store
+        → workspace → git → supervise-mcp. CA install runs first so
-        is rebuilt before anything inside the agent makes a TLS call.
+        the agent's trust store is rebuilt before anything inside the
-        Subclasses typically don't override this; they implement the
+        agent makes a TLS call.
-        sub-methods below.
+
+        Per PRD 0050 the per-provider steps (prompt, skills,
+        declarative provision-plan apply, supervise MCP registration)
+        live on the `AgentProvider` plugin. The backend only owns the
+        steps that are about backend infrastructure (CA, workspace,
+        git) and surfaces the supervise sidecar URL its launch step
+        knows about via `supervise_mcp_url`.
 
         PRD 0017: cred-proxy's agent-side dotfile rewrites (~/.npmrc,
         ~/.gitconfig insteadOf, tea config) are gone. Egress-proxy is
         on the agent's HTTP_PROXY path so every tool that respects
         HTTPS_PROXY (claude-code, git over HTTPS, npm, curl) is
         intercepted without per-tool reconfiguration."""
-        self.provision_ca(plan, target)
+        provider = get_provider(plan.agent_provision.template)
-        prompt_path = self.provision_prompt(plan, target)
+        self.provision_ca(plan, bottle)
-        self.provision_provider_auth(plan, target)
+        prompt_path = provider.provision_prompt(plan, bottle)
-        self.provision_skills(plan, target)
+        provider.provision(plan, bottle)
-        self.provision_workspace(plan, target)
+        provider.provision_skills(plan, bottle)
-        self.provision_git(plan, target)
+        self.provision_workspace(plan, bottle)
-        self.provision_supervise(plan, target)
+        self.provision_git(plan, bottle)
+        provider.provision_supervise_mcp(
+            plan, bottle, self.supervise_mcp_url(plan),
+        )
         return prompt_path
 
-    def provision_ca(self, plan: PlanT, target: str) -> None:
+    def provision_ca(self, plan: PlanT, bottle: "Bottle") -> None:
         """Install the per-bottle CA into the agent's trust store so
         the agent trusts the bumped CONNECT cert egress (was
         pipelock, pre-PRD-0017) presents. Default impl is a no-op so
@@ -351,39 +359,26 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         backend overrides to docker-cp the cert in and run
         `update-ca-certificates`."""
 
-    def provision_provider_auth(self, plan: PlanT, target: str) -> None:
+    def provision_workspace(self, plan: PlanT, bottle: "Bottle") -> None:
-        """Install non-secret provider auth marker files into the agent
-        home when a provider needs them to select the right auth mode.
-        The default is no-op."""
-
-    @abstractmethod
-    def provision_prompt(self, plan: PlanT, target: str) -> str | None:
-        """Copy the prompt file into the running bottle. Returns the
-        in-container path iff the agent has a non-empty prompt;
-        callers use the return value to decide whether to add
-        provider-specific prompt args to the agent's argv."""
-
-    @abstractmethod
-    def provision_skills(self, plan: PlanT, target: str) -> None:
-        """Copy the agent's named skills from the host into the
-        running bottle. No-op when the agent has no skills."""
-
-    def provision_workspace(self, plan: PlanT, target: str) -> None:
         """Copy the operator workspace into the running bottle when
         the backend cannot bake it into the agent image. Default is
         no-op for backends like Docker that handle this before launch."""
 
     @abstractmethod
-    def provision_git(self, plan: PlanT, target: str) -> None:
+    def provision_git(self, plan: PlanT, bottle: "Bottle") -> None:
         """Copy the host's cwd `.git` directory into the running
         bottle if the user requested --cwd. No-op otherwise."""
 
-    def provision_supervise(self, plan: PlanT, target: str) -> None:
+    def supervise_mcp_url(self, plan: PlanT) -> str:
-        """Write the in-bottle Claude Code MCP config so the agent
+        """Return the agent-side URL of the per-bottle supervise
-        discovers the per-bottle supervise sidecar (PRD 0013).
+        sidecar, or "" when this bottle has no sidecar. The provider
-        No-op when bottle.supervise is False or the backend doesn't
+        plugin's `provision_supervise_mcp` uses it to register the
-        support the supervise sidecar yet. The Docker backend
+        MCP entry inside the guest.
-        overrides."""
+
+        Default returns "" so backends without supervise support
+        don't have to implement it. Docker and smolmachines override."""
+        del plan
+        return ""
 
     @abstractmethod
     def prepare_cleanup(self) -> CleanupT:

bot_bottle/backend/docker/backend.py

@@ -9,6 +9,12 @@ This module is a thin façade. The real work lives in four siblings:
 
 The base class's `prepare` template runs cross-backend host-side
 validation before calling `_resolve_plan` here.
+
+Per PRD 0050 the per-provider provisioning steps (prompt, skills,
+the declarative provision-plan apply, supervise MCP registration)
+live on the `AgentProvider` plugin under `bot_bottle/contrib/`. The
+Docker backend only owns the steps that are about backend
+infrastructure: CA install and git copy-in.
 """
 
 from __future__ import annotations
@@ -18,7 +24,8 @@ from contextlib import contextmanager
 from pathlib import Path
 from typing import Generator, Sequence
 
-from .. import ActiveAgent, BottleBackend, BottleSpec
+from ...supervise import SUPERVISE_HOSTNAME, SUPERVISE_PORT
+from .. import ActiveAgent, Bottle, BottleBackend, BottleSpec
 from . import cleanup as _cleanup
 from . import enumerate as _enumerate
 from . import launch as _launch
@@ -28,10 +35,6 @@ from .bottle_cleanup_plan import DockerBottleCleanupPlan
 from .bottle_plan import DockerBottlePlan
 from .provision import ca as _ca
 from .provision import git as _git
-from .provision import prompt as _prompt
-from .provision import provider_auth as _provider_auth
-from .provision import skills as _skills
-from .provision import supervise as _supervise_prov
 
 
 class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanupPlan"]):
@@ -57,23 +60,19 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
         with _launch.launch(plan, provision=self.provision) as bottle:
             yield bottle
 
-    def provision_ca(self, plan: DockerBottlePlan, target: str) -> None:
+    def provision_ca(self, plan: DockerBottlePlan, bottle: Bottle) -> None:
-        _ca.provision_ca(plan, target)
+        _ca.provision_ca(plan, bottle)
 
-    def provision_prompt(self, plan: DockerBottlePlan, target: str) -> str | None:
+    def provision_git(self, plan: DockerBottlePlan, bottle: Bottle) -> None:
-        return _prompt.provision_prompt(plan, target)
+        _git.provision_git(plan, bottle)
 
-    def provision_provider_auth(self, plan: DockerBottlePlan, target: str) -> None:
+    def supervise_mcp_url(self, plan: DockerBottlePlan) -> str:
-        _provider_auth.provision_provider_auth(plan, target)
+        """Docker bottles reach the supervise sidecar via the
-
+        compose-network alias `supervise:9100`. No per-bottle URL
-    def provision_skills(self, plan: DockerBottlePlan, target: str) -> None:
+        plumbing needed; the alias resolves inside the bridge."""
-        _skills.provision_skills(plan, target)
+        if plan.supervise_plan is None:
-
+            return ""
-    def provision_git(self, plan: DockerBottlePlan, target: str) -> None:
+        return f"http://{SUPERVISE_HOSTNAME}:{SUPERVISE_PORT}/"
-        _git.provision_git(plan, target)
-
-    def provision_supervise(self, plan: DockerBottlePlan, target: str) -> None:
-        _supervise_prov.provision_supervise(plan, target)
 
     def prepare_cleanup(self) -> DockerBottleCleanupPlan:
         return _cleanup.prepare_cleanup()

bot_bottle/backend/docker/launch.py

@@ -208,19 +208,21 @@ def launch(
             compose_dump_logs, project, compose_file, compose_log_path(state_dir),
         )
 
-        # Step 8: provision. Unchanged — uses `docker exec` against
+        # Step 8: provision. Create the bottle first so provisioners
-        # the agent container by its known name.
+        # can use bottle.exec / bottle.cp_in; set the prompt path
-        prompt_path = provision(plan, plan.container_name)
+        # returned by provision_prompt after the fact.
+        bottle = DockerBottle(
+            plan.container_name,
+            teardown,
+            None,
+            agent_command=plan.agent_command,
+            agent_prompt_mode=plan.agent_prompt_mode,
+        )
+        bottle._prompt_path = provision(plan, bottle)
 
         # Step 9: yield. exec_agent continues to use `docker exec -it`
         # — the agent runs `sleep infinity` per the renderer's
         # service spec.
-        yield DockerBottle(
+        yield bottle
-            plan.container_name,
-            teardown,
-            prompt_path,
-            agent_command=plan.agent_command,
-            agent_prompt_mode=plan.agent_prompt_mode,
-        )
     finally:
         teardown()

bot_bottle/backend/docker/prepare.py

@@ -63,7 +63,7 @@ def resolve_plan(
     bottle = manifest.bottle_for(spec.agent_name)
     provider = bottle.agent_provider
     provider_runtime = runtime_for(provider.template)
-    guest_home = os.environ.get("BOT_BOTTLE_CONTAINER_HOME", "/home/node")
+    guest_home = "/home/node"
     workspace_plan = resolve_workspace_plan(spec, guest_home=guest_home)
 
     # PRD 0016 follow-up: identity, not bare slug. A fresh `start`
@@ -233,6 +233,7 @@ def resolve_plan(
     return DockerBottlePlan(
         spec=spec,
         stage_dir=stage_dir,
+        guest_home=guest_home,
         slug=slug,
         container_name=container_name,
         container_name_pinned=container_name_pinned,

bot_bottle/backend/docker/provision/__init__.py

@@ -1,8 +1,11 @@
-"""Per-provisioner modules for the Docker backend.
+"""Backend-infrastructure provisioners for the Docker backend.
 
-Each module exports one top-level function:
+Per PRD 0050 the per-provider provisioning steps (prompt, skills,
-    provision_<thing>(plan: DockerBottlePlan, target: str) -> ...
+declarative provision-plan apply, supervise MCP registration) live on
+the `AgentProvider` plugin under `bot_bottle/contrib/`. The modules
+left in this subpackage handle only the steps that are
+backend-specific:
 
-`DockerBottleBackend.provision_*` methods delegate to these. The
+  - ca.py   — install per-bottle CA bundle into the guest trust store
-abstract `BottleBackend.provision_*` surface is unchanged; this
+  - git.py  — copy host cwd `.git` into the guest when --cwd is used
-subpackage exists only to keep `backend.py` from being a god-file."""
+"""

bot_bottle/backend/docker/provision/ca.py

@@ -31,33 +31,21 @@ stage dir; nothing in the agent ever sees it."""
 
 from __future__ import annotations
 
-import subprocess
+from ... import Bottle
-
 from ...util import AGENT_CA_PATH, log_ca_fingerprint, select_ca_cert
 from ..bottle_plan import DockerBottlePlan
 
 
-def provision_ca(plan: DockerBottlePlan, target: str) -> None:
+def provision_ca(plan: DockerBottlePlan, bottle: Bottle) -> None:
     """Copy the agent-facing CA cert into the agent, rebuild the
     trust bundle, emit a one-line fingerprint log. Called from
     `BottleBackend.provision` after the agent container is up."""
-    container = target
     cert_host_path, label = select_ca_cert(plan.egress_plan, plan.proxy_plan)
 
-    subprocess.run(
+    bottle.cp_in(str(cert_host_path), AGENT_CA_PATH)
-        ["docker", "cp", str(cert_host_path), f"{container}:{AGENT_CA_PATH}"],
+    bottle.exec(
-        stdout=subprocess.DEVNULL,
+        f"chmod 644 {AGENT_CA_PATH} && update-ca-certificates",
-        check=True,
+        user="root",
-    )
-    subprocess.run(
-        ["docker", "exec", "-u", "0", container, "chmod", "644", AGENT_CA_PATH],
-        stdout=subprocess.DEVNULL,
-        check=True,
-    )
-    subprocess.run(
-        ["docker", "exec", "-u", "0", container, "update-ca-certificates"],
-        stdout=subprocess.DEVNULL,
-        check=True,
     )
 
     log_ca_fingerprint(cert_host_path, label)

bot_bottle/backend/docker/provision/git.py

@@ -18,75 +18,62 @@ Three concerns, all about git in the agent:
 
 from __future__ import annotations
 
-import os
+import shlex
-import subprocess
 
 from ....git_gate import GIT_GATE_HOSTNAME, git_gate_render_gitconfig
 from ....log import info
-from .. import util as docker_mod
+from ... import Bottle
 from ..bottle_plan import DockerBottlePlan
 
 
-def provision_git(plan: DockerBottlePlan, target: str) -> None:
+def provision_git(plan: DockerBottlePlan, bottle: Bottle) -> None:
     """Set up git inside the bottle. Runs all three subcases; each
     no-ops when its condition isn't met."""
-    _provision_cwd_git(plan, target)
+    _provision_cwd_git(plan, bottle)
-    _provision_git_gate_config(plan, target)
+    _provision_git_gate_config(plan, bottle)
-    _provision_git_user(plan, target)
+    _provision_git_user(plan, bottle)
 
 
-def _provision_cwd_git(plan: DockerBottlePlan, target: str) -> None:
+def _provision_cwd_git(plan: DockerBottlePlan, bottle: Bottle) -> None:
     """If --cwd was set and the host cwd has a .git directory, copy
     it into /home/node/workspace/.git and fix ownership. No-op
     otherwise."""
     workspace = plan.workspace_plan
     if not (workspace.enabled and workspace.copy_git and workspace.has_host_git_dir):
         return
-    container = target
     guest_workspace_git = f"{workspace.guest_path}/.git"
     host_git = str(workspace.host_path / ".git")
-    info(f"copying {host_git} -> {container}:{guest_workspace_git}")
+    info(f"copying {host_git} -> {bottle.name}:{guest_workspace_git}")
-    subprocess.run(
+    bottle.cp_in(host_git, guest_workspace_git)
-        ["docker", "cp", host_git, f"{container}:{guest_workspace_git}"],
+    bottle.exec(
-        stdout=subprocess.DEVNULL,
+        f"chown -R {shlex.quote(workspace.owner)} {shlex.quote(guest_workspace_git)}",
-        check=True,
+        user="root",
-    )
-    subprocess.run(
-        [
-            "docker", "exec", "-u", "0", container,
-            "chown", "-R", workspace.owner, guest_workspace_git,
-        ],
-        stdout=subprocess.DEVNULL,
-        check=True,
     )
 
 
-def _provision_git_gate_config(plan: DockerBottlePlan, target: str) -> None:
+def _provision_git_gate_config(plan: DockerBottlePlan, bottle: Bottle) -> None:
     """Write ~/.gitconfig in the bottle with the git-gate
     insteadOf rules. No-op when the bottle has no `git` entries."""
-    bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
+    manifest_bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
-    if not bottle.git:
+    if not manifest_bottle.git:
         return
-    container = target
+    container_gitconfig = f"{plan.guest_home}/.gitconfig"
-    container_home = os.environ.get("BOT_BOTTLE_CONTAINER_HOME", "/home/node")
-    container_gitconfig = f"{container_home}/.gitconfig"
 
-    content = git_gate_render_gitconfig(bottle.git, GIT_GATE_HOSTNAME)
+    content = git_gate_render_gitconfig(manifest_bottle.git, GIT_GATE_HOSTNAME)
     config_file = plan.stage_dir / "agent_gitconfig"
     config_file.write_text(content)
     config_file.chmod(0o600)
 
-    info(f"writing {container_gitconfig} with {len(bottle.git)} insteadOf rule(s)")
+    info(f"writing {container_gitconfig} with {len(manifest_bottle.git)} insteadOf rule(s)")
-    subprocess.run(
+    bottle.cp_in(str(config_file), container_gitconfig)
-        ["docker", "cp", str(config_file), f"{container}:{container_gitconfig}"],
+    bottle.exec(
-        stdout=subprocess.DEVNULL,
+        f"chown node:node {shlex.quote(container_gitconfig)} && "
-        check=True,
+        f"chmod 644 {shlex.quote(container_gitconfig)}",
+        user="root",
     )
-    docker_mod.docker_exec_root(container, ["chown", "node:node", container_gitconfig])
-    docker_mod.docker_exec_root(container, ["chmod", "644", container_gitconfig])
 
 
-def _provision_git_user(plan: DockerBottlePlan, target: str) -> None:
+def _provision_git_user(plan: DockerBottlePlan, bottle: Bottle) -> None:
     """Apply `git config --global user.{name,email}` inside the
     bottle so the agent's commits are attributed to the operator-
     chosen identity instead of the agent image's default
@@ -101,23 +88,19 @@ def _provision_git_user(plan: DockerBottlePlan, target: str) -> None:
     Each field set independently — name-only or email-only
     configs only run the `git config` line for the field
     present."""
-    bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
+    manifest_bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
-    gu = bottle.git_user
+    gu = manifest_bottle.git_user
     if gu.is_empty():
         return
     if gu.name:
         info(f"git config --global user.name = {gu.name!r}")
-        subprocess.run(
+        bottle.exec(
-            ["docker", "exec", "-u", "node", target,
+            f"git config --global user.name {shlex.quote(gu.name)}",
-             "git", "config", "--global", "user.name", gu.name],
+            user="node",
-            stdout=subprocess.DEVNULL,
-            check=True,
         )
     if gu.email:
         info(f"git config --global user.email = {gu.email!r}")
-        subprocess.run(
+        bottle.exec(
-            ["docker", "exec", "-u", "node", target,
+            f"git config --global user.email {shlex.quote(gu.email)}",
-             "git", "config", "--global", "user.email", gu.email],
+            user="node",
-            stdout=subprocess.DEVNULL,
-            check=True,
         )

bot_bottle/backend/docker/provision/prompt.py

@@ -1,43 +0,0 @@
-"""Copy the agent prompt into a running Docker bottle.
-
-The prompt file is always copied (so the in-container path always
-exists) but `--append-system-prompt-file` only fires when the agent
-actually has a prompt — the return value signals which case."""
-
-from __future__ import annotations
-
-import os
-import subprocess
-
-from ..bottle_plan import DockerBottlePlan
-
-
-def provision_prompt(plan: DockerBottlePlan, target: str) -> str | None:
-    """Copy the prompt file into the container, fix ownership/mode.
-    Returns the in-container path if the agent has a non-empty
-    prompt (drives --append-system-prompt-file), else None. The
-    file is copied either way so the path always exists."""
-    container = target
-    container_home = os.environ.get("BOT_BOTTLE_CONTAINER_HOME", "/home/node")
-    in_container_prompt_path = f"{container_home}/.bot-bottle-prompt.txt"
-
-    subprocess.run(
-        ["docker", "cp", str(plan.prompt_file), f"{container}:{in_container_prompt_path}"],
-        stdout=subprocess.DEVNULL,
-        check=True,
-    )
-    # `docker cp` preserves host UID; re-own/mode as root so node
-    # can read its own mode-600 prompt regardless of host UID.
-    subprocess.run(
-        ["docker", "exec", "-u", "0", container, "chown", "node:node", in_container_prompt_path],
-        stdout=subprocess.DEVNULL,
-        check=True,
-    )
-    subprocess.run(
-        ["docker", "exec", "-u", "0", container, "chmod", "600", in_container_prompt_path],
-        stdout=subprocess.DEVNULL,
-        check=True,
-    )
-
-    agent = plan.spec.manifest.agents[plan.spec.agent_name]
-    return in_container_prompt_path if agent.prompt else None

bot_bottle/backend/docker/provision/provider_auth.py

@@ -1,36 +0,0 @@
-"""Provision non-secret provider auth markers into a Docker bottle."""
-
-from __future__ import annotations
-
-import subprocess
-
-from ..bottle_plan import DockerBottlePlan
-
-
-def provision_provider_auth(plan: DockerBottlePlan, target: str) -> None:
-    """Apply provider-owned guest setup through Docker primitives."""
-    provision = plan.agent_provision
-    for d in provision.dirs:
-        _exec(target, ["mkdir", "-p", d.guest_path])
-        _exec(target, ["chown", d.owner, d.guest_path])
-        _exec(target, ["chmod", d.mode, d.guest_path])
-    for command in provision.pre_copy:
-        _exec(target, list(command.argv))
-    for f in provision.files:
-        subprocess.run(
-            ["docker", "cp", str(f.host_path), f"{target}:{f.guest_path}"],
-            stdout=subprocess.DEVNULL,
-            check=True,
-        )
-        _exec(target, ["chown", f.owner, f.guest_path])
-        _exec(target, ["chmod", f.mode, f.guest_path])
-    for command in provision.verify:
-        _exec(target, list(command.argv))
-
-
-def _exec(target: str, argv: list[str]) -> None:
-    subprocess.run(
-        ["docker", "exec", "-u", "0", target, *argv],
-        stdout=subprocess.DEVNULL,
-        check=True,
-    )

bot_bottle/backend/docker/provision/skills.py

@@ -1,62 +0,0 @@
-"""Copy host-side skill directories into a running Docker bottle.
-
-Skills are validated on the host before launch by the base class's
-`BottleBackend._validate_skills` (called from `prepare`); this module
-assumes that validation has already run. A skill disappearing between
-validation and copy still dies loudly rather than silently producing
-a partial container."""
-
-from __future__ import annotations
-
-import os
-import subprocess
-
-from ....log import die, info
-from ...util import host_skill_dir
-from ..bottle_plan import DockerBottlePlan
-
-
-def provision_skills(plan: DockerBottlePlan, target: str) -> None:
-    """Copy each of the agent's named skills from the host's
-    ~/.claude/skills/<name>/ into the container's equivalent path.
-    For each skill: ensure parent dir, wipe any prior copy, then
-    `docker cp <host>/. <container>:<dst>/` so the contents are
-    copied into a freshly-created destination dir. No-op when the
-    agent has no skills."""
-    agent = plan.spec.manifest.agents[plan.spec.agent_name]
-    if not agent.skills:
-        return
-
-    container = target
-    container_home = os.environ.get("BOT_BOTTLE_CONTAINER_HOME", "/home/node")
-    skills_dir = os.environ.get(
-        "BOT_BOTTLE_CONTAINER_SKILLS_DIR", f"{container_home}/.claude/skills"
-    )
-
-    subprocess.run(
-        ["docker", "exec", container, "mkdir", "-p", skills_dir],
-        stdout=subprocess.DEVNULL,
-        check=True,
-    )
-
-    for n in agent.skills:
-        src = host_skill_dir(n)
-        if not os.path.isdir(src):
-            die(f"skill '{n}' disappeared from host between validation and copy at {src}.")
-        dst = f"{skills_dir}/{n}"
-        info(f"copying skill {n} into {container}:{dst}")
-        subprocess.run(
-            ["docker", "exec", container, "rm", "-rf", dst],
-            stdout=subprocess.DEVNULL,
-            check=True,
-        )
-        subprocess.run(
-            ["docker", "exec", container, "mkdir", "-p", dst],
-            stdout=subprocess.DEVNULL,
-            check=True,
-        )
-        subprocess.run(
-            ["docker", "cp", f"{src}/.", f"{container}:{dst}/"],
-            stdout=subprocess.DEVNULL,
-            check=True,
-        )

bot_bottle/backend/docker/provision/supervise.py

@@ -1,65 +0,0 @@
-"""Supervise sidecar provisioning inside a running Docker bottle
-(PRD 0013).
-
-Registers the per-bottle supervise sidecar as an HTTP MCP server in
-the agent's claude-code config so the agent discovers the three
-stuck-recovery MCP tools (cred-proxy-block, pipelock-block,
-capability-block) at startup.
-
-Uses `claude mcp add` rather than writing JSON directly. claude-code
-owns the on-disk config format (`~/.claude.json` `mcpServers` shape,
-field names, scope semantics) and changes it between versions; the
-official command handles whatever the installed version expects.
-
-No-op when bottle.supervise is False — bottles that haven't opted
-into the supervise sidecar shouldn't get an MCP entry pointing at a
-sidecar that isn't running.
-"""
-
-from __future__ import annotations
-
-import subprocess
-
-from ....log import info, warn
-from ....supervise import SUPERVISE_HOSTNAME, SUPERVISE_PORT
-from ..bottle_plan import DockerBottlePlan
-
-
-_SUPERVISE_MCP_NAME = "supervise"
-
-
-def supervise_mcp_url() -> str:
-    return f"http://{SUPERVISE_HOSTNAME}:{SUPERVISE_PORT}/"
-
-
-def provision_supervise(plan: DockerBottlePlan, target: str) -> None:
-    """Run `claude mcp add` inside the agent container to register
-    the supervise sidecar in claude-code's user config. No-op when
-    bottle.supervise is False.
-
-    Failure is logged but not fatal: the bottle still works (you
-    just can't call supervise tools from the agent until the entry
-    is added manually). The operator sees the warning at launch."""
-    if plan.supervise_plan is None:
-        return
-    url = supervise_mcp_url()
-    argv = [
-        "docker", "exec", "-u", "node", target,
-        "claude", "mcp", "add",
-        "--scope", "user",
-        "--transport", "http",
-        _SUPERVISE_MCP_NAME,
-        url,
-    ]
-    info(f"registering supervise MCP server in agent claude config → {url}")
-    r = subprocess.run(argv, capture_output=True, text=True, check=False)
-    if r.returncode != 0:
-        warn(
-            f"`claude mcp add supervise` failed (exit {r.returncode}): "
-            f"{(r.stderr or r.stdout or '').strip()}. Inside the bottle, "
-            f"register manually with: "
-            f"claude mcp add --scope user --transport http supervise {url}"
-        )
-
-
-__all__ = ["provision_supervise", "supervise_mcp_url"]

bot_bottle/backend/smolmachines/backend.py

@@ -1,5 +1,11 @@
 """SmolmachinesBottleBackend — the smolmachines implementation of
-BottleBackend (PRD 0023)."""
+BottleBackend (PRD 0023).
+
+Per PRD 0050 the per-provider provisioning steps (prompt, skills,
+the declarative provision-plan apply, supervise MCP registration)
+live on the `AgentProvider` plugin under `bot_bottle/contrib/`. The
+smolmachines backend only owns the steps that are about backend
+infrastructure: CA install (no-op for now), workspace, git copy-in."""
 
 from __future__ import annotations
 
@@ -7,7 +13,7 @@ from contextlib import contextmanager
 from pathlib import Path
 from typing import Generator, Sequence
 
-from .. import ActiveAgent, BottleBackend, BottleSpec
+from .. import ActiveAgent, Bottle, BottleBackend, BottleSpec
 from . import cleanup as _cleanup
 from . import enumerate as _enumerate
 from . import launch as _launch
@@ -18,10 +24,6 @@ from .bottle_cleanup_plan import SmolmachinesBottleCleanupPlan
 from .bottle_plan import SmolmachinesBottlePlan
 from .provision import ca as _ca
 from .provision import git as _git
-from .provision import prompt as _prompt
-from .provision import provider_auth as _provider_auth
-from .provision import skills as _skills
-from .provision import supervise as _supervise
 from .provision import workspace as _workspace
 
 
@@ -54,39 +56,26 @@ class SmolmachinesBottleBackend(
             yield bottle
 
     def provision_ca(
-        self, plan: SmolmachinesBottlePlan, target: str
+        self, plan: SmolmachinesBottlePlan, bottle: Bottle
     ) -> None:
-        _ca.provision_ca(plan, target)
+        _ca.provision_ca(plan, bottle)
-
-    def provision_prompt(
-        self, plan: SmolmachinesBottlePlan, target: str
-    ) -> str | None:
-        return _prompt.provision_prompt(plan, target)
-
-    def provision_provider_auth(
-        self, plan: SmolmachinesBottlePlan, target: str
-    ) -> None:
-        _provider_auth.provision_provider_auth(plan, target)
-
-    def provision_skills(
-        self, plan: SmolmachinesBottlePlan, target: str
-    ) -> None:
-        _skills.provision_skills(plan, target)
 
     def provision_workspace(
-        self, plan: SmolmachinesBottlePlan, target: str
+        self, plan: SmolmachinesBottlePlan, bottle: Bottle
     ) -> None:
-        _workspace.provision_workspace(plan, target)
+        _workspace.provision_workspace(plan, bottle)
 
     def provision_git(
-        self, plan: SmolmachinesBottlePlan, target: str
+        self, plan: SmolmachinesBottlePlan, bottle: Bottle
     ) -> None:
-        _git.provision_git(plan, target)
+        _git.provision_git(plan, bottle)
 
-    def provision_supervise(
+    def supervise_mcp_url(self, plan: SmolmachinesBottlePlan) -> str:
-        self, plan: SmolmachinesBottlePlan, target: str
+        """The smolmachines guest reaches the supervise sidecar via a
-    ) -> None:
+        host-published random port the launch step pinned earlier
-        _supervise.provision_supervise(plan, target)
+        (`http://<loopback_ip>:<random_port>/`). `agent_supervise_url`
+        on the plan is "" when the bottle has no sidecar."""
+        return plan.agent_supervise_url
 
     def prepare_cleanup(self) -> SmolmachinesBottleCleanupPlan:
         return _cleanup.prepare_cleanup()

bot_bottle/backend/smolmachines/launch.py

@@ -113,15 +113,16 @@ def launch(
         _launch_vm(plan, agent_from_path, loopback_ip, stack)
         _init_vm(plan)
 
-        prompt_path = provision(plan, plan.machine_name)
+        bottle = SmolmachinesBottle(
-
-        yield SmolmachinesBottle(
             plan.machine_name,
-            prompt_path=prompt_path,
+            prompt_path=None,
             guest_env=plan.guest_env,
             agent_command=plan.agent_command,
             agent_prompt_mode=plan.agent_prompt_mode,
         )
+        bottle._prompt_path = provision(plan, bottle)
+
+        yield bottle
     finally:
         _teardown_smolmachines(stack, plan)
 

bot_bottle/backend/smolmachines/prepare.py

@@ -61,7 +61,7 @@ def resolve_plan(
     bottle = manifest.bottle_for(spec.agent_name)
     provider = bottle.agent_provider
     provider_runtime = runtime_for(provider.template)
-    guest_home = os.environ.get("BOT_BOTTLE_GUEST_HOME", "/home/node")
+    guest_home = "/home/node"
     workspace_plan = resolve_workspace_plan(spec, guest_home=guest_home)
 
     slug = spec.identity or bottle_identity(spec.agent_name)
@@ -172,6 +172,7 @@ def resolve_plan(
     return SmolmachinesBottlePlan(
         spec=spec,
         stage_dir=stage_dir,
+        guest_home=guest_home,
         slug=slug,
         bundle_subnet=subnet,
         bundle_gateway=gateway,

bot_bottle/backend/smolmachines/provision/__init__.py

@@ -1,14 +1,12 @@
-"""Provisioning helpers for the smolmachines backend (PRD 0023
+"""Backend-infrastructure provisioners for the smolmachines backend.
-chunk 4).
 
-Each method maps onto one of `BottleBackend`'s `provision_*`
+Per PRD 0050 the per-provider provisioning steps (prompt, skills,
-overrides. They run after the VM is up + the bundle is reachable
+declarative provision-plan apply, supervise MCP registration) live on
-and copy host-side state (prompt, skills, .git, CA cert,
+the `AgentProvider` plugin under `bot_bottle/contrib/`. The modules
-supervise MCP config) into the guest via `smolvm machine cp` /
+left in this subpackage handle only the steps that are
-`smolvm machine exec`.
+backend-specific:
 
-Chunk 4a ships `provision_prompt` and `provision_skills` — the
+  - ca.py        — install per-bottle CA bundle into the guest trust store
-two that don't depend on agent-image tooling (claude-code,
+  - git.py       — copy host cwd `.git` into the guest when --cwd is used
-update-ca-certificates) beyond `cp` and `mkdir`. provision_ca /
+  - workspace.py — copy the operator workspace into the guest
-provision_git / provision_supervise land once the agent-image
+"""
-gap is solved."""

bot_bottle/backend/smolmachines/provision/ca.py

@@ -2,8 +2,8 @@
 trust store (PRD 0023 chunk 4d).
 
 Mirrors `backend.docker.provision.ca`: select the right CA (egress
-when the bottle has routes, else pipelock), `smolvm machine cp` it
+when the bottle has routes, else pipelock), copy it to Debian's
-to Debian's `/usr/local/share/ca-certificates/` path,
+`/usr/local/share/ca-certificates/` path,
 `update-ca-certificates` to rebuild the trust bundle, and log the
 fingerprint once. The selected cert depends on the agent's
 HTTP_PROXY target — same logic as the docker backend, since the
@@ -24,20 +24,20 @@ from ...util import (
     log_ca_fingerprint,
     select_ca_cert,
 )
-from .. import smolvm as _smolvm
+from ... import Bottle, ExecResult
 from ..bottle_plan import SmolmachinesBottlePlan
 
 
 _SIGKILL_EXIT = 128 + 9
 
 
-def provision_ca(plan: SmolmachinesBottlePlan, target: str) -> None:
+def provision_ca(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
     """Copy the agent-facing CA cert into the guest, rebuild the
     trust bundle, emit a one-line fingerprint log. Called from
     `BottleBackend.provision` after the smolvm guest is up."""
     cert_host_path, label = select_ca_cert(plan.egress_plan, plan.proxy_plan)
 
-    _smolvm.machine_cp(str(cert_host_path), f"{target}:{AGENT_CA_PATH}")
+    bottle.cp_in(str(cert_host_path), AGENT_CA_PATH)
     # Mode 0644 — readable to non-root tools in the guest.
     # update-ca-certificates rebuilds the bundle at AGENT_CA_BUNDLE,
     # which is what curl / Python ssl / OpenSSL-based tools read by
@@ -45,21 +45,21 @@ def provision_ca(plan: SmolmachinesBottlePlan, target: str) -> None:
     # REQUESTS_CA_BUNDLE) on the guest_env covers Node + Python
     # `requests` / libraries that don't load the system bundle.
     #
-    r = _install_ca(target)
+    r = _install_ca(bottle)
     if r.returncode == _SIGKILL_EXIT:
         # smolvm/libkrun can SIGKILL an otherwise-normal exec
         # during early-VM provisioning. `update-ca-certificates`
         # is idempotent, so retry the same install once after a
         # short settle delay before treating it as fatal.
         time.sleep(1.0)
-        r = _install_ca(target)
+        r = _install_ca(bottle)
 
     if r.returncode != 0:
         # update-ca-certificates not adding our cert is fatal —
         # claude-code's TLS handshake against the egress-MITM'd
         # api.anthropic.com would fail downstream. Bail early
-        # with what we can see (output is captured by smolvm so
+        # with what we can see (output is captured so we can
-        # we can surface it).
+        # surface it).
         die(
             f"update-ca-certificates didn't add the agent CA "
             f"(exit {r.returncode}): "
@@ -70,21 +70,21 @@ def provision_ca(plan: SmolmachinesBottlePlan, target: str) -> None:
     log_ca_fingerprint(cert_host_path, label)
 
 
-def _install_ca(target: str) -> _smolvm.SmolvmRunResult:
+def _install_ca(bottle: Bottle) -> ExecResult:
     # chown + chmod + update-ca-certificates + bundle
-    # verification run in one `sh -c` so we only pay one
+    # verification run in one exec so we only pay one
-    # machine_exec round trip; the `&&` chaining surfaces the
+    # round trip; the `&&` chaining surfaces the first failure
-    # first failure as the return code. The verify check is more
+    # as the return code. The verify check is more stable than
-    # stable than requiring "1 added" in stdout: a retry after a
+    # requiring "1 added" in stdout: a retry after a
     # partially-completed first run may legitimately report "0
     # added" while the cert is already installed.
-    return _smolvm.machine_exec(target, [
+    return bottle.exec(
-        "sh", "-c",
         f"chown root:root {AGENT_CA_PATH} && "
         f"chmod 644 {AGENT_CA_PATH} && "
         f"update-ca-certificates && "
         f"openssl verify -CAfile {AGENT_CA_BUNDLE} {AGENT_CA_PATH}",
-    ])
+        user="root",
+    )
 
 
 # Re-exported for the launch/provision_ca caller + tests. The path

bot_bottle/backend/smolmachines/provision/git.py

@@ -26,35 +26,25 @@ git_gate module."""
 from __future__ import annotations
 
 import os
+import shlex
 import tempfile
 from pathlib import Path
 
 from ....git_gate import git_gate_render_gitconfig
 from ....log import info
-from .. import smolvm as _smolvm
+from ... import Bottle
 from ..bottle_plan import SmolmachinesBottlePlan
 
 
-# `node` is the agent user from the repo Dockerfile. Override via
+def provision_git(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
-# BOT_BOTTLE_GUEST_HOME mirrors the docker backend's
-# BOT_BOTTLE_CONTAINER_HOME knob — same purpose, different
-# transport.
-_DEFAULT_GUEST_HOME = "/home/node"
-
-
-def _guest_home() -> str:
-    return os.environ.get("BOT_BOTTLE_GUEST_HOME", _DEFAULT_GUEST_HOME)
-
-
-def provision_git(plan: SmolmachinesBottlePlan, target: str) -> None:
     """Set up git inside the guest. Runs all three subcases; each
     no-ops when its condition isn't met."""
-    _provision_cwd_git(plan, target)
+    _provision_cwd_git(plan, bottle)
-    _provision_git_gate_config(plan, target)
+    _provision_git_gate_config(plan, bottle)
-    _provision_git_user(plan, target)
+    _provision_git_user(plan, bottle)
 
 
-def _provision_cwd_git(plan: SmolmachinesBottlePlan, target: str) -> None:
+def _provision_cwd_git(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
     """If --cwd was set and the host cwd has a .git directory, copy
     it into <guest_home>/workspace/.git and fix ownership. No-op
     otherwise."""
@@ -63,25 +53,26 @@ def _provision_cwd_git(plan: SmolmachinesBottlePlan, target: str) -> None:
         return
     guest_workspace_git = f"{workspace.guest_path}/.git"
     host_git = str(workspace.host_path / ".git")
-    info(f"copying {host_git} -> {target}:{guest_workspace_git}")
+    info(f"copying {host_git} -> {bottle.name}:{guest_workspace_git}")
-    # mkdir -p the workspace dir so `machine cp` lands the .git
+    # mkdir -p the workspace dir so cp_in lands the .git
     # directly there even on first-time bottles.
-    _smolvm.machine_exec(target, ["mkdir", "-p", workspace.guest_path])
+    bottle.exec(f"mkdir -p {shlex.quote(workspace.guest_path)}", user="root")
-    _smolvm.machine_cp(
+    bottle.cp_in(host_git, guest_workspace_git)
-        host_git, f"{target}:{guest_workspace_git}",
+    # cp_in lands files as root; the agent runs as node so
-    )
-    # `machine cp` lands files as root; the agent runs as node so
     # the workspace tree must be chowned over.
-    _smolvm.machine_exec(
+    bottle.exec(
-        target, ["chown", "-R", workspace.owner, guest_workspace_git],
+        f"chown -R {shlex.quote(workspace.owner)} {shlex.quote(guest_workspace_git)}",
+        user="root",
     )
 
 
-def _provision_git_gate_config(plan: SmolmachinesBottlePlan, target: str) -> None:
+def _provision_git_gate_config(
+    plan: SmolmachinesBottlePlan, bottle: Bottle
+) -> None:
     """Write ~/.gitconfig in the guest with the git-gate insteadOf
     rules. No-op when the bottle has no `git` entries."""
-    bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
+    manifest_bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
-    if not bottle.git:
+    if not manifest_bottle.git:
         return
 
     # `<loopback alias>:<host port>` form: the bundle's git-gate
@@ -90,11 +81,11 @@ def _provision_git_gate_config(plan: SmolmachinesBottlePlan, target: str) -> Non
     # TSI, not the docker bridge IP) can dial it. launch.py
     # populates `plan.agent_git_gate_host` after bundle bringup.
     content = git_gate_render_gitconfig(
-        bottle.git, plan.agent_git_gate_host, scheme="http",
+        manifest_bottle.git, plan.agent_git_gate_host, scheme="http",
     )
 
-    guest_gitconfig = f"{_guest_home()}/.gitconfig"
+    guest_gitconfig = f"{plan.guest_home}/.gitconfig"
-    # Stage the file under the plan's stage_dir so `machine cp`
+    # Stage the file under the plan's stage_dir so cp_in
     # has a stable host path. The plan's stage_dir is cleaned up
     # by start.py's session-end teardown.
     with tempfile.NamedTemporaryFile(
@@ -105,41 +96,38 @@ def _provision_git_gate_config(plan: SmolmachinesBottlePlan, target: str) -> Non
         config_file = Path(f.name)
     os.chmod(config_file, 0o600)
 
-    info(f"writing {guest_gitconfig} with {len(bottle.git)} insteadOf rule(s)")
+    info(f"writing {guest_gitconfig} with {len(manifest_bottle.git)} insteadOf rule(s)")
-    _smolvm.machine_cp(str(config_file), f"{target}:{guest_gitconfig}")
+    bottle.cp_in(str(config_file), guest_gitconfig)
-    _smolvm.machine_exec(target, ["chown", "node:node", guest_gitconfig])
+    bottle.exec(
-    _smolvm.machine_exec(target, ["chmod", "644", guest_gitconfig])
+        f"chown node:node {shlex.quote(guest_gitconfig)} && "
+        f"chmod 644 {shlex.quote(guest_gitconfig)}",
+        user="root",
+    )
 
 
 def _provision_git_user(
-    plan: SmolmachinesBottlePlan, target: str,
+    plan: SmolmachinesBottlePlan, bottle: Bottle,
 ) -> None:
     """Apply `git config --global user.{name,email}` inside the
     guest as the node user so --global lands in the same
     `/home/node/.gitconfig` that `_provision_git_gate_config`
     writes to. No-op when the bottle didn't declare `git.user`.
 
-    Runs via `runuser -u node --`; HOME is forced via smolvm's
+    SmolmachinesBottle.exec(user="node") automatically sets
-    `-e` flag because runuser (without -l) inherits root's
+    HOME=/home/node so --global writes to /home/node/.gitconfig."""
-    HOME=/root, which would put --global in the wrong file."""
+    manifest_bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
-    bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
+    gu = manifest_bottle.git_user
-    gu = bottle.git_user
     if gu.is_empty():
         return
-    env = {"HOME": _guest_home(), "USER": "node"}
     if gu.name:
         info(f"git config --global user.name = {gu.name!r}")
-        _smolvm.machine_exec(
+        bottle.exec(
-            target,
+            f"git config --global user.name {shlex.quote(gu.name)}",
-            ["runuser", "-u", "node", "--",
+            user="node",
-             "git", "config", "--global", "user.name", gu.name],
-            env=env,
         )
     if gu.email:
         info(f"git config --global user.email = {gu.email!r}")
-        _smolvm.machine_exec(
+        bottle.exec(
-            target,
+            f"git config --global user.email {shlex.quote(gu.email)}",
-            ["runuser", "-u", "node", "--",
+            user="node",
-             "git", "config", "--global", "user.email", gu.email],
-            env=env,
         )

bot_bottle/backend/smolmachines/provision/prompt.py

@@ -1,42 +0,0 @@
-"""Copy the agent prompt into a running smolmachines bottle.
-
-The prompt file is always copied (so the in-guest path always
-exists) but `--append-system-prompt-file` only fires when the
-agent actually has a prompt — the return value signals which
-case, mirroring the docker backend's contract.
-
-`smolvm machine cp` lands files as root inside the VM; the claude
-process runs as `node`, so we chown + chmod the prompt after the
-copy. Same flow as the docker backend's provision_prompt."""
-
-from __future__ import annotations
-
-import os
-
-from .. import smolvm as _smolvm
-from ..bottle_plan import SmolmachinesBottlePlan
-
-
-# `node` is the agent user from the repo Dockerfile.
-# BOT_BOTTLE_GUEST_HOME mirrors the docker backend's
-# BOT_BOTTLE_CONTAINER_HOME knob.
-_DEFAULT_GUEST_HOME = "/home/node"
-
-
-def provision_prompt(plan: SmolmachinesBottlePlan, target: str) -> str | None:
-    """Copy the prompt file into the running smolvm guest, fix
-    ownership/mode. Returns the in-guest path if the agent has a
-    non-empty prompt (drives --append-system-prompt-file), else
-    None. The file is copied either way so the path always
-    exists — mirrors the docker backend's behavior."""
-    guest_home = os.environ.get("BOT_BOTTLE_GUEST_HOME", _DEFAULT_GUEST_HOME)
-    in_guest_prompt_path = f"{guest_home}/.bot-bottle-prompt.txt"
-
-    _smolvm.machine_cp(str(plan.prompt_file), f"{target}:{in_guest_prompt_path}")
-    # machine cp lands as root, source's 0o600 mode is preserved —
-    # node can't read its own prompt without these two.
-    _smolvm.machine_exec(target, ["chown", "node:node", in_guest_prompt_path])
-    _smolvm.machine_exec(target, ["chmod", "600", in_guest_prompt_path])
-
-    agent = plan.spec.manifest.agents[plan.spec.agent_name]
-    return in_guest_prompt_path if agent.prompt else None

bot_bottle/backend/smolmachines/provision/provider_auth.py

@@ -1,33 +0,0 @@
-"""Provision non-secret provider auth markers into a smolmachines bottle."""
-
-from __future__ import annotations
-
-from ....log import die
-from .. import smolvm as _smolvm
-from ..bottle_plan import SmolmachinesBottlePlan
-
-
-def provision_provider_auth(plan: SmolmachinesBottlePlan, target: str) -> None:
-    """Apply provider-owned guest setup through smolvm primitives."""
-    provision = plan.agent_provision
-    for d in provision.dirs:
-        _exec(target, ["mkdir", "-p", d.guest_path], f"could not create {d.guest_path}")
-        _exec(target, ["chown", d.owner, d.guest_path], f"could not chown {d.guest_path}")
-        _exec(target, ["chmod", d.mode, d.guest_path], f"could not chmod {d.guest_path}")
-    for command in provision.pre_copy:
-        _exec(target, list(command.argv), command.error)
-    for f in provision.files:
-        _smolvm.machine_cp(str(f.host_path), f"{target}:{f.guest_path}")
-        _exec(target, ["chown", f.owner, f.guest_path], f"could not chown {f.guest_path}")
-        _exec(target, ["chmod", f.mode, f.guest_path], f"could not chmod {f.guest_path}")
-    for command in provision.verify:
-        _exec(target, list(command.argv), command.error)
-
-
-def _exec(target: str, argv: list[str], error: str) -> None:
-    result = _smolvm.machine_exec(target, argv)
-    if result.returncode != 0:
-        detail = (result.stderr or result.stdout).strip()
-        if detail:
-            detail = f": {detail}"
-        die(f"agent provider provisioning: {error}{detail}")

bot_bottle/backend/smolmachines/provision/skills.py

@@ -1,63 +0,0 @@
-"""Copy host-side skill directories into a running smolmachines
-bottle.
-
-Skills are validated on the host before launch by
-`BottleBackend._validate_skills`; this module assumes that
-validation has already run. A skill that disappears between
-validation and copy still dies loudly rather than silently
-producing a partial guest."""
-
-from __future__ import annotations
-
-import os
-
-from ....log import die, info
-from ...util import host_skill_dir
-from .. import smolvm as _smolvm
-from ..bottle_plan import SmolmachinesBottlePlan
-
-
-# In-guest path mirrors the docker backend's claude-skills
-# convention (~/.claude/skills/<name>/) under the node user's
-# home — same path as the real bot-bottle image's
-# /home/node/.claude/skills (pre-created in the Dockerfile).
-_DEFAULT_SKILLS_DIR = "/home/node/.claude/skills"
-
-
-def provision_skills(plan: SmolmachinesBottlePlan, target: str) -> None:
-    """Copy each of the agent's named skills from the host's
-    ~/.claude/skills/<name>/ into the guest's equivalent path.
-    For each skill: `mkdir -p` the destination, `smolvm machine cp`
-    the host source dir over, then chown the result to node:node so
-    the agent can read it. No-op when the agent has no skills.
-
-    smolvm machine cp on a directory copies recursively (same
-    semantics as `cp -r`); unlike docker cp's trailing-slash
-    convention, smolvm doesn't need the `/.` suffix dance.
-
-    machine cp lands files as root inside the VM, so we chown each
-    skill tree over to node:node after the copy — same pattern as
-    the docker backend's provision_prompt."""
-    agent = plan.spec.manifest.agents[plan.spec.agent_name]
-    if not agent.skills:
-        return
-
-    skills_dir = os.environ.get(
-        "BOT_BOTTLE_GUEST_SKILLS_DIR", _DEFAULT_SKILLS_DIR,
-    )
-
-    _smolvm.machine_exec(target, ["mkdir", "-p", skills_dir])
-
-    for name in agent.skills:
-        src = host_skill_dir(name)
-        if not os.path.isdir(src):
-            die(
-                f"skill {name!r} disappeared from host between "
-                f"validation and copy at {src}."
-            )
-        dst = f"{skills_dir}/{name}"
-        info(f"copying skill {name} into {target}:{dst}")
-        # Wipe any prior copy so re-runs don't accumulate.
-        _smolvm.machine_exec(target, ["rm", "-rf", dst])
-        _smolvm.machine_cp(src, f"{target}:{dst}")
-        _smolvm.machine_exec(target, ["chown", "-R", "node:node", dst])

bot_bottle/backend/smolmachines/provision/supervise.py

@@ -1,67 +0,0 @@
-"""Supervise sidecar provisioning inside a running smolmachines
-bottle (PRD 0023 chunk 4d; PRD 0013 supervise plane).
-
-Registers the per-bottle supervise sidecar as an HTTP MCP server
-in the agent's claude-code config so the agent discovers the
-stuck-recovery MCP tools (pipelock-block, capability-block) at
-startup.
-
-Mirrors `backend.docker.provision.supervise` — same `claude mcp
-add` call, just dispatched via `smolvm machine exec` instead of
-`docker exec`, and against `<bundle_ip>:<port>` instead of the
-short `supervise` alias (no DNS in the TSI-allowlisted guest)."""
-
-from __future__ import annotations
-
-from ....log import info, warn
-from .. import smolvm as _smolvm
-from ..bottle_plan import SmolmachinesBottlePlan
-
-
-_SUPERVISE_MCP_NAME = "supervise"
-
-
-def provision_supervise(plan: SmolmachinesBottlePlan, target: str) -> None:
-    """Run `claude mcp add` inside the guest to register the
-    supervise sidecar in claude-code's user config. No-op when
-    bottle.supervise is False.
-
-    The URL is the agent-side endpoint launch.py populated after
-    bundle bringup — `http://127.0.0.1:<host port>/` rather than
-    the bundle's docker bridge IP, because that bridge isn't
-    reachable from the smolvm guest on macOS.
-
-    Failure is logged but not fatal: the bottle still works (you
-    just can't call supervise tools from the agent until the entry
-    is added manually). The operator sees the warning at launch."""
-    if plan.supervise_plan is None:
-        return
-    url = plan.agent_supervise_url
-    info(f"registering supervise MCP server in agent claude config → {url}")
-    # `claude mcp add --scope user` writes to ~/.claude.json. The
-    # agent is the `node` user; smolvm machine_exec runs as root
-    # by default, so we have to switch user explicitly and set
-    # HOME so the config lands in /home/node/.claude.json (where
-    # the agent's claude actually reads it from).
-    r = _smolvm.machine_exec(
-        target,
-        [
-            "runuser", "-u", "node", "--",
-            "env", "HOME=/home/node",
-            "claude", "mcp", "add",
-            "--scope", "user",
-            "--transport", "http",
-            _SUPERVISE_MCP_NAME,
-            url,
-        ],
-    )
-    if r.returncode != 0:
-        warn(
-            f"`claude mcp add supervise` failed (exit {r.returncode}): "
-            f"{(r.stderr or r.stdout or '').strip()}. Inside the bottle, "
-            f"register manually with: "
-            f"claude mcp add --scope user --transport http supervise {url}"
-        )
-
-
-__all__ = ["provision_supervise"]

bot_bottle/backend/smolmachines/provision/workspace.py

@@ -5,11 +5,11 @@ from __future__ import annotations
 import shlex
 
 from ....log import info
-from .. import smolvm as _smolvm
+from ... import Bottle
 from ..bottle_plan import SmolmachinesBottlePlan
 
 
-def provision_workspace(plan: SmolmachinesBottlePlan, target: str) -> None:
+def provision_workspace(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
     """Copy host cwd contents to the planned guest workspace."""
     workspace = plan.workspace_plan
     if not (workspace.enabled and workspace.copy_contents):
@@ -20,17 +20,13 @@ def provision_workspace(plan: SmolmachinesBottlePlan, target: str) -> None:
     guest_parent_q = shlex.quote(guest_parent)
     owner_q = shlex.quote(workspace.owner)
     mode_q = shlex.quote(workspace.mode)
-    info(f"copying {workspace.host_path} -> {target}:{workspace.guest_path}")
+    info(f"copying {workspace.host_path} -> {bottle.name}:{workspace.guest_path}")
-    _smolvm.machine_exec(
+    bottle.exec(
-        target,
+        f"rm -rf {guest_path_q} && mkdir -p {guest_parent_q}",
-        ["sh", "-c", f"rm -rf {guest_path_q} && mkdir -p {guest_parent_q}"],
+        user="root",
     )
-    _smolvm.machine_cp(str(workspace.host_path), f"{target}:{workspace.guest_path}")
+    bottle.cp_in(str(workspace.host_path), workspace.guest_path)
-    _smolvm.machine_exec(
+    bottle.exec(
-        target,
+        f"chown -R {owner_q} {guest_path_q} && chmod {mode_q} {guest_path_q}",
-        [
+        user="root",
-            "sh", "-c",
-            f"chown -R {owner_q} {guest_path_q} && "
-            f"chmod {mode_q} {guest_path_q}",
-        ],
     )

bot_bottle/contrib/claude/agent_provider.py

@@ -0,0 +1,226 @@
+"""Claude agent provider plugin (PRD 0050, contrib).
+
+The Claude-specific behavior previously inlined under
+`agent_provider.agent_provision_plan` (claude.json trust marker,
+api.anthropic.com egress route, OAuth-token placeholder), plus
+the `claude mcp add` invocation that registers the supervise
+sidecar in claude-code's user config (PRD 0013)."""
+
+from __future__ import annotations
+
+import json
+import os
+import shlex
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+from ...agent_provider import (
+    AgentProvider,
+    AgentProviderRuntime,
+    AgentProvisionFile,
+    AgentProvisionPlan,
+)
+from ...egress import EgressRoute
+from ...log import die, info, warn
+
+
+if TYPE_CHECKING:
+    from ...backend import Bottle, BottlePlan
+
+
+_REPO_ROOT = Path(__file__).resolve().parents[3]
+
+_SUPERVISE_MCP_NAME = "supervise"
+
+
+def _skills_dir(guest_home: str) -> str:
+    return f"{guest_home}/.claude/skills"
+
+
+def _prompt_path(guest_home: str) -> str:
+    return f"{guest_home}/.bot-bottle-prompt.txt"
+
+_RUNTIME = AgentProviderRuntime(
+    template="claude",
+    command="claude",
+    image="bot-bottle-claude:latest",
+    dockerfile=str(_REPO_ROOT / "Dockerfile.claude"),
+    prompt_mode="append_file",
+    bypass_args=("--dangerously-skip-permissions",),
+    resume_args=("--continue",),
+    remote_control_args=("--remote-control",),
+)
+
+
+class ClaudeAgentProvider(AgentProvider):
+    @property
+    def runtime(self) -> AgentProviderRuntime:
+        return _RUNTIME
+
+    def provision_plan(
+        self,
+        *,
+        dockerfile: str,
+        state_dir: Path,
+        guest_home: str,
+        guest_env: dict[str, str] | None = None,
+        auth_token: str = "",
+        forward_host_credentials: bool = False,
+        host_env: dict[str, str] | None = None,
+        trusted_project_path: str = "",
+    ) -> AgentProvisionPlan:
+        del forward_host_credentials, host_env  # Codex-only knobs
+        resolved_guest_env = dict(guest_env or {})
+        trusted_path = trusted_project_path or guest_home
+
+        env_vars: dict[str, str] = {
+            "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1",
+            "DISABLE_ERROR_REPORTING": "1",
+        }
+        claude_config = state_dir / "claude.json"
+        claude_projects = {guest_home: {"hasTrustDialogAccepted": True}}
+        claude_projects[trusted_path] = {"hasTrustDialogAccepted": True}
+        claude_config.write_text(json.dumps({
+            "hasCompletedOnboarding": True,
+            "theme": "dark",
+            "bypassPermissionsModeAccepted": True,
+            "projects": claude_projects,
+        }, indent=2) + "\n")
+        claude_config.chmod(0o600)
+        files = (
+            AgentProvisionFile(claude_config, f"{guest_home}/.claude.json"),
+        )
+        egress_routes = (EgressRoute(
+            host="api.anthropic.com",
+            auth_scheme="Bearer" if auth_token else "",
+            token_ref=auth_token,
+            tls_passthrough=True,
+        ),)
+        hidden_env_names: frozenset[str] = frozenset()
+        if auth_token:
+            env_vars["CLAUDE_CODE_OAUTH_TOKEN"] = "egress-placeholder"
+            hidden_env_names = frozenset({"CLAUDE_CODE_OAUTH_TOKEN"})
+
+        return AgentProvisionPlan(
+            template=_RUNTIME.template,
+            command=_RUNTIME.command,
+            prompt_mode=_RUNTIME.prompt_mode,
+            image=_RUNTIME.image,
+            dockerfile=dockerfile,
+            env_vars=env_vars,
+            guest_env=resolved_guest_env,
+            files=files,
+            egress_routes=egress_routes,
+            hidden_env_names=hidden_env_names,
+        )
+
+    def provision_skills(self, plan: "BottlePlan", bottle: "Bottle") -> None:
+        """Copy each named skill tree from `~/.claude/skills/<name>/`
+        on the host into the guest's claude-code skills dir. No-op
+        when the agent has no skills."""
+        from ...backend.util import host_skill_dir
+
+        agent = plan.spec.manifest.agents[plan.spec.agent_name]
+        if not agent.skills:
+            return
+        skills_dir = _skills_dir(plan.guest_home)
+        bottle.exec(f"mkdir -p {skills_dir}", user="root")
+        for name in agent.skills:
+            src = host_skill_dir(name)
+            if not os.path.isdir(src):
+                die(
+                    f"skill {name!r} disappeared from host between "
+                    f"validation and copy at {src}."
+                )
+            dst = f"{skills_dir}/{name}"
+            info(f"copying skill {name} into {bottle.name}:{dst}")
+            bottle.exec(f"rm -rf {dst} && mkdir -p {dst}", user="root")
+            bottle.cp_in(f"{src}/.", f"{dst}/")
+            bottle.exec(f"chown -R node:node {dst}", user="root")
+
+    def provision_prompt(self, plan: "BottlePlan", bottle: "Bottle") -> str | None:
+        """Copy the prompt file into the guest, fix ownership/mode.
+        Returns the in-guest path iff the agent has a non-empty
+        prompt (drives `--append-system-prompt-file`); the file is
+        copied either way so the path always exists."""
+        prompt_path = _prompt_path(plan.guest_home)
+        bottle.cp_in(str(plan.prompt_file), prompt_path)
+        bottle.exec(
+            f"chown node:node {prompt_path} && chmod 600 {prompt_path}",
+            user="root",
+        )
+        agent = plan.spec.manifest.agents[plan.spec.agent_name]
+        return prompt_path if agent.prompt else None
+
+    def provision(self, plan: "BottlePlan", bottle: "Bottle") -> None:
+        """Apply the claude-side declarative provision steps from
+        `plan.agent_provision` — today that's the `claude.json`
+        trust-marker file. Hot-replace this with a richer flow as
+        claude-code's harness shape evolves."""
+        provision = plan.agent_provision
+        for d in provision.dirs:
+            path = shlex.quote(d.guest_path)
+            _exec(bottle, f"mkdir -p {path}", f"could not create {d.guest_path}")
+            _exec(
+                bottle,
+                f"chown {shlex.quote(d.owner)} {path}",
+                f"could not chown {d.guest_path}",
+            )
+            _exec(
+                bottle,
+                f"chmod {shlex.quote(d.mode)} {path}",
+                f"could not chmod {d.guest_path}",
+            )
+        for command in provision.pre_copy:
+            _exec(bottle, shlex.join(command.argv), command.error)
+        for f in provision.files:
+            bottle.cp_in(str(f.host_path), f.guest_path)
+            path = shlex.quote(f.guest_path)
+            _exec(
+                bottle,
+                f"chown {shlex.quote(f.owner)} {path}",
+                f"could not chown {f.guest_path}",
+            )
+            _exec(
+                bottle,
+                f"chmod {shlex.quote(f.mode)} {path}",
+                f"could not chmod {f.guest_path}",
+            )
+        for command in provision.verify:
+            _exec(bottle, shlex.join(command.argv), command.error)
+
+    def provision_supervise_mcp(
+        self,
+        plan: "BottlePlan",
+        bottle: "Bottle",
+        supervise_url: str,
+    ) -> None:
+        """Run `claude mcp add` inside the agent guest to register the
+        supervise sidecar in claude-code's user config (~/.claude.json).
+
+        Failure is logged but not fatal — the bottle still works without
+        the entry; the operator can register it manually."""
+        if plan.supervise_plan is None:
+            return
+        info(f"registering supervise MCP server in agent claude config → {supervise_url}")
+        r = bottle.exec(
+            f"claude mcp add --scope user --transport http "
+            f"{_SUPERVISE_MCP_NAME} {supervise_url}",
+            user="node",
+        )
+        if r.returncode != 0:
+            warn(
+                f"`claude mcp add supervise` failed (exit {r.returncode}): "
+                f"{(r.stderr or r.stdout or '').strip()}. Inside the bottle, "
+                f"register manually with: "
+                f"claude mcp add --scope user --transport http supervise {supervise_url}"
+            )
+
+
+def _exec(bottle: "Bottle", script: str, error: str) -> None:
+    result = bottle.exec(script, user="root")
+    if result.returncode != 0:
+        detail = (result.stderr or result.stdout).strip()
+        if detail:
+            detail = f": {detail}"
+        die(f"agent provider provisioning: {error}{detail}")

bot_bottle/contrib/codex/agent_provider.py

@@ -0,0 +1,271 @@
+"""Codex agent provider plugin (PRD 0050, contrib).
+
+The Codex-specific behavior previously inlined under
+`agent_provider.agent_provision_plan` (config.toml trust marker,
+chatgpt.com / api.openai.com egress routes, optional host-credential
+forwarding with dummy-auth.json + verify), plus the `codex mcp add`
+invocation that registers the supervise sidecar in Codex's
+~/.codex/config.toml (PRD 0050)."""
+
+from __future__ import annotations
+
+import os
+import shlex
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+from ...agent_provider import (
+    CODEX_HOST_CREDENTIAL_HOSTS,
+    AgentProvider,
+    AgentProviderRuntime,
+    AgentProvisionCommand,
+    AgentProvisionDir,
+    AgentProvisionFile,
+    AgentProvisionPlan,
+)
+from ...codex_auth import codex_host_access_token, write_codex_dummy_auth_file
+from ...egress import CODEX_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
+from ...log import die, info, warn
+
+
+if TYPE_CHECKING:
+    from ...backend import Bottle, BottlePlan
+
+
+_REPO_ROOT = Path(__file__).resolve().parents[3]
+
+_SUPERVISE_MCP_NAME = "supervise"
+
+
+def _skills_dir(guest_home: str) -> str:
+    # Codex agents still read skills from the claude-code convention
+    # (~/.claude/skills/) — the bot-bottle-codex image follows the
+    # same layout. If Codex grows native skill discovery later,
+    # change here.
+    return f"{guest_home}/.claude/skills"
+
+
+def _prompt_path(guest_home: str) -> str:
+    return f"{guest_home}/.bot-bottle-prompt.txt"
+
+_RUNTIME = AgentProviderRuntime(
+    template="codex",
+    command="codex",
+    image="bot-bottle-codex:latest",
+    dockerfile=str(_REPO_ROOT / "Dockerfile.codex"),
+    prompt_mode="read_prompt_file",
+    bypass_args=("--dangerously-bypass-approvals-and-sandbox",),
+    resume_args=("resume", "--last"),
+    remote_control_args=(),
+)
+
+
+class CodexAgentProvider(AgentProvider):
+    @property
+    def runtime(self) -> AgentProviderRuntime:
+        return _RUNTIME
+
+    def provision_plan(
+        self,
+        *,
+        dockerfile: str,
+        state_dir: Path,
+        guest_home: str,
+        guest_env: dict[str, str] | None = None,
+        auth_token: str = "",
+        forward_host_credentials: bool = False,
+        host_env: dict[str, str] | None = None,
+        trusted_project_path: str = "",
+    ) -> AgentProvisionPlan:
+        del auth_token  # Claude-only knob
+        resolved_guest_env = dict(guest_env or {})
+        trusted_path = trusted_project_path or guest_home
+
+        env_vars: dict[str, str] = {
+            "CODEX_CA_CERTIFICATE": "/etc/ssl/certs/ca-certificates.crt",
+        }
+        auth_dir = resolved_guest_env.get("CODEX_HOME", f"{guest_home}/.codex")
+        if forward_host_credentials:
+            env_vars["CODEX_HOME"] = auth_dir
+
+        dirs = [AgentProvisionDir(auth_dir)]
+        files: list[AgentProvisionFile] = []
+        pre_copy: list[AgentProvisionCommand] = []
+        verify: list[AgentProvisionCommand] = []
+        provisioned_env: dict[str, str] = {}
+
+        config_path = f"{auth_dir}/config.toml"
+        config_file = state_dir / "codex-config.toml"
+        toml_path = trusted_path.replace("\\", "\\\\").replace('"', '\\"')
+        config_file.write_text(
+            f'[projects."{toml_path}"]\n'
+            'trust_level = "trusted"\n'
+        )
+        config_file.chmod(0o600)
+        files.append(AgentProvisionFile(config_file, config_path))
+
+        egress_routes: list[EgressRoute] = []
+        for host in CODEX_HOST_CREDENTIAL_HOSTS:
+            egress_routes.append(EgressRoute(
+                host=host,
+                auth_scheme="Bearer" if forward_host_credentials else "",
+                token_ref=CODEX_HOST_CREDENTIAL_TOKEN_REF if forward_host_credentials else "",
+                tls_passthrough=True,
+            ))
+
+        if forward_host_credentials:
+            _host_env = host_env or dict(os.environ)
+            provisioned_env[CODEX_HOST_CREDENTIAL_TOKEN_REF] = (
+                codex_host_access_token(_host_env)
+            )
+            auth_file = state_dir / "codex-auth.json"
+            write_codex_dummy_auth_file(auth_file, _host_env)
+            files.append(AgentProvisionFile(auth_file, f"{auth_dir}/auth.json"))
+            pre_copy.append(AgentProvisionCommand((
+                "find", auth_dir,
+                "-maxdepth", "1",
+                "-type", "f",
+                "(",
+                "-name", "*.sqlite",
+                "-o", "-name", "*.sqlite-*",
+                "-o", "-name", "*.codex-repair-*.bak",
+                ")",
+                "-delete",
+            ), "codex host credentials: could not reset runtime db files"))
+            verify.append(AgentProvisionCommand((
+                "runuser", "-u", "node", "--",
+                "env",
+                f"HOME={guest_home}",
+                f"CODEX_HOME={auth_dir}",
+                "codex", "login", "status",
+            ), (
+                "codex host credentials: dummy auth was copied into the "
+                "guest, but Codex did not accept it"
+            )))
+
+        return AgentProvisionPlan(
+            template=_RUNTIME.template,
+            command=_RUNTIME.command,
+            prompt_mode=_RUNTIME.prompt_mode,
+            image=_RUNTIME.image,
+            dockerfile=dockerfile,
+            env_vars=env_vars,
+            guest_env=resolved_guest_env,
+            dirs=tuple(dirs),
+            files=tuple(files),
+            pre_copy=tuple(pre_copy),
+            verify=tuple(verify),
+            egress_routes=tuple(egress_routes),
+            provisioned_env=provisioned_env,
+        )
+
+    def provision_skills(self, plan: "BottlePlan", bottle: "Bottle") -> None:
+        """Copy each named skill tree from `~/.claude/skills/<name>/`
+        on the host into the guest. No-op when the agent has no
+        skills."""
+        from ...backend.util import host_skill_dir
+
+        agent = plan.spec.manifest.agents[plan.spec.agent_name]
+        if not agent.skills:
+            return
+        skills_dir = _skills_dir(plan.guest_home)
+        bottle.exec(f"mkdir -p {skills_dir}", user="root")
+        for name in agent.skills:
+            src = host_skill_dir(name)
+            if not os.path.isdir(src):
+                die(
+                    f"skill {name!r} disappeared from host between "
+                    f"validation and copy at {src}."
+                )
+            dst = f"{skills_dir}/{name}"
+            info(f"copying skill {name} into {bottle.name}:{dst}")
+            bottle.exec(f"rm -rf {dst} && mkdir -p {dst}", user="root")
+            bottle.cp_in(f"{src}/.", f"{dst}/")
+            bottle.exec(f"chown -R node:node {dst}", user="root")
+
+    def provision_prompt(self, plan: "BottlePlan", bottle: "Bottle") -> str | None:
+        """Copy the prompt file into the guest, fix ownership/mode.
+        Codex reads it via the agent's `Read and follow the
+        instructions in <path>.` bootstrap (see `prompt_args`); the
+        file is copied either way so the path always exists."""
+        prompt_path = _prompt_path(plan.guest_home)
+        bottle.cp_in(str(plan.prompt_file), prompt_path)
+        bottle.exec(
+            f"chown node:node {prompt_path} && chmod 600 {prompt_path}",
+            user="root",
+        )
+        agent = plan.spec.manifest.agents[plan.spec.agent_name]
+        return prompt_path if agent.prompt else None
+
+    def provision(self, plan: "BottlePlan", bottle: "Bottle") -> None:
+        """Apply the codex-side declarative provision steps from
+        `plan.agent_provision`: the `~/.codex/` dir + config.toml
+        trust marker, plus the dummy-auth.json drop + `codex login
+        status` verify when host-credential forwarding is on."""
+        provision = plan.agent_provision
+        for d in provision.dirs:
+            path = shlex.quote(d.guest_path)
+            _exec(bottle, f"mkdir -p {path}", f"could not create {d.guest_path}")
+            _exec(
+                bottle,
+                f"chown {shlex.quote(d.owner)} {path}",
+                f"could not chown {d.guest_path}",
+            )
+            _exec(
+                bottle,
+                f"chmod {shlex.quote(d.mode)} {path}",
+                f"could not chmod {d.guest_path}",
+            )
+        for command in provision.pre_copy:
+            _exec(bottle, shlex.join(command.argv), command.error)
+        for f in provision.files:
+            bottle.cp_in(str(f.host_path), f.guest_path)
+            path = shlex.quote(f.guest_path)
+            _exec(
+                bottle,
+                f"chown {shlex.quote(f.owner)} {path}",
+                f"could not chown {f.guest_path}",
+            )
+            _exec(
+                bottle,
+                f"chmod {shlex.quote(f.mode)} {path}",
+                f"could not chmod {f.guest_path}",
+            )
+        for command in provision.verify:
+            _exec(bottle, shlex.join(command.argv), command.error)
+
+    def provision_supervise_mcp(
+        self,
+        plan: "BottlePlan",
+        bottle: "Bottle",
+        supervise_url: str,
+    ) -> None:
+        """Run `codex mcp add` inside the agent guest to register the
+        supervise sidecar in Codex's user config (~/.codex/config.toml).
+
+        Mirrors the Claude provider's `claude mcp add` flow — failure
+        is logged but not fatal."""
+        if plan.supervise_plan is None:
+            return
+        info(f"registering supervise MCP server in agent codex config → {supervise_url}")
+        r = bottle.exec(
+            f"codex mcp add --transport http "
+            f"{_SUPERVISE_MCP_NAME} {supervise_url}",
+            user="node",
+        )
+        if r.returncode != 0:
+            warn(
+                f"`codex mcp add supervise` failed (exit {r.returncode}): "
+                f"{(r.stderr or r.stdout or '').strip()}. Inside the bottle, "
+                f"register manually with: "
+                f"codex mcp add --transport http supervise {supervise_url}"
+            )
+
+
+def _exec(bottle: "Bottle", script: str, error: str) -> None:
+    result = bottle.exec(script, user="root")
+    if result.returncode != 0:
+        detail = (result.stderr or result.stdout).strip()
+        if detail:
+            detail = f": {detail}"
+        die(f"agent provider provisioning: {error}{detail}")

docs/prds/0049-named-labelled-agents.md

@@ -0,0 +1,283 @@
+# PRD 0049: Named / Labelled Agents
+
+- **Status:** Draft
+- **Author:** didericis
+- **Created:** 2026-06-03
+- **Issue:** #171
+
+## Summary
+
+At agent launch time, prompt the operator for a short human-readable label
+(defaulting to the manifest agent key) and an optional color from the 16-color
+ANSI palette. Store both in the bottle's `metadata.json`. Display the label —
+rendered in the chosen color — in the dashboard's active-agents pane, replacing
+the bare manifest key. Inject the label and color into the in-container
+`claude.json` as `name` / `color` so Claude Code can surface them in its own
+harness when upstream support lands.
+
+## Problem
+
+The dashboard's agents pane identifies each running instance by its manifest
+agent key (e.g., `implementer`) plus a random slug suffix. When an operator
+runs three `implementer` bottles simultaneously — one each for three different
+repos — the pane shows:
+
+```
+  [docker] a3f9  implementer  started 14:02:11  [egress,pipelock]
+  [docker] b81c  implementer  started 14:03:45  [egress,pipelock]
+  [docker] d220  implementer  started 14:05:01  [egress,pipelock]
+```
+
+There is no way to tell which bottle is working on which task without attaching
+to each one in turn. The slug is opaque; the manifest key is shared. Operators
+working a multi-bottle session resort to keeping a mental map of slug→task,
+which breaks the moment they switch windows.
+
+## Goals / Success Criteria
+
+1. After the operator selects an agent name (dashboard picker or CLI argument),
+   they are prompted for a label. The prompt suggests the manifest key as the
+   default; pressing Enter (or providing no input) accepts it. The label may
+   contain any printable characters up to 64 bytes.
+2. After the label prompt, the operator is optionally prompted for a color from
+   the 16-color ANSI palette (names: `black`, `red`, `green`, `yellow`, `blue`,
+   `magenta`, `cyan`, `white`, `bright-black`, `bright-red`, `bright-green`,
+   `bright-yellow`, `bright-blue`, `bright-magenta`, `bright-cyan`,
+   `bright-white`). Pressing Enter without a selection skips color entirely.
+3. `label` and `color` are stored in `BottleMetadata` and written to the
+   bottle's `metadata.json`. Both fields default to `""` (empty / unset).
+4. `ActiveAgent` carries `label` and `color`; `enumerate_active()` reads them
+   from `metadata.json`.
+5. `_format_agent_row` uses the label when non-empty (falling back to
+   `agent_name`). If a non-empty color is set and the terminal supports it, the
+   label substring is rendered in that color.
+6. `BottleSpec` carries `label` and `color`; the docker backend's `prepare`
+   step copies them into `BottleMetadata`.
+7. `agent_provider.py` writes `label` → `"name"` and `color` → `"color"` into
+   the generated `claude.json`, alongside the existing fields. Fields are
+   omitted when empty.
+8. The dashboard's `_new_agent_flow` (PRD 0020) includes the label+color step
+   between agent selection and the backend picker.
+9. `cmd_start` (CLI) includes the label+color step after argument validation
+   and before prepare-with-preflight.
+10. All existing unit tests stay green; no new tests are required for this
+    change (the label/color fields are thin plumbing with no branching logic
+    worth unit-testing beyond the already-tested metadata read/write path).
+
+## Non-goals
+
+- Showing the agent label inside the Claude Code TUI (status line, terminal
+  title, custom header). That requires upstream Claude Code / codex support.
+  Writing to `claude.json` is best-effort scaffolding for when that lands.
+- Per-bottle color affecting anything outside the dashboard agents pane (e.g.,
+  proposal-pane highlights, log prefixes).
+- Validating or constraining label content beyond the 64-byte printable cap.
+- Persisting color-pair state across dashboard restarts (color pairs are
+  initialized fresh each session).
+- Editing the label or color of an already-running bottle.
+- Exposing label/color via `./cli.py list` (out of scope for v1; trivial to
+  add later since the field will be in metadata).
+
+## Design
+
+### Data flow
+
+```
+operator input
+     │
+     ▼
+BottleSpec.label, BottleSpec.color
+     │
+     ├─► docker/prepare.py → BottleMetadata.label / .color → metadata.json
+     │
+     └─► agent_provider.py → claude.json {"name": label, "color": color}
+                                              (omitted when empty)
+
+dashboard refresh
+     │
+     ▼
+enumerate_active() → read_metadata(slug) → ActiveAgent.label / .color
+     │
+     ▼
+_format_agent_row → label (colored) in the row string
+```
+
+### BottleSpec changes
+
+```python
+@dataclass(frozen=True)
+class BottleSpec:
+    manifest: Manifest
+    agent_name: str
+    copy_cwd: bool
+    user_cwd: str
+    identity: str = ""
+    label: str = ""   # operator-chosen display name; defaults to agent_name at render time
+    color: str = ""   # one of the 16 ANSI color names, or "" for terminal default
+```
+
+`label` and `color` default to `""` so all existing callers remain valid with
+no changes.
+
+### BottleMetadata changes
+
+Add two new fields with backward-compatible defaults:
+
+```python
+@dataclass
+class BottleMetadata:
+    identity: str
+    agent_name: str
+    cwd: str
+    copy_cwd: bool
+    started_at: str
+    compose_project: str
+    backend: str
+    label: str = ""
+    color: str = ""
+```
+
+`metadata.json` written by older bot-bottle versions won't have these keys;
+`read_metadata` already uses `dict.get` with defaults, so existing slugs load
+cleanly with `label=""`, `color=""`.
+
+### ActiveAgent changes
+
+```python
+@dataclass(frozen=True)
+class ActiveAgent:
+    backend_name: str
+    slug: str
+    agent_name: str
+    started_at: str
+    services: tuple[str, ...]
+    label: str = ""
+    color: str = ""
+```
+
+`enumerate_active()` copies `label` and `color` out of `BottleMetadata` when
+constructing each `ActiveAgent`. The smolmachines backend gets the same
+additions for symmetry; it reads from its own metadata path.
+
+### Dashboard row rendering
+
+`_format_agent_row` already falls through cleanly on missing fields. The
+change is:
+
+```python
+display_name = a.label if a.label else a.agent_name
+```
+
+Color rendering uses the existing `_try_init_green()` pattern as a model.
+A `_color_pair_for(color_name)` helper initialises a fresh curses color pair
+for the requested named color and returns its attr (or 0 on failure). Each
+unique color in the active agent list gets its own pair index. Color pairs are
+allocated lazily and cached in a `dict[str, int]` that lives for the duration
+of the dashboard session.
+
+The 16 ANSI color name → curses constant mapping:
+
+| Name | curses constant |
+|------|----------------|
+| `black` | `curses.COLOR_BLACK` |
+| `red` | `curses.COLOR_RED` |
+| `green` | `curses.COLOR_GREEN` |
+| `yellow` | `curses.COLOR_YELLOW` |
+| `blue` | `curses.COLOR_BLUE` |
+| `magenta` | `curses.COLOR_MAGENTA` |
+| `cyan` | `curses.COLOR_CYAN` |
+| `white` | `curses.COLOR_WHITE` |
+| `bright-*` | same constant + `curses.A_BOLD` |
+
+Terminals that don't support color fall back to plain text (the helper returns
+0, which ORed in is a no-op — same pattern as `_try_init_green`).
+
+### Label + color prompt — dashboard
+
+In `_new_agent_flow`, after `_picker_modal` returns a non-None name and before
+`_backend_picker_modal`:
+
+```python
+label, color = _label_color_modal(stdscr, default_label=picked)
+```
+
+`_label_color_modal` uses `curses.endwin()` → text-mode prompts → restore
+(the same drop-and-resume pattern as the existing editor flow and preflight
+Y/N). Two sequential prompts:
+
+```
+bot-bottle: agent label [implementer]: <operator types>
+bot-bottle: color (red/green/blue/… or Enter to skip): <operator types>
+```
+
+Invalid color names are silently ignored (treated as empty). The function
+returns `(label, color)` — both strings, both possibly `""`.
+
+### Label + color prompt — CLI
+
+In `cmd_start`, after argument parsing and before `_launch_bottle`:
+
+```python
+label = _text_prompt_label(args.name)
+color = _text_prompt_color()
+```
+
+`_text_prompt_label(default)` writes `"bot-bottle: agent label [{default}]: "`
+to stderr and returns the stripped input (or `default` if blank).
+`_text_prompt_color()` writes the color prompt and returns the stripped input
+(or `""` if blank or invalid).
+
+Both use `read_tty_line()` (already in `start.py`) for the read.
+
+### Claude Code config injection
+
+In `agent_provider.py`, where `claude_config.write_text(...)` is called,
+expand the JSON dict conditionally:
+
+```python
+payload = {
+    "hasCompletedOnboarding": True,
+    "theme": "dark",
+    "bypassPermissionsModeAccepted": True,
+    "projects": claude_projects,
+}
+if spec.label:
+    payload["name"] = spec.label
+if spec.color:
+    payload["color"] = spec.color
+claude_config.write_text(json.dumps(payload, indent=2) + "\n")
+```
+
+`spec` here is the `AgentProvisionSpec` (or equivalent) that `agent_provider`
+already receives; it needs `label` and `color` threaded in from `BottleSpec`
+through whatever plan/provision object the provider operates on.
+
+## Implementation chunks
+
+Two PRs, each independently mergeable.
+
+### Chunk 1 — schema + storage
+
+- Add `label: str = ""` and `color: str = ""` to `BottleSpec`,
+  `BottleMetadata`, and `ActiveAgent`.
+- `docker/prepare.py`: copy `spec.label` / `spec.color` into `BottleMetadata`.
+- `docker/enumerate.py`: copy `metadata.label` / `metadata.color` into
+  `ActiveAgent`.
+- `agent_provider.py` (or the plan object it reads): thread label/color through
+  to `claude.json` write.
+- Smolmachines backend: parallel changes to metadata read/write and
+  `ActiveAgent` construction.
+- No prompt changes; no UI changes. All existing behavior is identical.
+
+### Chunk 2 — prompts + display
+
+- `start.py`: add `_text_prompt_label` and `_text_prompt_color`; call them in
+  `cmd_start` before `_launch_bottle`; pass `label` / `color` into `BottleSpec`.
+- `dashboard.py`: add `_label_color_modal` (drop-and-resume); call it in
+  `_new_agent_flow`; pass label/color into `BottleSpec`; add
+  `_color_pair_for` helper; update `_format_agent_row` to use `a.label` with
+  color rendering.
+
+## Open questions
+
+None.

docs/prds/0050-agent-provider-contrib.md

@@ -0,0 +1,401 @@
+# PRD 0050: Move provider-specific agent logic into contrib
+
+- **Status:** Active
+- **Author:** claude
+- **Created:** 2026-06-03
+- **Issue:** #177
+
+## Summary
+
+The agent provider module (`bot_bottle/agent_provider.py`) hard-codes
+the Claude- and Codex-specific provisioning rules — auth file shapes,
+trust-dialog markers, egress routes, dummy-auth dance, env vars — in a
+single `if template == "codex": ... if template == "claude": ...`
+chain (lines 154–230 today). Other pieces of provider behavior live in
+each backend's `provision/` directory (`provision_skills`,
+`provision_prompt`, `provision_provider_auth`, `provision_supervise`),
+duplicated once per backend, even though almost none of what they do
+is actually backend-specific.
+
+This PRD reshapes the agent provider into a proper plugin boundary.
+The two existing providers (Claude, Codex) move out of `agent_provider`
+into `bot_bottle/contrib/claude/` and `bot_bottle/contrib/codex/` —
+the same `contrib/` layout PRD 0048 established for the Gitea
+deploy-key provisioner. The four provisioner methods backends
+currently duplicate move into the provider plugin itself; the backend
+keeps only the bottle-side primitives (`cp_in`, `exec`) the plugin
+calls through. MCP server registration becomes a first-class part of
+the provider contract so Codex finally gets the supervise sidecar
+wired in alongside Claude.
+
+The shipping artifact is two new provider plugins under `contrib/`, a
+narrower `AgentProvider` ABC in `bot_bottle/agent_provider.py`, four
+fewer provisioner hooks on `BottleBackend`, and a supervise-MCP entry
+visible from the Codex agent at launch.
+
+## Problem
+
+Three concrete pains, all downstream of the provider abstraction not
+being where the work happens:
+
+1. **Adding a third provider is a five-file edit.** A hypothetical
+   Gemini or Aider provider has to: (a) add a branch in
+   `agent_provision_plan`, (b) add a runtime entry in `_RUNTIMES`,
+   (c) thread a `prompt_mode` enum value, (d) potentially extend
+   `provision_provider_auth` per backend, (e) wire MCP registration
+   into both `backend/docker/provision/supervise.py` and
+   `backend/smolmachines/provision/supervise.py`. Nothing about that
+   spread is load-bearing; it's leftover from when there was one
+   provider.
+
+2. **MCP server registration is Claude-only.** Both
+   `backend/docker/provision/supervise.py` and
+   `backend/smolmachines/provision/supervise.py` run `claude mcp add`
+   verbatim. Codex bottles silently get no MCP entry — the sidecar
+   is running, the routes are open, but the agent can't see the
+   tools because nothing wrote them into Codex's TOML config. Today
+   this is a latent gap. The provider plugin is the only layer that
+   knows how a given agent discovers MCP servers, so that's where
+   the registration belongs.
+
+3. **`provision_skills` / `provision_prompt` / `provision_provider_auth`
+   are duplicated between backends.** Each backend has its own
+   ~50-line copy. The differences are entirely about which path the
+   backend uses for `cp_in` and what user it `chown`s to. Same
+   business logic, two implementations, two test surfaces, two
+   places to update when the rules change.
+
+The agent_provider module is the right home for all of this. It already
+owns the `AgentProvisionPlan` (the declarative description of what
+needs to land in the guest); extending it to own the imperative
+"actually land it" step is the natural next move. Putting
+provider-specific code under `contrib/` mirrors the convention PRD 0048
+established and keeps the core package provider-agnostic.
+
+## Goals / Success Criteria
+
+1. `bot_bottle/agent_provider.py` contains no Claude- or
+   Codex-specific branches. The Claude and Codex template strings
+   themselves still live in the core module (they're the public
+   manifest values), but everything keyed off them moves out.
+2. `bot_bottle/contrib/claude/agent_provider.py` and
+   `bot_bottle/contrib/codex/agent_provider.py` exist and contain
+   the provider-specific behavior previously in lines 154–230 of
+   `agent_provider.py`. Each is reachable from the core registry via
+   a lazy import (the same pattern PRD 0048 used for
+   `GiteaDeployKeyProvisioner`).
+3. `AgentProvider` is an ABC (or protocol) with at minimum:
+   - `provision_plan(...) -> AgentProvisionPlan` — what the existing
+     `agent_provision_plan` produces today, scoped to one provider.
+   - `provision_skills(bottle, plan)` — copy host skills into the guest.
+   - `provision_prompt(bottle, plan)` — copy the prompt file, return
+     the in-guest path (or None).
+   - `provision_supervise_mcp(bottle, plan, supervise_url)` — register
+     the supervise sidecar in the provider's MCP config. No-op when
+     the bottle has no supervise sidecar.
+   - The Claude implementation runs `claude mcp add`. The Codex
+     implementation writes the corresponding entry into
+     `~/.codex/config.toml`'s `[mcp_servers.supervise]` table.
+4. `BottleBackend` loses the four abstract methods being moved
+   (`provision_skills`, `provision_prompt`, `provision_provider_auth`,
+   `provision_supervise`). `BottleBackend.provision_in_bottle` calls
+   the provider plugin directly via the bottle and plan it already
+   has. `provision_ca`, `provision_workspace`, and `provision_git`
+   stay on the backend — they're backend infrastructure, not
+   provider behavior.
+5. `bot_bottle/backend/docker/provision/{skills,prompt,provider_auth,
+   supervise}.py` and `bot_bottle/backend/smolmachines/provision/{skills,
+   prompt,provider_auth,supervise}.py` are deleted. The
+   backend-specific provisioners that remain (`ca`, `git`,
+   `workspace`) stay.
+6. A Codex bottle launched with `--supervise` shows the
+   supervise MCP server entry in its Codex config and can call
+   supervise tools from inside the bottle (egress-block,
+   pipelock-block, capability-block).
+7. Existing tests for the moved logic move with the code:
+   provider-specific tests under `tests/unit/test_contrib_claude_*.py`
+   and `tests/unit/test_contrib_codex_*.py`, mirroring
+   `tests/unit/test_contrib_gitea_deploy_key.py`.
+8. PRD 0050's Status flips Draft → Active in the same commit that
+   removes the last `if template == "claude"` branch from
+   `agent_provider.py`.
+
+## Non-goals
+
+- **A third agent provider.** This PRD reshapes the boundary so a
+  third provider is cheap to add. It does not add one.
+- **Changing the manifest surface.** The `agent.provider`
+  manifest field still takes `"claude"` or `"codex"`. The set of
+  valid strings is unchanged.
+- **Changing `AgentProvisionPlan`'s shape.** The dataclasses
+  (`AgentProvisionDir`, `AgentProvisionFile`, `AgentProvisionCommand`,
+  `AgentProvisionPlan` itself) stay in the core module and keep their
+  current fields. Provider plugins produce the same plan shape; only
+  the producer moves.
+- **Changing the supervise sidecar protocol or the supervise tool
+  surface.** PRDs 0013–0016 stay Active. What changes is how the
+  agent discovers the sidecar's MCP endpoint, not what it does once
+  connected.
+- **Per-skill provider differences.** A Codex agent and a Claude
+  agent see the same `~/.claude/skills/<name>/` tree today (Codex
+  reads it via its own skills mechanism). This PRD does not change
+  that — `provision_skills` lands the same content for both.
+- **Removing the `prompt_args` helper from `agent_provider.py`.** It
+  stays at module scope; it's already a pure dispatch on `prompt_mode`
+  and has no Claude/Codex `if` chain to extract.
+- **`provision_provider_auth` migration.** The issue notes this method
+  is "probably not needed anymore" once each provider owns its own
+  provisioning. After the move, the work that
+  `provision_provider_auth` did (apply `dirs` / `files` / `pre_copy` /
+  `verify` from the plan) becomes a shared helper the per-provider
+  `provision_skills` / `provision_prompt` calls dispatch through —
+  or, more likely, a single `provision(bottle)` entry point on the
+  provider. The hook is removed from `BottleBackend`; whether the
+  underlying loop lives on `AgentProvider` as a default
+  implementation or as a free function in `contrib/_apply.py` is
+  decided at implementation time, not in this PRD.
+
+## Scope
+
+### In scope
+
+- New `AgentProvider` ABC in `bot_bottle/agent_provider.py` with the
+  five methods listed under Goal 3. Existing `agent_provision_plan`
+  becomes `AgentProvider.provision_plan`.
+- New `bot_bottle/contrib/claude/__init__.py`,
+  `bot_bottle/contrib/claude/agent_provider.py`,
+  `bot_bottle/contrib/codex/__init__.py`,
+  `bot_bottle/contrib/codex/agent_provider.py`. Each defines a
+  `ClaudeAgentProvider` / `CodexAgentProvider` class.
+- A `get_provider(template) -> AgentProvider` registry in
+  `bot_bottle/agent_provider.py`, lazy-imported from `contrib/`,
+  mirroring `get_provisioner(provider, ...)` in
+  `bot_bottle/deploy_key_provisioner.py`.
+- Backend changes:
+  - `BottleBackend.provision_in_bottle` resolves the provider once
+    and calls `provider.provision_skills(bottle, plan)`,
+    `provider.provision_prompt(bottle, plan)`, and
+    `provider.provision_supervise_mcp(bottle, plan, url)` in place
+    of the current four abstract hooks.
+  - `BottleBackend.provision_skills`, `provision_prompt`,
+    `provision_provider_auth`, `provision_supervise` are removed.
+  - Docker and smolmachines backends remove their corresponding
+    `provision_*` implementations and the
+    `backend/<name>/provision/{skills,prompt,provider_auth,
+    supervise}.py` modules.
+- Codex MCP wiring: `CodexAgentProvider.provision_supervise_mcp`
+  writes a `[mcp_servers.supervise]` block into
+  `~/.codex/config.toml` pointing at the same agent-side supervise
+  URL the Claude provider uses. The file already exists from the
+  trust-dialog step; the MCP entry is appended (or the file is
+  rewritten in a single shot, whichever's simpler).
+- Tests migrate. Backend tests that targeted the four moved
+  provisioners are rewritten against the provider plugin, with one
+  test file per provider mirroring `tests/unit/test_contrib_gitea_*.py`.
+
+### Out of scope
+
+- Adding a manifest field for "extra MCP servers the agent should
+  see". The supervise sidecar is the only MCP server provisioned
+  today, and the issue's "Add mcp server configuring into agent
+  provision" line is about the supervise sidecar specifically. A
+  general-purpose user-declared MCP list is a follow-up if and when
+  the need surfaces.
+- Refactoring `AgentProvisionPlan`'s dataclasses. They stay byte-
+  for-byte the same so the diff is purely "who owns the producer".
+- A `BottleBackend.provision_provider_auth` shim during transition.
+  The hook is removed in one cut; the only caller is the backend
+  itself, no manifest consumers reference it.
+- Renaming `agent_provider.py` → `agent_providers/`. The module
+  still has core dataclasses + the ABC + the registry; it's a single
+  file's worth of code.
+
+## Proposed design
+
+### Module shape after the cut
+
+```
+bot_bottle/agent_provider.py
+  PROVIDER_CLAUDE, PROVIDER_CODEX, PROVIDER_TEMPLATES
+  PromptMode  (Literal)
+  AgentProvisionDir, AgentProvisionFile, AgentProvisionCommand,
+    AgentProvisionPlan  (dataclasses, unchanged)
+  AgentProviderRuntime  (dataclass — template/command/image/etc.)
+  AgentProvider  (ABC)
+    .runtime() -> AgentProviderRuntime
+    .provision_plan(state_dir, ..., trusted_project_path, ...) -> AgentProvisionPlan
+    .provision_skills(bottle, plan) -> None
+    .provision_prompt(bottle, plan) -> str | None
+    .provision_supervise_mcp(bottle, plan, supervise_url) -> None
+  get_provider(template: str) -> AgentProvider     # lazy-imports contrib
+  prompt_args(prompt_mode, prompt_path, *, argv)   # unchanged
+
+bot_bottle/contrib/claude/agent_provider.py
+  ClaudeAgentProvider(AgentProvider)
+    _RUNTIME = AgentProviderRuntime(template="claude", ...)
+    .provision_plan(...)         # owns the lines-204–230 chunk
+    .provision_skills(...)       # was backend/<name>/provision/skills.py
+    .provision_prompt(...)       # was backend/<name>/provision/prompt.py
+    .provision_supervise_mcp(...)# was backend/<name>/provision/supervise.py
+
+bot_bottle/contrib/codex/agent_provider.py
+  CodexAgentProvider(AgentProvider)
+    _RUNTIME = AgentProviderRuntime(template="codex", ...)
+    .provision_plan(...)         # owns the lines-154–204 chunk
+    .provision_skills(...)       # same as Claude impl, factored to shared helper
+    .provision_prompt(...)       # same as Claude impl, factored to shared helper
+    .provision_supervise_mcp(...)# writes [mcp_servers.supervise] to config.toml
+```
+
+The skills / prompt / provider-auth-apply implementations are 99%
+identical across providers — `cp_in` then `chown` / `chmod`. They are
+extracted to small free functions in
+`bot_bottle/contrib/_provision_apply.py` (or kept as default
+implementations on `AgentProvider` if every concrete subclass would
+just call them). Picked at implementation time; both options match
+PRD 0048's contrib convention. The visible contract is that
+provisioning lives on the provider plugin.
+
+### MCP registration for Codex
+
+Codex reads MCP servers from `~/.codex/config.toml` (or whatever
+`CODEX_HOME/config.toml` resolves to). The provider already writes
+this file once during `provision_plan` to set the project trust
+level. `CodexAgentProvider.provision_supervise_mcp` extends the
+existing write: same path, append a `[mcp_servers.supervise]` table
+pointing at the agent-side supervise URL.
+
+Two implementation routes worth flagging:
+
+- **Option A:** Pre-bake the MCP entry in the same config-write that
+  happens during `provision_plan`, before bottle launch. Simpler;
+  the supervise URL has to be known at plan time, which means
+  `provision_plan` needs the supervise URL (or a sentinel that means
+  "fill this in"). The smolmachines backend already plumbs
+  `agent_supervise_url` through to its provision_supervise step, so
+  the value is available.
+- **Option B:** Append at bottle-launch time via a `bottle.exec`
+  that writes to the file inside the guest, matching the
+  `claude mcp add` flow. Slower but uniform with how
+  `ClaudeAgentProvider.provision_supervise_mcp` works.
+
+Option B is the symmetric choice and the one this PRD assumes.
+The implementer can switch to A if Option B turns out to need a
+TOML-merge primitive the codebase doesn't already have.
+
+### Backend after the cut
+
+```python
+class BottleBackend:
+    def provision_in_bottle(self, plan, bottle, supervise_url):
+        provider = get_provider(plan.spec.manifest.agents[
+            plan.spec.agent_name].provider)
+        self.provision_ca(plan, bottle)
+        prompt_path = provider.provision_prompt(bottle, plan)
+        provider.provision_skills(bottle, plan)
+        self.provision_workspace(plan, bottle)
+        self.provision_git(plan, bottle)
+        provider.provision_supervise_mcp(bottle, plan, supervise_url)
+        return prompt_path
+```
+
+`supervise_url` is the existing per-backend "where does the agent
+reach the sidecar from inside the guest" value. The Docker backend
+passes `http://supervise:<port>/`; smolmachines passes the
+`http://127.0.0.1:<port>/` it already computed. The backend's only
+remaining provider-touching duty is "tell the provider what the
+sidecar URL is".
+
+### Registry
+
+```python
+# bot_bottle/agent_provider.py
+def get_provider(template: str) -> AgentProvider:
+    if template == PROVIDER_CLAUDE:
+        from bot_bottle.contrib.claude.agent_provider import (
+            ClaudeAgentProvider,
+        )
+        return ClaudeAgentProvider()
+    if template == PROVIDER_CODEX:
+        from bot_bottle.contrib.codex.agent_provider import (
+            CodexAgentProvider,
+        )
+        return CodexAgentProvider()
+    raise ValueError(f"unknown agent provider template: {template!r}")
+```
+
+Lazy imports keep core import-time graph small and match PRD 0048.
+
+## Implementation chunks
+
+Each chunk is one commit on the PR; the PR ships as one cut.
+
+1. **Lift `AgentProvider` ABC + registry.** Add the ABC and
+   `get_provider` next to the existing `agent_provision_plan`
+   function. Have `agent_provision_plan` delegate to
+   `get_provider(template).provision_plan(...)` so callers keep
+   working through the transition.
+2. **Move provider-specific `provision_plan` content into
+   contrib.** Create `contrib/claude/` and `contrib/codex/`. The
+   Claude and Codex branches of `agent_provision_plan` move into
+   the respective provider classes. The shared scaffolding
+   (initial dict setup, final `AgentProvisionPlan(...)` return)
+   stays in the ABC as a template method or moves into each
+   subclass — whichever needs less indirection.
+3. **Move backend provisioners onto the provider.** Add
+   `provision_skills`, `provision_prompt`, `provision_supervise_mcp`
+   to `AgentProvider` (with a shared apply helper for skills /
+   prompt). Update `BottleBackend.provision_in_bottle` to call them.
+   Delete the four backend hook methods and the eight
+   `backend/<name>/provision/{skills,prompt,provider_auth,supervise}.py`
+   modules.
+4. **Add Codex MCP support.** Implement
+   `CodexAgentProvider.provision_supervise_mcp` against
+   `~/.codex/config.toml`. Add a unit test that runs the method
+   against an in-memory FakeBottle and asserts the
+   `[mcp_servers.supervise]` block is present.
+5. **Migrate tests.** Per-backend tests for the moved
+   provisioners turn into per-provider tests under
+   `tests/unit/test_contrib_claude_*.py` and
+   `tests/unit/test_contrib_codex_*.py`. Keep one integration-style
+   test per backend that confirms `provision_in_bottle` still
+   reaches every step.
+6. **Activate.** Flip Status: Draft → Active in this PRD; close
+   #177 on merge.
+
+## Open questions (resolved)
+
+1. **`codex mcp add` exists.** Implementation calls
+   `codex mcp add --transport http supervise <url>` as `node` —
+   symmetric with `claude mcp add` (no `--scope user`; Codex writes
+   `~/.codex/config.toml` by default). Failure logs a warning; the
+   bottle still works without the entry.
+2. **Each provider owns its apply steps end-to-end.** The base
+   ABC declares `provision_skills` / `provision_prompt` /
+   `provision` as abstract; each concrete provider implements its
+   own copy loop. No shared `_provision_apply.py`. The apply
+   sequences look similar today, but Claude and Codex harnesses
+   diverge over time (codex already grew a dummy-auth dance + a
+   `codex login status` verify with no Claude analogue) and the
+   "shared because both happen to call cp_in then chown" coupling
+   would just rot. Duplication is intentional.
+3. **Env knobs removed.** `BOT_BOTTLE_CONTAINER_HOME`,
+   `BOT_BOTTLE_GUEST_HOME`, `BOT_BOTTLE_CONTAINER_SKILLS_DIR`, and
+   `BOT_BOTTLE_GUEST_SKILLS_DIR` are gone; `/home/node` is hardcoded
+   everywhere it was read. The values were effectively constants;
+   the knobs added surface area for no real flexibility.
+
+## References
+
+- Issue
+  [#177](https://gitea.dideric.is/didericis/bot-bottle/issues/177)
+  — the request: move provider logic into contrib, add MCP
+  configuration to agent provision, rename provision_supervise →
+  provision_supervise_mcp, ensure Codex gets MCP provisioned.
+- PRD 0013 — supervise plane foundation (defines the MCP-discoverable
+  block-remediation tools this PRD makes available to Codex).
+- PRD 0048 — SSH deploy key provisioning (the `contrib/` convention
+  this PRD follows).
+- Current source:
+  [agent_provider.py L154-L230](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/bot_bottle/agent_provider.py#L154-L230)
+  — the provider-specific block this PRD relocates to contrib.

docs/research/gitea-webhook-agent-dispatch.md

@@ -0,0 +1,151 @@
+# Gitea Webhook Agent Dispatch
+
+## Question
+
+How should bot-bottle spawn and manage agents in response to Gitea PR events — and how do we reuse the same agent (with its full session context) across every event in a PR's lifecycle?
+
+## Summary
+
+A lightweight webhook receiver maps Gitea PR events to `cli.py` invocations. Spawning is straightforward: the existing work on non-interactive run mode (see [host-dispatch-to-container-agents.md](host-dispatch-to-container-agents.md)) is the missing piece. Session continuity is harder: it requires tracking two identifiers per open PR — the **bottle identity** (bot-bottle's slug for the container state dir) and the **Claude session ID** (the UUID Claude writes to its JSONL transcript). The transcript snapshot mechanism already used by capability-block is the right foundation; it just needs a non-interactive path and a PR-keyed store.
+
+## Gitea Webhook Events for PR Lifecycle
+
+Gitea fires `X-Gitea-Event: pull_request` (with an `action` field) for most PR state changes. The payload always includes `pull_request.number`, which is the stable key for correlating events to a running agent.
+
+| `X-Gitea-Event` value | Relevant `action` values | When it fires |
+|---|---|---|
+| `pull_request` | `opened`, `reopened`, `closed`, `synchronized` | PR created, closed, or pushed to |
+| `pull_request_comment` | `created`, `edited` | Timeline comment posted |
+| `pull_request_review_approved` | — | Review submitted with approval |
+| `pull_request_review_rejected` | — | Review submitted requesting changes |
+| `pull_request_review_comment` | — | Inline code review comment |
+| `pull_request_sync` | — | New commits pushed to the PR branch |
+
+`pull_request` with `action: synchronized` and `pull_request_sync` both fire on push; they carry the same information but are separate subscriptions in the webhook config UI. Subscribe to `pull_request` and `pull_request_review` (the umbrella) plus `pull_request_comment` to cover the full lifecycle.
+
+The webhook receiver validates the `X-Gitea-Signature-256` HMAC header (SHA-256 of the raw body, keyed by the configured secret) before dispatching.
+
+## Spawning an Agent From a Webhook
+
+### What we need from bot-bottle
+
+The current `cli.py start` is interactive — it prompts y/N and attaches a tty. A webhook handler needs a non-interactive mode that:
+
+1. Starts the container for a named agent.
+2. Runs `claude -p "<task>" --output-format json --dangerously-skip-permissions` inside it (no tty, no session picker).
+3. Captures stdout as JSON, extracts `session_id`.
+4. Blocks until Claude exits, then tears down.
+
+The [host-dispatch-to-container-agents](host-dispatch-to-container-agents.md) research proposes `cli.py run <agent> <task>` for exactly this. That command is the prerequisite for everything below. It should return the Claude JSON output so callers can extract `session_id`.
+
+### Webhook receiver sketch
+
+The receiver is a small HTTP service (Flask, FastAPI, or a Go net/http handler) running alongside bot-bottle on the host. It:
+
+1. Validates the HMAC signature.
+2. Extracts `pull_request.number` and `X-Gitea-Event` / `action`.
+3. Looks up whether a bottle already exists for this PR number.
+4. Spawns or resumes accordingly (see next section).
+5. Optionally posts a comment back to the PR via Gitea API once Claude finishes.
+
+The receiver does not need to be async or queue-based for a single-repo bot, but should at minimum serialize events for the same PR number (a per-PR lock) to avoid two concurrent sessions clobbering each other's transcript.
+
+## Reusing the Same Agent Across a PR
+
+This is the harder problem. Two separate identities need to be tracked and connected:
+
+### Identity 1: bottle identity (bot-bottle slug)
+
+The slug is the per-bottle state directory name (`~/.bot-bottle/state/<slug>/`). It's what `cli.py resume <slug>` uses to relaunch a container and mount the preserved state — including the transcript snapshot. This already works for the capability-block flow.
+
+### Identity 2: Claude session ID
+
+Claude Code's `--output-format json` response includes a `session_id` UUID. Passing `--resume <session_id>` on a subsequent non-interactive run makes Claude continue from exactly that conversation, with full memory of prior tool calls. `--continue` (which maps to `resume_args` in `agent_provider.py`) only picks up the *most recent* session in the project directory — unsafe when multiple sessions may be running concurrently.
+
+The session JSONL lives at `~/.claude/projects/<encoded-cwd>/<session_id>.jsonl` inside the container guest. The transcript snapshot (`snapshot_transcript(slug)` in `capability_apply.py`) copies all of `~/.claude` out of the container before teardown, so the JSONL is preserved in `~/.bot-bottle/state/<slug>/transcript/.claude/`. When the bottle is relaunched and the transcript remounted, `claude --resume <session_id>` can find the JSONL at the right path.
+
+### Per-PR session registry
+
+The receiver needs a small persistent map:
+
+```
+PR number → { bottle_identity: str, claude_session_id: str, agent_name: str }
+```
+
+The simplest implementation is a JSON file at `~/.bot-bottle/pr-sessions.json`, written after each successful first-run and updated with each resume. A sqlite database is better if concurrent multi-repo support is needed.
+
+### Full lifecycle flow
+
+```
+PR opened
+  → webhook: action=opened
+  → no entry in pr-sessions.json
+  → cli.py run <agent> "Review PR #N: <title>\n<diff URL>"
+      → starts container, runs claude -p ... --output-format json
+      → on success: captures session_id from JSON output
+      → snapshot_transcript(slug)
+      → tears down container
+  → write pr-sessions.json: { pr: N, slug: <slug>, session_id: <uuid> }
+
+PR gets new commit
+  → webhook: action=synchronized OR pull_request_sync
+  → look up pr-sessions.json: found slug + session_id
+  → cli.py run-resume <slug> --claude-session <session_id> "New commits pushed. Review the diff."
+      → relaunches container with transcript snapshot mounted
+      → runs claude -p ... --resume <session_id> --output-format json
+      → captures new session_id (same or rotated)
+      → snapshot_transcript(slug) again
+  → update pr-sessions.json with latest session_id
+
+Comment @-mentions bot
+  → webhook: pull_request_comment, action=created
+  → extract comment body, check for bot mention
+  → same resume flow as above with comment as the prompt
+
+PR closed / merged
+  → webhook: action=closed
+  → cli.py cleanup <slug> (or equivalent)
+  → remove from pr-sessions.json
+```
+
+### What needs to be built
+
+| Piece | Status | Notes |
+|---|---|---|
+| `cli.py run <agent> <task>` | Missing | Non-interactive start; see host-dispatch research |
+| `cli.py run-resume <slug> --claude-session <id> <task>` | Missing | Like `resume` but non-interactive, passes `--resume <id>` to claude |
+| `snapshot_transcript` on clean exit | Exists (PRD 0012) | Already called from `start.py`'s session-end path |
+| Transcript remount on resume | Exists | `bottle_state.py::transcript_snapshot_dir` → docker cp in on launch |
+| PR session registry | Missing | Needs to be designed; `~/.bot-bottle/pr-sessions.json` is the simplest start |
+| Webhook receiver service | Missing | New service; needs to be a declared bottle or run as a host process |
+
+## Known Rough Edges
+
+**Session ID is not available from within the session.** The ID is only in the `--output-format json` result, readable after the process exits. There is no env var or hook that exposes it mid-session ([upstream issue #44607](https://github.com/anthropics/claude-code/issues/44607)). For the webhook bot this is fine — the outer receiver reads it from the subprocess result.
+
+**`--continue` vs `--resume <id>`:** The existing `resume_args = ("--continue",)` in `agent_provider.py` picks up the *most recent* session. For an interactive single-user resume this is fine. For a webhook bot that may have multiple open PRs, it is not safe — two PRs' transcripts would collide if they share a project directory encoding. Use `--resume <session_id>` explicitly.
+
+**Project directory encoding.** Claude stores sessions keyed by the absolute cwd, encoded as a path. Inside the container the cwd is always `/home/node` or a subdir. As long as every run for the same PR uses the same cwd, `--resume <session_id>` will find the right JSONL. The cwd should be pinned per PR entry in the session registry.
+
+**Concurrent events for the same PR.** If two webhooks arrive close together (e.g., push + CI comment), the receiver must serialize them. A per-PR asyncio lock or a simple file lock on the session registry entry is enough.
+
+**Context window growth.** Each resume appends to the same session. A PR with many round trips will eventually hit the context limit. Mitigation options: start a fresh Claude session (new `cli.py run`) periodically and carry forward a summary; or rely on Claude's built-in compaction. The session registry could include a turn count to trigger rotation.
+
+**Webhook delivery ordering.** Gitea does not guarantee ordered delivery or exactly-once delivery. The receiver should be idempotent (same PR event processed twice should not create two bottles) and should ignore events for closed PRs.
+
+## Relationship to Existing Bot-Bottle Infrastructure
+
+The transcript snapshot + bottle identity system (PRD 0012, `capability_apply.py`) was designed for the capability-block flow: an operator-triggered resume after a security event. The webhook flow is the same mechanism on a faster loop driven by Gitea events instead of operator action. The implementation delta is:
+
+1. Non-interactive run mode (the `cli.py run` gap already identified in host-dispatch research).
+2. Passing `--resume <session_id>` explicitly rather than `--continue`.
+3. A PR-keyed registry to connect PR numbers to bottle identities and session IDs.
+4. A webhook receiver to drive the loop.
+
+These are additive changes that sit on top of the existing transcript preservation machinery without altering it.
+
+## Recommendation
+
+Start with the non-interactive run mode (`cli.py run`) since everything else depends on it. Once that exists, the webhook receiver and session registry are straightforward glue. The receiver should run as a host process (not inside a bottle) since it needs to call `cli.py` and manage the session registry file. Serialize per-PR to avoid concurrency bugs. Use `--resume <session_id>` (not `--continue`) for all resume paths.
+
+The PR session registry is deliberately minimal to start — a JSON file is fine. If multi-repo or multi-agent scenarios appear, migrating to sqlite is a one-file change.

docs/research/local-ollama-harness-and-model-selection.md

@@ -0,0 +1,278 @@
+# Local Ollama: Deployment Topology, Harness Selection, and Model Sizing
+
+Research notes on running Ollama locally for a bot-bottle coding agent workflow.
+Covers the native-vs-VM question, which harness integrates best with an agent loop,
+and which models make sense on an RTX 3070 (8 GB VRAM / 30 GB RAM) machine.
+
+---
+
+## 1. Deployment topology: native, container, or VM?
+
+The core question is whether running Ollama in a VM significantly degrades inference
+performance. The short answer: a full KVM/QEMU VM with GPU passthrough adds roughly
+2–5% overhead, Docker on Linux adds roughly 1–2%, and LXC containers add sub-1%. None
+of these are significant for interactive coding use.
+
+### Native (bare metal)
+
+Zero overhead, immediate GPU access, simplest setup. The right default for a solo
+developer doing inference on their own workstation.
+
+### Docker containers on Linux + NVIDIA
+
+With `nvidia-container-toolkit` and `--gpus all`, containerized Ollama runs at
+essentially native speed (~1–2% overhead on Linux). The dramatic exception is macOS,
+where Docker Desktop runs a Linux VM with no access to Apple's Metal/GPU — inference
+is 5–6× slower. On Linux/Windows with NVIDIA hardware, Docker is fine.
+
+Common pitfall: if `docker exec ollama ollama ps` shows 0 GPU layers, the container
+fell back to CPU. Usual causes: stale VRAM allocation, missing `nvidia-container-toolkit`,
+or a host driver too old for the container's CUDA version.
+
+### KVM/QEMU VM with full PCIe passthrough
+
+Full GPU passthrough makes the GPU invisible to the host while the VM owns it. Overhead
+from the IOMMU translation layer and virtualized PCIe bus is ~2–5%. This is viable if
+you need VM-level isolation (snapshotting, migration, separate kernel). Setup complexity
+is non-trivial: BIOS IOMMU, IOMMU group management, VFIO driver binding. Once configured
+it is stable.
+
+**Critical gotcha:** set the VM's CPU type to `host`. If left at the default
+(`x86-64-v2-AES` / "QEMU Virtual CPU version 2.5+"), Ollama may silently disable GPU
+support even when drivers appear correct.
+
+### LXC containers (Proxmox et al.)
+
+The sweet spot for isolation without overhead. Sub-1% performance difference from bare
+metal because LXC shares the host kernel; GPU device files are bind-mounted into the
+container. The tradeoff is weaker isolation (shared kernel) and the requirement that
+host and container driver versions match. Not suitable if you need VM-level snapshots
+or live migration.
+
+### Summary
+
+| Topology | GPU overhead | Isolation | Complexity |
+|---|---|---|---|
+| Native | 0% | None | Low |
+| Docker (Linux) | ~1–2% | Process | Low |
+| LXC | <1% | Namespace | Medium |
+| KVM passthrough | 2–5% | Full VM | High |
+| VM no passthrough | CPU-only | Full VM | Medium |
+
+Running Ollama in a VM will **not** significantly slow inference as long as GPU passthrough
+is configured. Without passthrough (software rendering / CPU fallback) performance
+collapses — that is what the user is rightly worried about.
+
+### Local vs. remote server
+
+| Factor | Local machine | Remote server |
+|---|---|---|
+| Latency | Near-zero | Network round-trip; cumulative in agent loops |
+| Cost | Zero after hardware | Per-token or subscription |
+| Privacy | 100% on-device | Data leaves the machine |
+| Model size ceiling | VRAM-limited | No hard limit (671B+ feasible) |
+| Offline use | Yes | No |
+| Concurrency under load | Sequential by default | Scales horizontally |
+
+For agentic coding workflows making 20–50 tool calls per session, network latency
+accumulates quickly. Local inference eliminates this. A practical hybrid pattern:
+use the local GPU for routine coding loops; route only to a remote API for tasks
+requiring a 70B+ model or very long context (>128K tokens).
+
+---
+
+## 2. Harness selection
+
+The landscape in 2026 has settled into three categories: IDE plugins, terminal agents,
+and chat UIs.
+
+### Continue.dev — recommended IDE plugin
+
+Open-source VS Code / JetBrains / Zed / Vim extension. Routes autocomplete, chat, and
+refactoring commands to any configured LLM backend (Ollama, cloud APIs). The recommended
+setup uses two models: a small FIM-capable model for inline autocomplete (Qwen2.5-Coder 7B)
+and a larger model for chat/edit. Handles inline completions, multi-file edits, and
+codebase-aware chat. No API key, no data leaving the machine.
+
+### Aider — recommended for git-native terminal workflows
+
+Terminal-based coding agent. Builds a codebase map before editing, makes changes
+directly, and auto-commits to git with readable messages. Every change is one
+`git revert` away. Supports 100+ languages; connects to any Ollama-served model
+via the OpenAI-compatible API. Best for terminal-first developers who want
+version-controlled agent interactions. Does not do inline autocomplete.
+
+### OpenCode — recommended for bot-bottle–style agent loops
+
+Terminal-based coding agent with 15 built-in tools (bash execution, file read/write/edit,
+grep, glob, web fetch, MCP support) and connections to 75+ model providers including
+local Ollama models. This is the closest open-source equivalent to a Claude Code–style
+plan → tool-call → execute → observe → loop. Native Ollama integration.
+
+**Critical setup note:** Ollama defaults to a 4096-token context window, which is
+completely insufficient for an agent loop carrying conversation history, tool schemas,
+a system prompt, and code simultaneously. Configure at least 64K tokens explicitly
+in the model's context settings.
+
+### Cline — agentic VS Code assistant
+
+VS Code extension that operates as an autonomous agent: plans, edits files, runs commands
+in a loop, connects to Ollama's local endpoint. Compared to OpenCode it lives inside the
+IDE rather than the terminal; compared to Continue.dev it is a full agent rather than a
+plugin. Its system prompt overhead is higher (~7,000–10,000 tokens) than minimal harnesses.
+
+### Open WebUI / Jan / LM Studio — chat UIs, not coding harnesses
+
+These are browser or desktop chat interfaces useful for ad-hoc conversations (explaining
+APIs, drafting documentation, exploring ideas) but without IDE integration, autocomplete,
+or git integration. LM Studio offers the smoothest onboarding (visual model browser with
+VRAM estimates). Jan is the most privacy-auditable (fully open-source, Apache 2.0, no
+telemetry). Neither is a replacement for a coding harness.
+
+### Harness comparison
+
+| Harness | Type | Autocomplete | Agent loop | Ollama | Git integration |
+|---|---|---|---|---|---|
+| Continue.dev | IDE plugin | Yes (FIM) | Basic | Native | No |
+| Aider | Terminal agent | No | Multi-turn | Via API | Auto-commit |
+| OpenCode | Terminal agent | No | Full tools | Native | Via bash |
+| Cline | IDE agent | No | Full tools | Via API | Via bash |
+| Open WebUI | Chat UI | No | No | Native | No |
+| Jan | Chat UI | No | No | Native | No |
+
+For a bot-bottle workflow (an isolated sandbox running an agentic loop with tool access),
+**OpenCode** is the closest open-source match. For an IDE-first developer who wants
+autocomplete + chat, **Continue.dev + Qwen2.5-Coder 7B** is the recommended pair.
+
+---
+
+## 3. Model selection: RTX 3070 (8 GB VRAM / 30 GB RAM)
+
+### VRAM hard limits at Q4_K_M quantization
+
+| Model size | Approx. VRAM (Q4_K_M) | Fits in 8 GB? | Tokens/sec (RTX 3070) |
+|---|---|---|---|
+| 3–4B | 2.5–3.5 GB | Yes, with headroom | 60–90 |
+| 7–8B | 5–6 GB | Yes | 35–55 |
+| 12–14B | 7.5–9 GB | Edge / RAM offload | 8–18 |
+| 22B+ | 14+ GB | No | — |
+
+The RTX 3070 has high memory bandwidth for its VRAM tier and consistently outperforms
+the newer RTX 4060 Ti on token generation speed. Bandwidth matters more than raw compute
+for inference.
+
+### Does Gemma 4 exist?
+
+Yes. Google released **Gemma 4** on 2 April 2026 (Apache 2.0). The family includes
+E2B (2B), E4B (4B), a 26B MoE, and a 31B Dense. A 12B multimodal variant was announced
+2026-06-04. The 31B scores 80.0% on LiveCodeBench v6 — a major jump from Gemma 3 27B
+at 29.1%. However, only the E4B fits comfortably within 8 GB VRAM:
+
+| Variant | VRAM (approx.) | Fits? |
+|---|---|---|
+| Gemma 4 E2B | ~2 GB | Yes |
+| Gemma 4 E4B | ~5 GB | Yes |
+| Gemma 4 12B | ~8–9 GB (Q4) | Edge |
+| Gemma 4 26B MoE | 14–18 GB | No |
+| Gemma 4 31B Dense | ~20 GB | No |
+
+### Model-by-model evaluation
+
+**Qwen2.5-Coder 7B — primary recommendation**
+
+The strongest purpose-built coding model that fits fully within 8 GB VRAM. Leads
+HumanEval among 7–8B-class models. Strong on Python, JavaScript, TypeScript. Has
+FIM (fill-in-the-middle) support for inline autocomplete. 35–55 tok/sec on RTX 3070.
+
+```
+ollama pull qwen2.5-coder:7b
+```
+
+**Qwen2.5-Coder 14B — secondary, with RAM offloading**
+
+At Q4_K_M this needs ~8.7 GB, just over the 8 GB limit. With 30 GB system RAM, Ollama
+automatically offloads the overflow layers to CPU. Performance drops to ~8–18 tok/sec
+versus 35–55 tok/sec for the 7B fully in VRAM. Quality is noticeably better for complex
+multi-file reasoning. Viable for chat-based coding tasks where quality matters more than
+speed; too slow for live autocomplete. Keep context window at 8K tokens to minimize
+VRAM pressure during offloaded inference.
+
+```
+ollama pull qwen2.5-coder:14b
+```
+
+**Gemma 4 E4B (~5 GB VRAM)**
+
+Fits comfortably with 3 GB to spare. Strong on reasoning, multimodal, and general-purpose
+tasks. Less specialized for coding than Qwen2.5-Coder 7B. Good choice for one model that
+covers coding + general reasoning + image analysis. The E4B outperforms Gemma 3 equivalents
+significantly on coding benchmarks.
+
+```
+ollama pull gemma4:e4b
+```
+
+**Phi-4 Mini 3.8B (~3 GB VRAM)**
+
+Best reasoning-per-VRAM model; leaves ~5 GB free for other applications. Strong on math,
+logic, and structured output. Good for agentic sub-tasks requiring tight reasoning. Not the
+strongest at raw code synthesis but excellent for reasoning-heavy parts of a coding loop.
+Viable as the autocomplete model in a two-model Continue.dev setup.
+
+```
+ollama pull phi4-mini
+```
+
+**DeepSeek-R1 8B (~5–6 GB VRAM)**
+
+Strong reasoning model for logic-heavy code (algorithms, correctness proofs). The full
+DeepSeek-Coder-V2 (236B MoE) is impractical here — only the 8B distilled variants are
+relevant. Outperforms Gemma 4 E4B on reasoning-heavy benchmarks; weaker on raw code
+generation than Qwen2.5-Coder 7B.
+
+**Codestral — not viable at 8 GB**
+
+The top FIM autocomplete model on HumanEval-FIM benchmarks, but requires 12–16 GB VRAM
+minimum. Not an option here. Worth revisiting if upgrading to a 12 GB+ card (RTX 4070
+Super or newer).
+
+### RAM offloading: does 30 GB help?
+
+Yes, meaningfully. Ollama automatically splits layers between GPU and system RAM when
+VRAM is exceeded. With 30 GB RAM, models up to ~14B at Q4_K_M run with partial offloading.
+The tradeoff is a 2–5× throughput penalty (8–18 tok/sec vs 35–55 tok/sec). Acceptable
+for batch tasks (reviewing a PR, generating an algorithm); too slow for live autocomplete.
+
+### Recommended setup
+
+**Autocomplete (fast, always-in-VRAM):** `qwen2.5-coder:7b`
+- Configure in Continue.dev as the tab-completion model
+- FIM-capable; 35–55 tok/sec; fits with 2–3 GB VRAM to spare
+
+**Chat / agent loop (quality-first):** `qwen2.5-coder:14b` or `gemma4:e4b`
+- 14B for strongest multi-file coding; expect 8–18 tok/sec with RAM offload
+- Gemma 4 E4B if you want vision + general reasoning + coding in one model; ~60 tok/sec
+
+**Two-model Continue.dev config (lower VRAM pressure):**
+`phi4-mini` (autocomplete) + `qwen2.5-coder:7b` (chat) — both fit simultaneously with
+~1–2 GB to spare, keeping the OS and IDE from contending for VRAM.
+
+---
+
+## Sources
+
+- [Ollama on Proxmox: GPU Passthrough for LXC and VM AI Workloads](https://linuxprofessional.ie/article.php?slug=ollama-proxmox-gpu-passthrough-lxc-vm)
+- [Run Ollama with NVIDIA GPU in Proxmox VMs and LXC containers](https://www.virtualizationhowto.com/2025/05/run-ollama-with-nvidia-gpu-in-proxmox-vms-and-lxc-containers/)
+- [Ollama Performance Tuning: Getting Maximum Speed from Local LLMs](https://dasroot.net/posts/2026/01/ollama-performance-tuning-gpu-acceleration-model-quantization/)
+- [Pros and Cons: Containerized Ollama vs. Local Setup](https://alain-airom.medium.com/pros-and-cons-using-containerized-ollama-vs-local-setup-d9bdf225bbb5)
+- [Best Local Coding Models Ranked: Every VRAM Tier (2026)](https://insiderllm.com/guides/best-local-coding-models-2026/)
+- [Best Local LLMs for RTX 4060, RTX 3070, and RTX 5060](https://aiagentskit.com/blog/best-local-llms-rtx-4060-3070-5060/)
+- [Best Local LLMs for 8GB VRAM: Real Hardware Benchmarks (2026)](https://localllm.in/blog/best-local-llms-8gb-vram-2025)
+- [Self-Hosted AI Coding Agent: Ollama + Continue + Open WebUI Setup in 2026](https://www.web3aiblog.com/blog/self-hosted-ai-coding-agent-ollama-continue-2026)
+- [Best Local-First AI Coding Tools 2026: 14 Compared](https://nimbalyst.com/blog/best-local-first-ai-coding-tools-2026/)
+- [OpenCode + Ollama: Private Local AI Coding Agent Setup](https://lushbinary.com/blog/opencode-ollama-local-ai-coding-privacy-guide/)
+- [Gemma 4: Google DeepMind](https://deepmind.google/models/gemma/gemma-4/)
+- [Running Gemma 4 Locally: VRAM Requirements](https://knightli.com/en/2026/05/01/gemma-4-local-vram-quantization-table/)
+- [Phi-4 Mini vs. Gemma 3 vs. Qwen 2.5: Best SLM for Coding Tasks in 2026](https://botmonster.com/ai/phi-4-mini-vs-gemma-3-vs-qwen-25-best-slm-coding-2026/)
+- [Qwen2.5-Coder 14B VRAM Requirements Guide](https://willitrunai.com/blog/qwen-2-5-coder-14b-vram-requirements)
+- [Comparing AI Harnesses: OpenCode, Ollama, LM Studio, Claude Code, Open WebUI, and VS Code](https://jace.pro/blog/comparing-ai-harnesses-opencode-ollama-lm-studio-claude-code-open-webui-and-vs-code/)

tests/unit/test_agent_provider.py

@@ -27,6 +27,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
     def test_codex_plan_declares_home_state(self):
         with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="codex",
                 dockerfile="/tmp/Dockerfile.codex",
                 state_dir=Path(tmp),
@@ -51,6 +52,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
     def test_codex_trusts_requested_project_path(self):
         with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
             agent_provision_plan(
+                guest_home="/home/node",
                 template="codex",
                 dockerfile="",
                 state_dir=Path(tmp),
@@ -68,6 +70,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
                 "tokens": {"access_token": _jwt(2000000000)},
             }))
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="codex",
                 dockerfile="",
                 state_dir=Path(tmp),
@@ -87,6 +90,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
     def test_claude_with_auth_token_injects_provider_route_and_placeholder(self):
         with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="claude",
                 dockerfile="/tmp/Dockerfile.claude",
                 state_dir=Path(tmp),
@@ -109,6 +113,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
     def test_claude_trusts_requested_project_path(self):
         with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
             agent_provision_plan(
+                guest_home="/home/node",
                 template="claude",
                 dockerfile="",
                 state_dir=Path(tmp),
@@ -127,6 +132,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
                 "tokens": {"access_token": _jwt(2000000000)},
             }))
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="codex",
                 dockerfile="",
                 state_dir=Path(tmp),
@@ -143,6 +149,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
     def test_codex_without_forward_host_credentials_has_passthrough_egress_routes(self):
         with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="codex",
                 dockerfile="",
                 state_dir=Path(tmp),
@@ -160,6 +167,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
     def test_claude_without_auth_token_has_passthrough_egress_route(self):
         with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="claude",
                 dockerfile="",
                 state_dir=Path(tmp),
@@ -183,6 +191,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
                 "tokens": {"access_token": access},
             }))
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="codex",
                 dockerfile="",
                 state_dir=Path(tmp),
@@ -197,6 +206,7 @@ class TestAgentProviderRuntime(unittest.TestCase):
     def test_codex_without_forward_host_credentials_has_empty_provisioned_env(self):
         with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
             plan = agent_provision_plan(
+                guest_home="/home/node",
                 template="codex",
                 dockerfile="",
                 state_dir=Path(tmp),

tests/unit/test_compose.py

@@ -164,6 +164,7 @@ def _plan(
 
     spec = _spec(supervise=supervise, with_git=with_git, with_egress=with_egress)
     return DockerBottlePlan(
+        guest_home="/home/node",
         spec=spec,
         stage_dir=STAGE,
         slug=SLUG,

tests/unit/test_contrib_claude_provider.py

@@ -0,0 +1,303 @@
+"""Unit: ClaudeAgentProvider provisioning (PRD 0050, contrib/claude).
+
+Each provider owns its own in-guest provisioning end-to-end —
+skills copy, prompt copy, declarative dirs/files/pre_copy/verify
+apply, and supervise MCP registration. The Claude / Codex paths
+intentionally don't share a helper module: harness changes on
+either side are expected to diverge the implementations."""
+
+from __future__ import annotations
+
+import unittest
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+from bot_bottle.agent_provider import (
+    AgentProvisionCommand,
+    AgentProvisionDir,
+    AgentProvisionFile,
+    AgentProvisionPlan,
+)
+from bot_bottle.backend import Bottle, BottleSpec, ExecResult
+from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
+from bot_bottle.contrib.claude.agent_provider import ClaudeAgentProvider
+from bot_bottle.egress import EgressPlan
+from bot_bottle.git_gate import GitGatePlan
+from bot_bottle.manifest import Manifest
+from bot_bottle.pipelock import PipelockProxyPlan
+from bot_bottle.supervise import SupervisePlan
+from bot_bottle.workspace import workspace_plan
+
+
+_URL = "http://supervise:9100/"
+
+
+def _make_bottle(exec_result: ExecResult | None = None) -> MagicMock:
+    bottle = MagicMock(spec=Bottle)
+    bottle.name = "bot-bottle-demo-abc12"
+    bottle.exec.return_value = (
+        exec_result if exec_result is not None
+        else ExecResult(returncode=0, stdout="", stderr="")
+    )
+    return bottle
+
+
+def _exec_scripts(bottle: MagicMock) -> list[str]:
+    return [c.args[0] for c in bottle.exec.call_args_list]
+
+
+def _plan(
+    *,
+    agent_prompt: str = "",
+    skills: list[str] | None = None,
+    agent_provision: AgentProvisionPlan | None = None,
+    supervise: bool = False,
+) -> DockerBottlePlan:
+    bottle_json: dict = {"agent_provider": {"template": "claude"}}
+    if supervise:
+        bottle_json["supervise"] = True
+    manifest = Manifest.from_json_obj({
+        "bottles": {"dev": bottle_json},
+        "agents": {
+            "demo": {
+                "skills": list(skills or []),
+                "prompt": agent_prompt,
+                "bottle": "dev",
+            },
+        },
+    })
+    spec = BottleSpec(
+        manifest=manifest, agent_name="demo",
+        copy_cwd=False, user_cwd="/tmp/x",
+    )
+    supervise_plan = None
+    if supervise:
+        supervise_plan = SupervisePlan(
+            slug="demo-abc12",
+            queue_dir=Path("/tmp/queue"),
+            current_config_dir=Path("/tmp/current-config"),
+        )
+    return DockerBottlePlan(
+        guest_home="/home/node",
+        spec=spec,
+        stage_dir=Path("/tmp/stage"),
+        slug="demo-abc12",
+        container_name="bot-bottle-demo-abc12",
+        container_name_pinned=False,
+        image="bot-bottle-claude:latest",
+        derived_image="",
+        runtime_image="bot-bottle-claude:latest",
+        dockerfile_path="",
+        env_file=Path("/tmp/agent.env"),
+        forwarded_env={},
+        prompt_file=Path("/tmp/state/demo-abc12/agent/prompt.txt"),
+        proxy_plan=PipelockProxyPlan(
+            yaml_path=Path("/tmp/pipelock.yaml"), slug="demo-abc12",
+        ),
+        git_gate_plan=GitGatePlan(
+            slug="demo-abc12",
+            entrypoint_script=Path("/tmp/git-gate-entrypoint.sh"),
+            hook_script=Path("/tmp/git-gate-hook"),
+            access_hook_script=Path("/tmp/git-gate-access-hook"),
+            upstreams=(),
+        ),
+        egress_plan=EgressPlan(
+            slug="demo-abc12",
+            routes_path=Path("/tmp/routes.yaml"),
+            routes=(),
+            token_env_map={},
+        ),
+        supervise_plan=supervise_plan,
+        use_runsc=False,
+        agent_provision=agent_provision or AgentProvisionPlan(
+            template="claude", command="claude", prompt_mode="append_file",
+            image="", dockerfile="", guest_env={},
+        ),
+        workspace_plan=workspace_plan(spec, guest_home="/home/node"),
+    )
+
+
+class TestClaudeProvisionPrompt(unittest.TestCase):
+    def test_cp_uses_bottle_cp_in(self):
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision_prompt(_plan(), bottle)
+        bottle.cp_in.assert_called_once_with(
+            "/tmp/state/demo-abc12/agent/prompt.txt",
+            "/home/node/.bot-bottle-prompt.txt",
+        )
+
+    def test_returns_path_when_agent_has_prompt(self):
+        bottle = _make_bottle()
+        r = ClaudeAgentProvider().provision_prompt(
+            _plan(agent_prompt="You are helpful."), bottle,
+        )
+        self.assertEqual("/home/node/.bot-bottle-prompt.txt", r)
+
+    def test_returns_none_when_agent_has_no_prompt(self):
+        bottle = _make_bottle()
+        r = ClaudeAgentProvider().provision_prompt(_plan(agent_prompt=""), bottle)
+        self.assertIsNone(r)
+        bottle.cp_in.assert_called_once()
+
+    def test_chowns_to_node_after_copy(self):
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision_prompt(_plan(), bottle)
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(
+            any("chown node:node" in s
+                and "/home/node/.bot-bottle-prompt.txt" in s
+                for s in scripts)
+        )
+        self.assertTrue(
+            any("chmod 600" in s
+                and "/home/node/.bot-bottle-prompt.txt" in s
+                for s in scripts)
+        )
+
+
+class TestClaudeProvisionSkills(unittest.TestCase):
+    def test_noop_when_agent_has_no_skills(self):
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision_skills(_plan(skills=[]), bottle)
+        bottle.cp_in.assert_not_called()
+        bottle.exec.assert_not_called()
+
+    def test_mkdir_plus_cp_per_skill(self):
+        bottle = _make_bottle()
+        with patch(
+            "bot_bottle.backend.util.host_skill_dir",
+            side_effect=lambda n: f"/host/skills/{n}",
+        ), patch(
+            "bot_bottle.contrib.claude.agent_provider.os.path.isdir",
+            return_value=True,
+        ):
+            ClaudeAgentProvider().provision_skills(
+                _plan(skills=["init-prd", "verify"]), bottle,
+            )
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(
+            any("mkdir -p" in s and "/home/node/.claude/skills" in s
+                for s in scripts)
+        )
+        cp_targets = {c.args[1] for c in bottle.cp_in.call_args_list}
+        self.assertEqual({
+            "/home/node/.claude/skills/init-prd/",
+            "/home/node/.claude/skills/verify/",
+        }, cp_targets)
+        self.assertEqual(
+            2, sum(1 for s in scripts if "chown -R node:node" in s),
+        )
+
+    def test_missing_skill_dies(self):
+        bottle = _make_bottle()
+        with patch(
+            "bot_bottle.backend.util.host_skill_dir",
+            side_effect=lambda n: f"/host/skills/{n}",
+        ), patch(
+            "bot_bottle.contrib.claude.agent_provider.os.path.isdir",
+            return_value=False,
+        ):
+            with self.assertRaises(SystemExit):
+                ClaudeAgentProvider().provision_skills(
+                    _plan(skills=["init-prd"]), bottle,
+                )
+
+
+class TestClaudeProvision(unittest.TestCase):
+    """The declarative dirs/files/pre_copy/verify apply loop for
+    the claude.json trust marker."""
+
+    def test_noop_on_empty_provision_plan(self):
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision(_plan(), bottle)
+        bottle.cp_in.assert_not_called()
+        bottle.exec.assert_not_called()
+
+    def test_copies_files_and_chowns(self):
+        provision = AgentProvisionPlan(
+            template="claude", command="claude", prompt_mode="append_file",
+            image="", dockerfile="", guest_env={},
+            files=(AgentProvisionFile(
+                Path("/tmp/claude.json"), "/home/node/.claude.json",
+            ),),
+        )
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision(
+            _plan(agent_provision=provision), bottle,
+        )
+        bottle.cp_in.assert_called_once_with(
+            "/tmp/claude.json", "/home/node/.claude.json",
+        )
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(
+            any("chown" in s and "/home/node/.claude.json" in s for s in scripts)
+        )
+        self.assertTrue(
+            any("chmod" in s and "/home/node/.claude.json" in s for s in scripts)
+        )
+
+    def test_dies_when_file_chown_fails(self):
+        provision = AgentProvisionPlan(
+            template="claude", command="claude", prompt_mode="append_file",
+            image="", dockerfile="", guest_env={},
+            files=(AgentProvisionFile(
+                Path("/tmp/claude.json"), "/home/node/.claude.json",
+            ),),
+        )
+        bottle = _make_bottle(
+            exec_result=ExecResult(1, "", "chown: no such file\n"),
+        )
+        with self.assertRaises(SystemExit):
+            ClaudeAgentProvider().provision(
+                _plan(agent_provision=provision), bottle,
+            )
+
+    def test_runs_verify_commands(self):
+        provision = AgentProvisionPlan(
+            template="claude", command="claude", prompt_mode="append_file",
+            image="", dockerfile="", guest_env={},
+            verify=(AgentProvisionCommand(
+                ("/usr/bin/true",), "verify failed",
+            ),),
+        )
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision(
+            _plan(agent_provision=provision), bottle,
+        )
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(any("/usr/bin/true" in s for s in scripts))
+
+
+class TestClaudeSuperviseMcp(unittest.TestCase):
+    def test_noop_when_supervise_disabled(self):
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision_supervise_mcp(
+            _plan(supervise=False), bottle, _URL,
+        )
+        bottle.exec.assert_not_called()
+
+    def test_runs_claude_mcp_add_as_node(self):
+        bottle = _make_bottle()
+        ClaudeAgentProvider().provision_supervise_mcp(
+            _plan(supervise=True), bottle, _URL,
+        )
+        bottle.exec.assert_called_once()
+        script = bottle.exec.call_args.args[0]
+        self.assertEqual("node", bottle.exec.call_args.kwargs.get("user"))
+        self.assertIn("claude mcp add", script)
+        self.assertIn("--scope user", script)
+        self.assertIn("--transport http", script)
+        self.assertIn("supervise", script)
+        self.assertIn(_URL, script)
+
+    def test_logs_warning_on_failure_but_does_not_raise(self):
+        bottle = _make_bottle(
+            exec_result=ExecResult(returncode=1, stdout="", stderr="boom"),
+        )
+        ClaudeAgentProvider().provision_supervise_mcp(
+            _plan(supervise=True), bottle, _URL,
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_contrib_codex_provider.py

@@ -0,0 +1,271 @@
+"""Unit: CodexAgentProvider provisioning (PRD 0050, contrib/codex).
+
+The Codex provider owns its own skills / prompt / provision /
+supervise-mcp end-to-end — symmetric with the claude provider but
+not sharing a helper module, since codex's apply steps include
+the dummy-auth dance and a `codex login status` verify that have
+no claude equivalent."""
+
+from __future__ import annotations
+
+import unittest
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+from bot_bottle.agent_provider import (
+    AgentProvisionCommand,
+    AgentProvisionDir,
+    AgentProvisionFile,
+    AgentProvisionPlan,
+)
+from bot_bottle.backend import Bottle, BottleSpec, ExecResult
+from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
+from bot_bottle.contrib.codex.agent_provider import CodexAgentProvider
+from bot_bottle.egress import EgressPlan
+from bot_bottle.git_gate import GitGatePlan
+from bot_bottle.manifest import Manifest
+from bot_bottle.pipelock import PipelockProxyPlan
+from bot_bottle.supervise import SupervisePlan
+from bot_bottle.workspace import workspace_plan
+
+
+_URL = "http://supervise:9100/"
+
+
+def _make_bottle(exec_result: ExecResult | None = None) -> MagicMock:
+    bottle = MagicMock(spec=Bottle)
+    bottle.name = "bot-bottle-demo-abc12"
+    bottle.exec.return_value = (
+        exec_result if exec_result is not None
+        else ExecResult(returncode=0, stdout="", stderr="")
+    )
+    return bottle
+
+
+def _exec_scripts(bottle: MagicMock) -> list[str]:
+    return [c.args[0] for c in bottle.exec.call_args_list]
+
+
+def _plan(
+    *,
+    agent_prompt: str = "",
+    skills: list[str] | None = None,
+    agent_provision: AgentProvisionPlan | None = None,
+    supervise: bool = False,
+) -> DockerBottlePlan:
+    bottle_json: dict = {"agent_provider": {"template": "codex"}}
+    if supervise:
+        bottle_json["supervise"] = True
+    manifest = Manifest.from_json_obj({
+        "bottles": {"dev": bottle_json},
+        "agents": {
+            "demo": {
+                "skills": list(skills or []),
+                "prompt": agent_prompt,
+                "bottle": "dev",
+            },
+        },
+    })
+    spec = BottleSpec(
+        manifest=manifest, agent_name="demo",
+        copy_cwd=False, user_cwd="/tmp/x",
+    )
+    supervise_plan = None
+    if supervise:
+        supervise_plan = SupervisePlan(
+            slug="demo-abc12",
+            queue_dir=Path("/tmp/queue"),
+            current_config_dir=Path("/tmp/current-config"),
+        )
+    return DockerBottlePlan(
+        guest_home="/home/node",
+        spec=spec,
+        stage_dir=Path("/tmp/stage"),
+        slug="demo-abc12",
+        container_name="bot-bottle-demo-abc12",
+        container_name_pinned=False,
+        image="bot-bottle-codex:latest",
+        derived_image="",
+        runtime_image="bot-bottle-codex:latest",
+        dockerfile_path="",
+        env_file=Path("/tmp/agent.env"),
+        forwarded_env={},
+        prompt_file=Path("/tmp/state/demo-abc12/agent/prompt.txt"),
+        proxy_plan=PipelockProxyPlan(
+            yaml_path=Path("/tmp/pipelock.yaml"), slug="demo-abc12",
+        ),
+        git_gate_plan=GitGatePlan(
+            slug="demo-abc12",
+            entrypoint_script=Path("/tmp/git-gate-entrypoint.sh"),
+            hook_script=Path("/tmp/git-gate-hook"),
+            access_hook_script=Path("/tmp/git-gate-access-hook"),
+            upstreams=(),
+        ),
+        egress_plan=EgressPlan(
+            slug="demo-abc12",
+            routes_path=Path("/tmp/routes.yaml"),
+            routes=(),
+            token_env_map={},
+        ),
+        supervise_plan=supervise_plan,
+        use_runsc=False,
+        agent_provision=agent_provision or AgentProvisionPlan(
+            template="codex", command="codex", prompt_mode="read_prompt_file",
+            image="", dockerfile="", guest_env={},
+        ),
+        workspace_plan=workspace_plan(spec, guest_home="/home/node"),
+    )
+
+
+class TestCodexProvisionPrompt(unittest.TestCase):
+    def test_cp_uses_bottle_cp_in_and_chowns(self):
+        bottle = _make_bottle()
+        r = CodexAgentProvider().provision_prompt(
+            _plan(agent_prompt="hello"), bottle,
+        )
+        self.assertEqual("/home/node/.bot-bottle-prompt.txt", r)
+        bottle.cp_in.assert_called_once_with(
+            "/tmp/state/demo-abc12/agent/prompt.txt",
+            "/home/node/.bot-bottle-prompt.txt",
+        )
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(
+            any("chown node:node" in s
+                and "/home/node/.bot-bottle-prompt.txt" in s
+                for s in scripts)
+        )
+
+    def test_returns_none_when_agent_has_no_prompt(self):
+        bottle = _make_bottle()
+        r = CodexAgentProvider().provision_prompt(_plan(agent_prompt=""), bottle)
+        self.assertIsNone(r)
+        bottle.cp_in.assert_called_once()
+
+
+class TestCodexProvisionSkills(unittest.TestCase):
+    def test_noop_when_agent_has_no_skills(self):
+        bottle = _make_bottle()
+        CodexAgentProvider().provision_skills(_plan(skills=[]), bottle)
+        bottle.cp_in.assert_not_called()
+        bottle.exec.assert_not_called()
+
+    def test_mkdir_plus_cp_per_skill(self):
+        bottle = _make_bottle()
+        with patch(
+            "bot_bottle.backend.util.host_skill_dir",
+            side_effect=lambda n: f"/host/skills/{n}",
+        ), patch(
+            "bot_bottle.contrib.codex.agent_provider.os.path.isdir",
+            return_value=True,
+        ):
+            CodexAgentProvider().provision_skills(
+                _plan(skills=["init-prd"]), bottle,
+            )
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(
+            any("mkdir -p" in s and "/home/node/.claude/skills" in s
+                for s in scripts)
+        )
+        bottle.cp_in.assert_called_once()
+        self.assertEqual(
+            "/home/node/.claude/skills/init-prd/",
+            bottle.cp_in.call_args.args[1],
+        )
+
+
+class TestCodexProvision(unittest.TestCase):
+    """Codex's declarative provision step: ~/.codex/ dir + config.toml
+    + (optional) dummy-auth.json + `codex login status` verify."""
+
+    def test_creates_dir_and_copies_config(self):
+        provision = AgentProvisionPlan(
+            template="codex", command="codex",
+            prompt_mode="read_prompt_file",
+            image="", dockerfile="", guest_env={},
+            dirs=(AgentProvisionDir("/home/node/.codex"),),
+            files=(AgentProvisionFile(
+                Path("/tmp/codex-config.toml"),
+                "/home/node/.codex/config.toml",
+            ),),
+        )
+        bottle = _make_bottle()
+        CodexAgentProvider().provision(
+            _plan(agent_provision=provision), bottle,
+        )
+        bottle.cp_in.assert_called_once_with(
+            "/tmp/codex-config.toml",
+            "/home/node/.codex/config.toml",
+        )
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(any("mkdir -p" in s and "/home/node/.codex" in s for s in scripts))
+        self.assertTrue(any("chown" in s and "/home/node/.codex/config.toml" in s for s in scripts))
+        self.assertTrue(any("chmod" in s and "/home/node/.codex/config.toml" in s for s in scripts))
+
+    def test_runs_pre_copy_then_verify(self):
+        provision = AgentProvisionPlan(
+            template="codex", command="codex",
+            prompt_mode="read_prompt_file",
+            image="", dockerfile="", guest_env={},
+            pre_copy=(AgentProvisionCommand(
+                ("find", "/home/node/.codex", "-name", "*.sqlite", "-delete"),
+                "could not reset runtime db files",
+            ),),
+            verify=(AgentProvisionCommand(
+                ("runuser", "-u", "node", "--", "codex", "login", "status"),
+                "codex rejected the dummy auth",
+            ),),
+        )
+        bottle = _make_bottle()
+        CodexAgentProvider().provision(
+            _plan(agent_provision=provision), bottle,
+        )
+        scripts = _exec_scripts(bottle)
+        self.assertTrue(any("find" in s and "-delete" in s for s in scripts))
+        self.assertTrue(any("runuser" in s and "codex login status" in s for s in scripts))
+
+    def test_dies_when_dir_creation_fails(self):
+        provision = AgentProvisionPlan(
+            template="codex", command="codex",
+            prompt_mode="read_prompt_file",
+            image="", dockerfile="", guest_env={},
+            dirs=(AgentProvisionDir("/home/node/.codex"),),
+        )
+        bottle = _make_bottle(exec_result=ExecResult(1, "", "mkdir: nope\n"))
+        with self.assertRaises(SystemExit):
+            CodexAgentProvider().provision(
+                _plan(agent_provision=provision), bottle,
+            )
+
+
+class TestCodexSuperviseMcp(unittest.TestCase):
+    def test_noop_when_supervise_disabled(self):
+        bottle = _make_bottle()
+        CodexAgentProvider().provision_supervise_mcp(
+            _plan(supervise=False), bottle, _URL,
+        )
+        bottle.exec.assert_not_called()
+
+    def test_runs_codex_mcp_add_as_node(self):
+        bottle = _make_bottle()
+        CodexAgentProvider().provision_supervise_mcp(
+            _plan(supervise=True), bottle, _URL,
+        )
+        bottle.exec.assert_called_once()
+        script = bottle.exec.call_args.args[0]
+        self.assertEqual("node", bottle.exec.call_args.kwargs.get("user"))
+        self.assertIn("codex mcp add", script)
+        self.assertIn("--transport http", script)
+        self.assertIn("supervise", script)
+        self.assertIn(_URL, script)
+
+    def test_logs_warning_on_failure_but_does_not_raise(self):
+        bottle = _make_bottle(
+            exec_result=ExecResult(returncode=1, stdout="", stderr="boom"),
+        )
+        CodexAgentProvider().provision_supervise_mcp(
+            _plan(supervise=True), bottle, _URL,
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_docker_launch_teardown.py

@@ -44,6 +44,7 @@ def _plan(tmp: str) -> DockerBottlePlan:
         identity="test-teardown-00001",
     )
     return DockerBottlePlan(
+        guest_home="/home/node",
         spec=spec,
         stage_dir=stage,
         git_gate_plan=GitGatePlan(

tests/unit/test_docker_provision_git_user.py

@@ -1,20 +1,20 @@
 """Unit: docker backend `_provision_git_user` (issue #86).
 
-Mocks `subprocess.run` and asserts the `docker exec -u node …
+Mocks `bottle.exec` / `bottle.cp_in` and asserts on the script
-git config --global …` argv shape. The cwd + git-gate passes
+strings and user parameter. The cwd + git-gate passes are covered
-are covered indirectly by the existing integration-shaped tests
+indirectly by the existing integration-shaped tests in
-in test_smolmachines_provision; this file targets just the new
+test_smolmachines_provision; this file targets just the git_user
-git_user pass."""
+pass."""
 
 from __future__ import annotations
 
 import tempfile
 import unittest
 from pathlib import Path
-from unittest.mock import patch
+from unittest.mock import MagicMock, call
 
 from bot_bottle.agent_provider import AgentProvisionPlan
-from bot_bottle.backend import BottleSpec
+from bot_bottle.backend import Bottle, BottleSpec, ExecResult
 from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
 from bot_bottle.backend.docker.provision import git as _git
 from bot_bottle.egress import EgressPlan
@@ -40,6 +40,7 @@ def _plan(*, git_user: dict | None = None,
         copy_cwd=copy_cwd, user_cwd=user_cwd,
     )
     return DockerBottlePlan(
+        guest_home="/home/node",
         spec=spec,
         stage_dir=stage_dir or Path("/tmp/stage"),
         slug="demo-abc12",
@@ -82,16 +83,22 @@ def _plan(*, git_user: dict | None = None,
     )
 
 
-def _git_config_calls(mock_run) -> list[list[str]]:
+def _make_bottle(name: str = "bot-bottle-demo-abc12") -> MagicMock:
-    """Filter `subprocess.run` calls down to the ones that run
+    bottle = MagicMock(spec=Bottle)
-    `git config --global` inside the bottle, returning each argv."""
+    bottle.name = name
-    out: list[list[str]] = []
+    bottle.exec.return_value = ExecResult(returncode=0, stdout="", stderr="")
-    for call in mock_run.call_args_list:
+    return bottle
-        argv = call.args[0]
+
-        if (len(argv) >= 5
+
-                and argv[0] == "docker" and argv[1] == "exec"
+def _git_config_exec_calls(bottle: MagicMock) -> list[tuple[str, str]]:
-                and "git" in argv and "config" in argv):
+    """Filter bottle.exec calls to git-config invocations.
-            out.append(list(argv))
+    Returns list of (script, user) tuples."""
+    out = []
+    for c in bottle.exec.call_args_list:
+        script = c.args[0] if c.args else c.kwargs.get("script", "")
+        user = c.kwargs.get("user", c.args[1] if len(c.args) > 1 else "node")
+        if "git config" in script:
+            out.append((script, user))
     return out
 
 
@@ -104,71 +111,65 @@ class TestProvisionGitUser(unittest.TestCase):
         self._tmp.cleanup()
 
     def test_noop_when_no_git_user(self):
-        with patch.object(_git.subprocess, "run") as run:
+        bottle = _make_bottle()
-            _git._provision_git_user(
+        _git._provision_git_user(_plan(stage_dir=self.stage), bottle)
-                _plan(stage_dir=self.stage), "bot-bottle-demo-abc12",
+        self.assertEqual([], _git_config_exec_calls(bottle))
-            )
-        self.assertEqual([], _git_config_calls(run))
 
     def test_copies_cwd_git_to_workspace_plan_path(self):
         cwd = self.stage / "cwd"
         (cwd / ".git").mkdir(parents=True)
         plan = _plan(copy_cwd=True, user_cwd=str(cwd), stage_dir=self.stage)
-        with patch.object(_git.subprocess, "run") as run:
+        bottle = _make_bottle()
-            _git._provision_cwd_git(plan, "bot-bottle-demo-abc12")
+        _git._provision_cwd_git(plan, bottle)
 
-        self.assertEqual(
+        bottle.cp_in.assert_called_once_with(
-            [
+            f"{cwd}/.git",
-                "docker", "cp", f"{cwd}/.git",
+            "/home/node/workspace/.git",
-                "bot-bottle-demo-abc12:/home/node/workspace/.git",
-            ],
-            run.call_args_list[0].args[0],
-        )
-        self.assertEqual(
-            [
-                "docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-                "chown", "-R", "node:node", "/home/node/workspace/.git",
-            ],
-            run.call_args_list[1].args[0],
         )
+        chown_calls = [
+            c for c in bottle.exec.call_args_list
+            if "chown" in (c.args[0] if c.args else "")
+        ]
+        self.assertEqual(1, len(chown_calls))
+        self.assertIn("node:node", chown_calls[0].args[0])
+        self.assertIn("/home/node/workspace/.git", chown_calls[0].args[0])
 
     def test_sets_name_and_email(self):
         plan = _plan(
             git_user={"name": "Eric Bauerfeld", "email": "eric@dideric.is"},
             stage_dir=self.stage,
         )
-        with patch.object(_git.subprocess, "run") as run:
+        bottle = _make_bottle()
-            _git._provision_git_user(plan, "bot-bottle-demo-abc12")
+        _git._provision_git_user(plan, bottle)
-        calls = _git_config_calls(run)
+        calls = _git_config_exec_calls(bottle)
         self.assertEqual(2, len(calls))
-        # All `docker exec` invocations run as `-u node` so the
+        for script, user in calls:
-        # --global config lands in /home/node/.gitconfig.
+            self.assertEqual("node", user)
-        for argv in calls:
+            self.assertIn("git config --global", script)
-            self.assertEqual(
+        self.assertIn("user.name", calls[0][0])
-                ["docker", "exec", "-u", "node", "bot-bottle-demo-abc12",
+        self.assertIn("Eric Bauerfeld", calls[0][0])
-                 "git", "config", "--global"],
+        self.assertIn("user.email", calls[1][0])
-                argv[:8],
+        self.assertIn("eric@dideric.is", calls[1][0])
-            )
-        self.assertEqual(["user.name", "Eric Bauerfeld"], calls[0][8:])
-        self.assertEqual(["user.email", "eric@dideric.is"], calls[1][8:])
 
     def test_name_only_sets_only_name(self):
         plan = _plan(git_user={"name": "Bot"}, stage_dir=self.stage)
-        with patch.object(_git.subprocess, "run") as run:
+        bottle = _make_bottle()
-            _git._provision_git_user(plan, "bot-bottle-demo-abc12")
+        _git._provision_git_user(plan, bottle)
-        calls = _git_config_calls(run)
+        calls = _git_config_exec_calls(bottle)
         self.assertEqual(1, len(calls))
-        self.assertEqual(["user.name", "Bot"], calls[0][8:])
+        self.assertIn("user.name", calls[0][0])
+        self.assertIn("Bot", calls[0][0])
 
     def test_email_only_sets_only_email(self):
         plan = _plan(
             git_user={"email": "bot@example.com"}, stage_dir=self.stage,
         )
-        with patch.object(_git.subprocess, "run") as run:
+        bottle = _make_bottle()
-            _git._provision_git_user(plan, "bot-bottle-demo-abc12")
+        _git._provision_git_user(plan, bottle)
-        calls = _git_config_calls(run)
+        calls = _git_config_exec_calls(bottle)
         self.assertEqual(1, len(calls))
-        self.assertEqual(["user.email", "bot@example.com"], calls[0][8:])
+        self.assertIn("user.email", calls[0][0])
+        self.assertIn("bot@example.com", calls[0][0])
 
 
 if __name__ == "__main__":

tests/unit/test_docker_provision_provider_auth.py

@@ -1,191 +0,0 @@
-"""Unit: docker provider auth marker provisioning."""
-
-from __future__ import annotations
-
-import unittest
-from pathlib import Path
-from unittest.mock import patch
-
-from bot_bottle.agent_provider import (
-    AgentProvisionDir,
-    AgentProvisionFile,
-    AgentProvisionPlan,
-)
-from bot_bottle.backend import BottleSpec
-from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
-from bot_bottle.backend.docker.provision import provider_auth as _provider_auth
-from bot_bottle.egress import EgressPlan
-from bot_bottle.git_gate import GitGatePlan
-from bot_bottle.manifest import Manifest
-from bot_bottle.pipelock import PipelockProxyPlan
-from bot_bottle.workspace import workspace_plan
-
-
-def _plan(
-    *,
-    codex_auth_file: Path | None = None,
-    agent_provider_template: str = "codex",
-) -> DockerBottlePlan:
-    manifest = Manifest.from_json_obj({
-        "bottles": {"dev": {"agent_provider": {"template": "codex"}}},
-        "agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
-    })
-    spec = BottleSpec(
-        manifest=manifest,
-        agent_name="demo",
-        copy_cwd=False,
-        user_cwd="/tmp/x",
-    )
-    return DockerBottlePlan(
-        spec=spec,
-        stage_dir=Path("/tmp/stage"),
-        slug="demo-abc12",
-        container_name="bot-bottle-demo-abc12",
-        container_name_pinned=False,
-        image="bot-bottle-codex:latest",
-        derived_image="",
-        runtime_image="bot-bottle-codex:latest",
-        dockerfile_path="",
-        env_file=Path("/tmp/agent.env"),
-        forwarded_env={},
-        prompt_file=Path("/tmp/prompt.txt"),
-        proxy_plan=PipelockProxyPlan(
-            yaml_path=Path("/tmp/pipelock.yaml"),
-            slug="demo-abc12",
-        ),
-        git_gate_plan=GitGatePlan(
-            slug="demo-abc12",
-            entrypoint_script=Path("/tmp/git-gate-entrypoint.sh"),
-            hook_script=Path("/tmp/git-gate-hook"),
-            access_hook_script=Path("/tmp/git-gate-access-hook"),
-            upstreams=(),
-        ),
-        egress_plan=EgressPlan(
-            slug="demo-abc12",
-            routes_path=Path("/tmp/routes.yaml"),
-            routes=(),
-            token_env_map={},
-        ),
-        supervise_plan=None,
-        use_runsc=False,
-        agent_provision=_agent_provision(
-            agent_provider_template, codex_auth_file=codex_auth_file,
-        ),
-        workspace_plan=workspace_plan(spec, guest_home="/home/node"),
-    )
-
-
-def _agent_provision(
-    template: str, *, codex_auth_file: Path | None = None,
-) -> AgentProvisionPlan:
-    if template != "codex":
-        return AgentProvisionPlan(
-            template=template,
-            command=template,
-            prompt_mode="append_file",
-            image="",
-            dockerfile="",
-            guest_env={},
-        )
-    files = [
-        AgentProvisionFile(
-            Path("/tmp/codex-config.toml"),
-            "/home/node/.codex/config.toml",
-        ),
-    ]
-    if codex_auth_file is not None:
-        files.append(AgentProvisionFile(
-            codex_auth_file,
-            "/home/node/.codex/auth.json",
-        ))
-    return AgentProvisionPlan(
-        template="codex",
-        command="codex",
-        prompt_mode="read_prompt_file",
-        image="bot-bottle-codex:latest",
-        dockerfile="",
-        guest_env={},
-        dirs=(AgentProvisionDir("/home/node/.codex"),),
-        files=tuple(files),
-    )
-
-
-class TestProvisionProviderAuth(unittest.TestCase):
-    def test_noop_for_non_codex_provider(self):
-        with patch.object(_provider_auth.subprocess, "run") as run:
-            _provider_auth.provision_provider_auth(
-                _plan(agent_provider_template="claude"), "bot-bottle-demo-abc12",
-            )
-        self.assertEqual(0, run.call_count)
-
-    def test_codex_provider_trusts_launch_dir_without_auth_file(self):
-        with patch.object(_provider_auth.subprocess, "run") as run:
-            _provider_auth.provision_provider_auth(
-                _plan(), "bot-bottle-demo-abc12",
-            )
-        argvs = [call.args[0] for call in run.call_args_list]
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "mkdir", "-p", "/home/node/.codex"],
-            argvs,
-        )
-        trust_config = next(
-            a for a in argvs
-            if a[:2] == ["docker", "cp"] and a[2] == "/tmp/codex-config.toml"
-        )
-        self.assertEqual(
-            "bot-bottle-demo-abc12:/home/node/.codex/config.toml",
-            trust_config[3],
-        )
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "chown", "node:node", "/home/node/.codex/config.toml"],
-            argvs,
-        )
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "chmod", "600", "/home/node/.codex/config.toml"],
-            argvs,
-        )
-
-    def test_copies_dummy_auth_json_to_codex_home(self):
-        with patch.object(_provider_auth.subprocess, "run") as run:
-            _provider_auth.provision_provider_auth(
-                _plan(codex_auth_file=Path("/tmp/codex-auth.json")),
-                "bot-bottle-demo-abc12",
-            )
-        argvs = [call.args[0] for call in run.call_args_list]
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "mkdir", "-p", "/home/node/.codex"],
-            argvs,
-        )
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "chown", "node:node", "/home/node/.codex"],
-            argvs,
-        )
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "chmod", "700", "/home/node/.codex"],
-            argvs,
-        )
-        self.assertIn(
-            ["docker", "cp", "/tmp/codex-auth.json",
-             "bot-bottle-demo-abc12:/home/node/.codex/auth.json"],
-            argvs,
-        )
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "chown", "node:node", "/home/node/.codex/auth.json"],
-            argvs,
-        )
-        self.assertIn(
-            ["docker", "exec", "-u", "0", "bot-bottle-demo-abc12",
-             "chmod", "600", "/home/node/.codex/auth.json"],
-            argvs,
-        )
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_plan_print_parity.py

@@ -103,6 +103,7 @@ def _proxy_plan(tmp: str) -> PipelockProxyPlan:
 def _docker_plan(spec: BottleSpec, tmp: str) -> DockerBottlePlan:
     stage = Path(tmp)
     return DockerBottlePlan(
+        guest_home="/home/node",
         spec=spec,
         stage_dir=stage,
         git_gate_plan=_git_gate_plan(tmp),
@@ -128,6 +129,7 @@ def _docker_plan(spec: BottleSpec, tmp: str) -> DockerBottlePlan:
 def _smolmachines_plan(spec: BottleSpec, tmp: str) -> SmolmachinesBottlePlan:
     stage = Path(tmp)
     return SmolmachinesBottlePlan(
+        guest_home="/home/node",
         spec=spec,
         stage_dir=stage,
         git_gate_plan=_git_gate_plan(tmp),

tests/unit/test_provision_supervise.py

@@ -1,30 +0,0 @@
-"""Unit: supervise MCP provisioning (PRD 0013 follow-up).
-
-The real provisioning runs `claude mcp add` inside the agent
-container — exercised by the existing supervise integration test
-chain once the agent container is brought up. Here we just cover
-the URL computation so a regression in SUPERVISE_HOSTNAME / PORT
-plumbing surfaces in unit CI."""
-
-import unittest
-
-from bot_bottle.backend.docker.provision.supervise import supervise_mcp_url
-from bot_bottle.supervise import SUPERVISE_HOSTNAME, SUPERVISE_PORT
-
-
-class TestSuperviseMcpUrl(unittest.TestCase):
-    def test_url_matches_sidecar_constants(self):
-        self.assertEqual(
-            f"http://{SUPERVISE_HOSTNAME}:{SUPERVISE_PORT}/",
-            supervise_mcp_url(),
-        )
-
-    def test_url_is_http_not_https(self):
-        # The agent dials the sidecar on the internal docker network;
-        # no TLS termination, no CA trust juggling. If this ever
-        # needs HTTPS, the sidecar's listener side has to change too.
-        self.assertTrue(supervise_mcp_url().startswith("http://"))
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_smolmachines_provision.py

@@ -1,8 +1,8 @@
 """Unit: smolmachines provisioning helpers (PRD 0023 chunks 4a + 4d).
 
-Tests mock `smolvm.machine_cp` / `smolvm.machine_exec` and assert
+Tests mock `bottle.exec` / `bottle.cp_in` and assert on the
-on the dispatched call shape. The real round-trip lives in the
+dispatched script shape. The real round-trip lives in the chunk-4
-chunk-4 integration smoke."""
+integration smoke."""
 
 from __future__ import annotations
 
@@ -11,7 +11,7 @@ import tempfile
 import unittest
 from dataclasses import replace
 from pathlib import Path
-from unittest.mock import patch
+from unittest.mock import MagicMock, patch
 
 from bot_bottle.agent_provider import (
     AgentProvisionCommand,
@@ -19,21 +19,16 @@ from bot_bottle.agent_provider import (
     AgentProvisionFile,
     AgentProvisionPlan,
 )
-from bot_bottle.backend import BottleSpec
+from bot_bottle.backend import Bottle, BottleSpec, ExecResult
 from bot_bottle.backend.smolmachines.bottle_plan import (
     SmolmachinesBottlePlan,
 )
 from bot_bottle.backend.smolmachines.provision import (
     ca as _ca,
     git as _git,
-    prompt as _prompt,
-    provider_auth as _provider_auth,
-    skills as _skills,
-    supervise as _supervise,
     workspace as _workspace,
 )
 from bot_bottle.backend.smolmachines.launch import _bundle_launch_spec
-from bot_bottle.backend.smolmachines.smolvm import SmolvmRunResult
 from bot_bottle.egress import EgressPlan, EgressRoute
 from bot_bottle.git_gate import GitGatePlan, GitGateUpstream
 from bot_bottle.manifest import GitEntry, Manifest
@@ -42,6 +37,28 @@ from bot_bottle.supervise import SupervisePlan
 from bot_bottle.workspace import workspace_plan
 
 
+def _make_bottle(
+    name: str = "bot-bottle-demo-abc12",
+    exec_result: ExecResult | None = None,
+) -> MagicMock:
+    bottle = MagicMock(spec=Bottle)
+    bottle.name = name
+    bottle.exec.return_value = (
+        exec_result if exec_result is not None
+        else ExecResult(returncode=0, stdout="", stderr="")
+    )
+    return bottle
+
+
+def _exec_scripts(bottle: MagicMock) -> list[str]:
+    """All script strings passed to bottle.exec, in call order."""
+    return [c.args[0] for c in bottle.exec.call_args_list]
+
+
+def _exec_users(bottle: MagicMock) -> list[str]:
+    """user= kwarg from each bottle.exec call, in order."""
+    return [c.kwargs.get("user", "node") for c in bottle.exec.call_args_list]
+
 
 def _plan(
     *,
@@ -103,6 +120,7 @@ def _plan(
             current_config_dir=Path("/tmp/current-config"),
         )
     return SmolmachinesBottlePlan(
+        guest_home="/home/node",
         spec=spec,
         stage_dir=stage_dir or Path("/tmp/stage"),
         slug="demo-abc12",
@@ -202,340 +220,6 @@ def _agent_provision(
     )
 
 
-class TestProvisionPrompt(unittest.TestCase):
-    def test_cp_uses_smolvm_machine_cp_with_machine_path_syntax(self):
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_cp"
-        ) as cp, patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_exec"
-        ):
-            _prompt.provision_prompt(_plan(), "bot-bottle-demo-abc12")
-        cp.assert_called_once_with(
-            "/tmp/state/demo-abc12/agent/prompt.txt",
-            "bot-bottle-demo-abc12:/home/node/.bot-bottle-prompt.txt",
-        )
-
-    def test_returns_path_when_agent_has_prompt(self):
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_cp"
-        ), patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_exec"
-        ):
-            r = _prompt.provision_prompt(
-                _plan(agent_prompt="You are a helpful assistant."),
-                "bot-bottle-demo-abc12",
-            )
-        self.assertEqual("/home/node/.bot-bottle-prompt.txt", r)
-
-    def test_returns_none_when_agent_has_no_prompt(self):
-        # The file is still copied (path-must-exist contract);
-        # only the return value differs.
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_cp"
-        ) as cp, patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_exec"
-        ):
-            r = _prompt.provision_prompt(_plan(agent_prompt=""), "bot-bottle-demo-abc12")
-        self.assertIsNone(r)
-        cp.assert_called_once()
-
-    def test_chowns_to_node_after_copy(self):
-        # machine cp lands as root; without the chown, the node user
-        # can't read its own mode-600 prompt.
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_cp"
-        ), patch(
-            "bot_bottle.backend.smolmachines.provision.prompt._smolvm.machine_exec"
-        ) as ex:
-            _prompt.provision_prompt(_plan(), "bot-bottle-demo-abc12")
-        argv_seen = [call.args[1] for call in ex.call_args_list]
-        self.assertIn(
-            ["chown", "node:node", "/home/node/.bot-bottle-prompt.txt"],
-            argv_seen,
-        )
-        self.assertIn(
-            ["chmod", "600", "/home/node/.bot-bottle-prompt.txt"],
-            argv_seen,
-        )
-
-
-class TestProvisionProviderAuth(unittest.TestCase):
-    def _patch(self):
-        return (
-            patch(
-                "bot_bottle.backend.smolmachines.provision.provider_auth._smolvm.machine_cp"
-            ),
-            patch(
-                "bot_bottle.backend.smolmachines.provision.provider_auth._smolvm.machine_exec"
-            ),
-        )
-
-    def test_noop_for_non_codex_provider(self):
-        cp_p, ex_p = self._patch()
-        with cp_p as cp, ex_p as ex:
-            _provider_auth.provision_provider_auth(_plan(), "bot-bottle-demo-abc12")
-        self.assertEqual(0, cp.call_count)
-        self.assertEqual(0, ex.call_count)
-
-    def test_codex_provider_trusts_launch_dir_without_auth_file(self):
-        cp_p, ex_p = self._patch()
-        with cp_p as cp, ex_p as ex:
-            ex.return_value = SmolvmRunResult(0, "", "")
-            _provider_auth.provision_provider_auth(
-                _plan(agent_provider_template="codex"),
-                "bot-bottle-demo-abc12",
-            )
-        cp.assert_called_once_with(
-            "/tmp/codex-config.toml",
-            "bot-bottle-demo-abc12:/home/node/.codex/config.toml",
-        )
-        argv_seen = [call.args[1] for call in ex.call_args_list]
-        self.assertIn(["mkdir", "-p", "/home/node/.codex"], argv_seen)
-        self.assertIn(
-            ["chown", "node:node", "/home/node/.codex/config.toml"],
-            argv_seen,
-        )
-        self.assertIn(["chmod", "600", "/home/node/.codex/config.toml"], argv_seen)
-
-    def test_copies_dummy_auth_json_to_codex_home(self):
-        cp_p, ex_p = self._patch()
-        with cp_p as cp, ex_p as ex:
-            ex.return_value = SmolvmRunResult(0, "Logged in using ChatGPT\n", "")
-            _provider_auth.provision_provider_auth(
-                _plan(
-                    agent_provider_template="codex",
-                    codex_auth_file=Path("/tmp/codex-auth.json"),
-                ),
-                "bot-bottle-demo-abc12",
-            )
-        cp_calls = [call.args for call in cp.call_args_list]
-        self.assertIn(
-            ("/tmp/codex-config.toml",
-             "bot-bottle-demo-abc12:/home/node/.codex/config.toml"),
-            cp_calls,
-        )
-        self.assertIn(
-            ("/tmp/codex-auth.json",
-             "bot-bottle-demo-abc12:/home/node/.codex/auth.json"),
-            cp_calls,
-        )
-        argv_seen = [call.args[1] for call in ex.call_args_list]
-        self.assertIn(["mkdir", "-p", "/home/node/.codex"], argv_seen)
-        self.assertIn(
-            ["chown", "node:node", "/home/node/.codex"],
-            argv_seen,
-        )
-        self.assertIn(
-            ["chmod", "700", "/home/node/.codex"],
-            argv_seen,
-        )
-        self.assertIn(
-            [
-                "find", "/home/node/.codex",
-                "-maxdepth", "1",
-                "-type", "f",
-                "(",
-                "-name", "*.sqlite",
-                "-o", "-name", "*.sqlite-*",
-                "-o", "-name", "*.codex-repair-*.bak",
-                ")",
-                "-delete",
-            ],
-            argv_seen,
-        )
-        self.assertIn(
-            ["chown", "node:node", "/home/node/.codex/auth.json"],
-            argv_seen,
-        )
-        self.assertIn(["chmod", "600", "/home/node/.codex/auth.json"], argv_seen)
-        self.assertIn(
-            [
-                "runuser", "-u", "node", "--",
-                "env",
-                "HOME=/home/node",
-                "CODEX_HOME=/home/node/.codex",
-                "codex", "login", "status",
-            ],
-            argv_seen,
-        )
-
-    def test_honors_codex_home_from_guest_env(self):
-        cp_p, ex_p = self._patch()
-        with cp_p as cp, ex_p as ex:
-            ex.return_value = SmolvmRunResult(0, "Logged in using ChatGPT\n", "")
-            _provider_auth.provision_provider_auth(
-                _plan(
-                    agent_provider_template="codex",
-                    codex_auth_file=Path("/tmp/codex-auth.json"),
-                    guest_env={"CODEX_HOME": "/run/codex-home"},
-                ),
-                "bot-bottle-demo-abc12",
-            )
-        cp_calls = [call.args for call in cp.call_args_list]
-        self.assertIn(
-            ("/tmp/codex-config.toml",
-             "bot-bottle-demo-abc12:/run/codex-home/config.toml"),
-            cp_calls,
-        )
-        self.assertIn(
-            ("/tmp/codex-auth.json",
-             "bot-bottle-demo-abc12:/run/codex-home/auth.json"),
-            cp_calls,
-        )
-        argv_seen = [call.args[1] for call in ex.call_args_list]
-        self.assertIn(
-            [
-                "runuser", "-u", "node", "--",
-                "env",
-                "HOME=/home/node",
-                "CODEX_HOME=/run/codex-home",
-                "codex", "login", "status",
-            ],
-            argv_seen,
-        )
-
-    def test_dies_when_codex_home_cannot_be_created(self):
-        cp_p, ex_p = self._patch()
-        with cp_p as cp, ex_p as ex:
-            ex.return_value = SmolvmRunResult(1, "", "mkdir: nope\n")
-            with self.assertRaises(SystemExit):
-                _provider_auth.provision_provider_auth(
-                    _plan(
-                        agent_provider_template="codex",
-                        codex_auth_file=Path("/tmp/codex-auth.json"),
-                    ),
-                    "bot-bottle-demo-abc12",
-                )
-        self.assertEqual(0, cp.call_count)
-        self.assertEqual(1, ex.call_count)
-
-    def test_dies_when_codex_rejects_dummy_auth(self):
-        cp_p, ex_p = self._patch()
-        with cp_p, ex_p as ex:
-            # CODEX_HOME setup ok (0), but codex login status fails (1).
-            ex.side_effect = [
-                SmolvmRunResult(0, "", ""),  # mkdir CODEX_HOME
-                SmolvmRunResult(0, "", ""),  # chown CODEX_HOME
-                SmolvmRunResult(0, "", ""),  # chmod CODEX_HOME
-                SmolvmRunResult(0, "", ""),  # reset runtime db files
-                SmolvmRunResult(0, "", ""),  # chown config.toml
-                SmolvmRunResult(0, "", ""),  # chmod config.toml
-                SmolvmRunResult(0, "", ""),  # chown auth.json
-                SmolvmRunResult(0, "", ""),  # chmod auth.json
-                SmolvmRunResult(1, "Not logged in\n", ""),  # login status
-            ]
-            with self.assertRaises(SystemExit):
-                _provider_auth.provision_provider_auth(
-                    _plan(
-                        agent_provider_template="codex",
-                        codex_auth_file=Path("/tmp/codex-auth.json"),
-                    ),
-                    "bot-bottle-demo-abc12",
-                )
-
-
-class TestProvisionSkills(unittest.TestCase):
-    def _patch_host_skill_dir(self, returns: dict[str, str]):
-        return patch(
-            "bot_bottle.backend.smolmachines.provision.skills.host_skill_dir",
-            side_effect=lambda n: returns.get(n, f"/nope/{n}"),
-        )
-
-    def test_no_op_when_agent_has_no_skills(self):
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_cp"
-        ) as cp, patch(
-            "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_exec"
-        ) as ex:
-            _skills.provision_skills(_plan(skills=[]), "bot-bottle-demo-abc12")
-        self.assertEqual(0, cp.call_count)
-        self.assertEqual(0, ex.call_count)
-
-    def test_mkdir_plus_cp_per_skill(self):
-        with self._patch_host_skill_dir({
-            "init-prd": "/host/skills/init-prd",
-            "verify": "/host/skills/verify",
-        }), patch(
-            "bot_bottle.backend.smolmachines.provision.skills.os.path.isdir",
-            return_value=True,
-        ), patch(
-            "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_cp"
-        ) as cp, patch(
-            "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_exec"
-        ) as ex:
-            _skills.provision_skills(
-                _plan(skills=["init-prd", "verify"]),
-                "bot-bottle-demo-abc12",
-            )
-
-        # mkdir -p once + (rm -rf + chown) per skill = 5 exec calls.
-        self.assertEqual(5, ex.call_count)
-        mkdir_call = ex.call_args_list[0]
-        self.assertEqual(
-            ("bot-bottle-demo-abc12", ["mkdir", "-p", "/home/node/.claude/skills"]),
-            mkdir_call.args,
-        )
-        # Two cp calls, one per skill, into the per-skill subdir.
-        self.assertEqual(2, cp.call_count)
-        cp_targets = {call.args[1] for call in cp.call_args_list}
-        self.assertEqual(
-            {
-                "bot-bottle-demo-abc12:/home/node/.claude/skills/init-prd",
-                "bot-bottle-demo-abc12:/home/node/.claude/skills/verify",
-            },
-            cp_targets,
-        )
-        # Each skill gets a chown -R node:node so claude can read it.
-        chown_argvs = [
-            call.args[1] for call in ex.call_args_list
-            if call.args[1][:1] == ["chown"]
-        ]
-        self.assertEqual(2, len(chown_argvs))
-        chown_targets = {argv[-1] for argv in chown_argvs}
-        self.assertEqual(
-            {
-                "/home/node/.claude/skills/init-prd",
-                "/home/node/.claude/skills/verify",
-            },
-            chown_targets,
-        )
-
-    def test_skills_dir_overridable_via_env(self):
-        import os
-        with self._patch_host_skill_dir({"init-prd": "/host/skills/init-prd"}), \
-             patch(
-                 "bot_bottle.backend.smolmachines.provision.skills.os.path.isdir",
-                 return_value=True,
-             ), \
-             patch.dict(os.environ, {"BOT_BOTTLE_GUEST_SKILLS_DIR": "/home/node/.claude/skills"}), \
-             patch(
-                 "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_cp"
-             ) as cp, \
-             patch(
-                 "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_exec"
-             ):
-            _skills.provision_skills(_plan(skills=["init-prd"]), "bot-bottle-demo-abc12")
-        self.assertEqual(
-            "bot-bottle-demo-abc12:/home/node/.claude/skills/init-prd",
-            cp.call_args.args[1],
-        )
-
-    def test_missing_skill_dies(self):
-        with self._patch_host_skill_dir({"init-prd": "/host/skills/init-prd"}), \
-             patch(
-                 "bot_bottle.backend.smolmachines.provision.skills.os.path.isdir",
-                 return_value=False,
-             ), \
-             patch(
-                 "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_cp"
-             ), \
-             patch(
-                 "bot_bottle.backend.smolmachines.provision.skills._smolvm.machine_exec"
-             ):
-            with self.assertRaises(SystemExit):
-                _skills.provision_skills(_plan(skills=["init-prd"]), "bot-bottle-demo-abc12")
-
-
 def _write_self_signed_cert(path: Path) -> None:
     """Drop a real self-signed PEM at `path` so provision_ca's
     fingerprint computation (PEM_cert_to_DER_cert + sha256) has
@@ -553,7 +237,7 @@ def _write_self_signed_cert(path: Path) -> None:
 class TestProvisionCA(unittest.TestCase):
     """provision_ca selects the right CA cert (egress when the
     bottle has routes, else pipelock) and dispatches
-    machine_cp + machine_exec in the right order."""
+    cp_in + exec in the right order."""
 
     def setUp(self):
         self._tmp = tempfile.TemporaryDirectory(prefix="cb-prov-ca.")
@@ -566,10 +250,10 @@ class TestProvisionCA(unittest.TestCase):
     def tearDown(self):
         self._tmp.cleanup()
 
-    # provision_ca dies hard if update-ca-certificates' stdout
+    # provision_ca dies hard if update-ca-certificates' exit
-    # doesn't include "1 added"; supply a stock success return
+    # is non-zero; supply a stock success return so the bulk of
-    # so the bulk of the tests below exercise the happy path.
+    # the tests below exercise the happy path.
-    _UPDATE_OK = SmolvmRunResult(
+    _UPDATE_OK = ExecResult(
         returncode=0,
         stdout="Updating certificates in /etc/ssl/certs...\n1 added, 0 removed; done.\n",
         stderr="",
@@ -577,27 +261,20 @@ class TestProvisionCA(unittest.TestCase):
 
     def test_pipelock_path_when_no_routes(self):
         plan = _plan(pipelock_ca_path=self.pipelock_ca)
-        with patch(
+        bottle = _make_bottle(exec_result=self._UPDATE_OK)
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_cp"
+        _ca.provision_ca(plan, bottle)
-        ) as cp, patch(
+        bottle.cp_in.assert_called_once_with(
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec",
-            return_value=self._UPDATE_OK,
-        ) as ex:
-            _ca.provision_ca(plan, "bot-bottle-demo-abc12")
-        cp.assert_called_once_with(
             str(self.pipelock_ca),
-            "bot-bottle-demo-abc12:" + _ca.AGENT_CA_PATH,
+            _ca.AGENT_CA_PATH,
         )
-        # chmod + chown + update-ca-certificates are now folded
+        # chmod + chown + update-ca-certificates are folded into
-        # into one `sh -c` invocation (working around a smolvm
+        # one exec invocation; look at the single exec's script
-        # exec warm-up SIGKILL race), so we look at the single
+        # rather than expecting separate calls.
-        # exec's argv rather than expecting separate calls.
+        bottle.exec.assert_called_once()
-        ex.assert_called_once()
+        script = bottle.exec.call_args.args[0]
-        argv = ex.call_args.args[1]
+        self.assertIn("chmod 644", script)
-        self.assertEqual("sh", argv[0])
+        self.assertIn("update-ca-certificates", script)
-        self.assertEqual("-c", argv[1])
+        self.assertEqual("root", bottle.exec.call_args.kwargs.get("user"))
-        self.assertIn("chmod 644", argv[2])
-        self.assertIn("update-ca-certificates", argv[2])
 
     def test_egress_path_when_routes_declared(self):
         plan = _plan(
@@ -605,51 +282,39 @@ class TestProvisionCA(unittest.TestCase):
             egress_ca_path=self.egress_ca,
             pipelock_ca_path=self.pipelock_ca,
         )
-        with patch(
+        bottle = _make_bottle(exec_result=self._UPDATE_OK)
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_cp"
+        _ca.provision_ca(plan, bottle)
-        ) as cp, patch(
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec",
-            return_value=self._UPDATE_OK,
-        ):
-            _ca.provision_ca(plan, "bot-bottle-demo-abc12")
         # When routes are declared, egress is the agent's first hop,
         # so egress's CA is the one that gets installed.
-        cp.assert_called_once_with(
+        bottle.cp_in.assert_called_once_with(
             str(self.egress_ca),
-            "bot-bottle-demo-abc12:" + _ca.AGENT_CA_PATH,
+            _ca.AGENT_CA_PATH,
         )
 
     def test_retries_smolvm_sigkill_during_update_ca(self):
         plan = _plan(pipelock_ca_path=self.pipelock_ca)
-        killed = SmolvmRunResult(
+        killed = ExecResult(
             returncode=137,
             stdout="Updating certificates in /etc/ssl/certs...\n",
             stderr="",
         )
+        bottle = _make_bottle()
+        bottle.exec.side_effect = [killed, self._UPDATE_OK]
         with patch(
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_cp"
-        ), patch(
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec",
-            side_effect=[killed, self._UPDATE_OK],
-        ) as ex, patch(
             "bot_bottle.backend.smolmachines.provision.ca.time.sleep"
         ) as sleep:
-            _ca.provision_ca(plan, "bot-bottle-demo-abc12")
+            _ca.provision_ca(plan, bottle)
 
-        self.assertEqual(2, ex.call_count)
+        self.assertEqual(2, bottle.exec.call_count)
         sleep.assert_called_once_with(1.0)
 
     def test_dies_when_selected_cert_missing(self):
         # Plan claims a pipelock cert at a path that doesn't exist —
         # something went wrong in launch's pipelock_tls_init.
         plan = _plan(pipelock_ca_path=self.tmp / "does-not-exist.pem")
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_cp"
+        with self.assertRaises(SystemExit):
-        ), patch(
+            _ca.provision_ca(plan, bottle)
-            "bot_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec"
-        ):
-            with self.assertRaises(SystemExit):
-                _ca.provision_ca(plan, "bot-bottle-demo-abc12")
 
 
 class TestProvisionGit(unittest.TestCase):
@@ -665,16 +330,10 @@ class TestProvisionGit(unittest.TestCase):
         self._tmp.cleanup()
 
     def test_noop_when_no_cwd_and_no_git_entries(self):
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_cp"
+        _git.provision_git(_plan(stage_dir=self.stage), bottle)
-        ) as cp, patch(
+        bottle.cp_in.assert_not_called()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
+        bottle.exec.assert_not_called()
-        ) as ex:
-            _git.provision_git(
-                _plan(stage_dir=self.stage), "bot-bottle-demo-abc12",
-            )
-        cp.assert_not_called()
-        ex.assert_not_called()
 
     def test_copies_cwd_git_when_copy_cwd_and_git_present(self):
         # Stage a fake host .git dir under user_cwd so the path-
@@ -684,33 +343,25 @@ class TestProvisionGit(unittest.TestCase):
         plan = _plan(
             copy_cwd=True, user_cwd=str(cwd), stage_dir=self.stage,
         )
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_cp"
+        _git.provision_git(plan, bottle)
-        ) as cp, patch(
+        bottle.cp_in.assert_called_once_with(
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
-        ) as ex:
-            _git.provision_git(plan, "bot-bottle-demo-abc12")
-        cp.assert_called_once_with(
             f"{cwd}/.git",
-            "bot-bottle-demo-abc12:/home/node/workspace/.git",
+            "/home/node/workspace/.git",
         )
-        argvs = [c.args[1] for c in ex.call_args_list]
+        scripts = _exec_scripts(bottle)
-        self.assertIn(["mkdir", "-p", "/home/node/workspace"], argvs)
+        self.assertTrue(any("mkdir -p" in s and "/home/node/workspace" in s for s in scripts))
         # chown the workspace tree so the agent (node) owns it.
-        self.assertIn(
+        self.assertTrue(
-            ["chown", "-R", "node:node", "/home/node/workspace/.git"],
+            any("chown -R" in s and "node:node" in s and "/home/node/workspace/.git" in s
-            argvs,
+                for s in scripts)
         )
 
     def test_skips_cwd_when_copy_cwd_false(self):
         plan = _plan(copy_cwd=False, stage_dir=self.stage)
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_cp"
+        _git.provision_git(plan, bottle)
-        ) as cp, patch(
+        bottle.cp_in.assert_not_called()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
-        ):
-            _git.provision_git(plan, "bot-bottle-demo-abc12")
-        cp.assert_not_called()
 
     def test_writes_gitconfig_with_ip_port_form_for_smolmachines(self):
         # Smolmachines's TSI-allowlisted guest dials git-gate via
@@ -726,15 +377,11 @@ class TestProvisionGit(unittest.TestCase):
             stage_dir=self.stage,
             agent_git_gate_host="127.0.0.1:9418",
         )
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_cp"
+        _git.provision_git(plan, bottle)
-        ) as cp, patch(
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
-        ):
-            _git.provision_git(plan, "bot-bottle-demo-abc12")
         # The staged gitconfig path is whatever NamedTemporaryFile
         # picked; we read its contents.
-        cp_call = cp.call_args
+        cp_call = bottle.cp_in.call_args
         staged_path = Path(cp_call.args[0])
         self.assertEqual(self.stage, staged_path.parent)
         content = staged_path.read_text()
@@ -776,71 +423,63 @@ class TestBundleLaunchSpec(unittest.TestCase):
 
 class TestProvisionGitUser(unittest.TestCase):
     """`_provision_git_user` runs `git config --global` inside the
-    guest as the node user with HOME forced via `smolvm -e`
+    guest as the node user. SmolmachinesBottle.exec sets HOME and
-    (otherwise --global lands in /root/.gitconfig). No-op when the
+    USER automatically for the requested user, so --global lands
-    bottle didn't declare git_user (issue #86)."""
+    in /home/node/.gitconfig. No-op when the bottle didn't declare
+    git_user (issue #86)."""
 
-    def _git_config_calls(self, mock_exec):
+    def _git_config_calls(self, bottle: MagicMock) -> list[tuple[str, str]]:
-        """Filter machine_exec calls down to git-config invocations,
+        """Filter bottle.exec calls down to git-config invocations,
-        return list of (argv, env-dict) tuples."""
+        return list of (script, user) tuples."""
         out = []
-        for c in mock_exec.call_args_list:
+        for c in bottle.exec.call_args_list:
-            argv = c.args[1] if len(c.args) > 1 else c.kwargs.get("argv", [])
+            script = c.args[0] if c.args else ""
-            if "git" in argv and "config" in argv:
+            user = c.kwargs.get("user", "node")
-                out.append((argv, c.kwargs.get("env") or {}))
+            if "git config" in script:
+                out.append((script, user))
         return out
 
     def test_noop_when_no_git_user(self):
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
+        _git._provision_git_user(_plan(), bottle)
-        ) as ex:
+        self.assertEqual([], self._git_config_calls(bottle))
-            _git._provision_git_user(_plan(), "bot-bottle-demo-abc12")
-        self.assertEqual([], self._git_config_calls(ex))
 
     def test_sets_name_and_email_as_node(self):
         plan = _plan(git_user={
             "name": "Eric Bauerfeld",
             "email": "eric@dideric.is",
         })
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
+        _git._provision_git_user(plan, bottle)
-        ) as ex:
+        calls = self._git_config_calls(bottle)
-            _git._provision_git_user(plan, "bot-bottle-demo-abc12")
-        calls = self._git_config_calls(ex)
         self.assertEqual(2, len(calls))
-        # Both go through `runuser -u node --` so they run as node;
+        # Both run as node so SmolmachinesBottle.exec sets HOME=/home/node
-        # HOME is forced via smolvm -e so --global writes to
+        # automatically, ensuring --global writes to /home/node/.gitconfig.
-        # /home/node/.gitconfig and not /root/.gitconfig.
+        for script, user in calls:
-        for argv, env in calls:
+            self.assertEqual("node", user)
-            self.assertEqual(
+            self.assertIn("git config --global", script)
-                ["runuser", "-u", "node", "--",
+        self.assertIn("user.name", calls[0][0])
-                 "git", "config", "--global"],
+        self.assertIn("Eric Bauerfeld", calls[0][0])
-                argv[:7],
+        self.assertIn("user.email", calls[1][0])
-            )
+        self.assertIn("eric@dideric.is", calls[1][0])
-            self.assertEqual("/home/node", env.get("HOME"))
-            self.assertEqual("node", env.get("USER"))
-        self.assertEqual(["user.name", "Eric Bauerfeld"], calls[0][0][7:])
-        self.assertEqual(["user.email", "eric@dideric.is"], calls[1][0][7:])
 
     def test_name_only(self):
         plan = _plan(git_user={"name": "Bot"})
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
+        _git._provision_git_user(plan, bottle)
-        ) as ex:
+        calls = self._git_config_calls(bottle)
-            _git._provision_git_user(plan, "bot-bottle-demo-abc12")
-        calls = self._git_config_calls(ex)
         self.assertEqual(1, len(calls))
-        self.assertEqual(["user.name", "Bot"], calls[0][0][7:])
+        self.assertIn("user.name", calls[0][0])
+        self.assertIn("Bot", calls[0][0])
 
     def test_email_only(self):
         plan = _plan(git_user={"email": "bot@example.com"})
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.git._smolvm.machine_exec"
+        _git._provision_git_user(plan, bottle)
-        ) as ex:
+        calls = self._git_config_calls(bottle)
-            _git._provision_git_user(plan, "bot-bottle-demo-abc12")
-        calls = self._git_config_calls(ex)
         self.assertEqual(1, len(calls))
-        self.assertEqual(["user.email", "bot@example.com"], calls[0][0][7:])
+        self.assertIn("user.email", calls[0][0])
+        self.assertIn("bot@example.com", calls[0][0])
 
 
 class TestProvisionWorkspace(unittest.TestCase):
@@ -853,95 +492,33 @@ class TestProvisionWorkspace(unittest.TestCase):
 
     def test_noop_when_copy_cwd_false(self):
         plan = _plan(copy_cwd=False, stage_dir=self.stage)
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.workspace._smolvm.machine_cp"
+        _workspace.provision_workspace(plan, bottle)
-        ) as cp, patch(
+        bottle.cp_in.assert_not_called()
-            "bot_bottle.backend.smolmachines.provision.workspace._smolvm.machine_exec"
+        bottle.exec.assert_not_called()
-        ) as ex:
-            _workspace.provision_workspace(plan, "bot-bottle-demo-abc12")
-        cp.assert_not_called()
-        ex.assert_not_called()
 
     def test_copies_workspace_to_plan_path_and_chowns(self):
         cwd = self.stage / "cwd"
         cwd.mkdir()
         plan = _plan(copy_cwd=True, user_cwd=str(cwd), stage_dir=self.stage)
-        with patch(
+        bottle = _make_bottle()
-            "bot_bottle.backend.smolmachines.provision.workspace._smolvm.machine_cp"
+        _workspace.provision_workspace(plan, bottle)
-        ) as cp, patch(
-            "bot_bottle.backend.smolmachines.provision.workspace._smolvm.machine_exec"
-        ) as ex:
-            _workspace.provision_workspace(plan, "bot-bottle-demo-abc12")
 
-        cp.assert_called_once_with(
+        bottle.cp_in.assert_called_once_with(
             str(cwd),
-            "bot-bottle-demo-abc12:/home/node/workspace",
+            "/home/node/workspace",
         )
-        argvs = [c.args[1] for c in ex.call_args_list]
+        scripts = _exec_scripts(bottle)
-        self.assertIn(
+        self.assertTrue(
-            ["sh", "-c", "rm -rf /home/node/workspace && mkdir -p /home/node"],
+            any("rm -rf /home/node/workspace" in s and "mkdir -p /home/node" in s
-            argvs,
+                for s in scripts)
         )
-        self.assertIn(
+        self.assertTrue(
-            [
+            any("chown -R node:node /home/node/workspace" in s
-                "sh", "-c",
+                and "chmod 755 /home/node/workspace" in s
-                "chown -R node:node /home/node/workspace && "
+                for s in scripts)
-                "chmod 755 /home/node/workspace",
-            ],
-            argvs,
         )
 
 
-class TestProvisionSupervise(unittest.TestCase):
-    def test_noop_when_supervise_not_enabled(self):
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.supervise._smolvm.machine_exec"
-        ) as ex:
-            _supervise.provision_supervise(_plan(), "bot-bottle-demo-abc12")
-        ex.assert_not_called()
-
-    def test_calls_claude_mcp_add_when_supervise_enabled(self):
-        plan = _plan(
-            supervise=True,
-            agent_supervise_url="http://127.0.0.1:9100/",
-        )
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.supervise._smolvm.machine_exec",
-            return_value=SmolvmRunResult(returncode=0, stdout="", stderr=""),
-        ) as ex:
-            _supervise.provision_supervise(plan, "bot-bottle-demo-abc12")
-        ex.assert_called_once()
-        argv = ex.call_args.args[1]
-        # `claude mcp add --scope user` writes to ~/.claude.json,
-        # and the agent is the `node` user — switch UID + set
-        # HOME so the config lands in /home/node/.claude.json,
-        # not root's. URL is the agent-side endpoint (host
-        # loopback + discovered port), not the docker bridge IP.
-        self.assertEqual(
-            [
-                "runuser", "-u", "node", "--",
-                "env", "HOME=/home/node",
-                "claude", "mcp", "add",
-                "--scope", "user",
-                "--transport", "http",
-                "supervise",
-                "http://127.0.0.1:9100/",
-            ],
-            argv,
-        )
-
-    def test_non_zero_exit_logs_warning_but_does_not_raise(self):
-        plan = _plan(supervise=True)
-        with patch(
-            "bot_bottle.backend.smolmachines.provision.supervise._smolvm.machine_exec",
-            return_value=SmolvmRunResult(
-                returncode=1, stdout="", stderr="boom",
-            ),
-        ):
-            # No raise — the bottle still works without the MCP
-            # entry, so we log and move on.
-            _supervise.provision_supervise(plan, "bot-bottle-demo-abc12")
-
-
 if __name__ == "__main__":
     unittest.main()