Merge remote-tracking branch 'origin/main' into fix/quality-cleanup-consolidated

bot_bottle/orchestrator/api.py

@@ -7,6 +7,7 @@ import asyncio
 import math
 import sys
 from fastapi import FastAPI, HTTPException
+from fastapi.exceptions import RequestValidationError
 from fastapi.responses import JSONResponse
 from pydantic import BaseModel, ConfigDict, StrictStr
 from starlette.types import ASGIApp, Message, Receive, Scope, Send
@@ -208,6 +209,19 @@ def create_app(orch: OrchestratorCore, *, signing_key: str) -> FastAPI:
     )
     app.add_middleware(ControlPlaneBoundary, signing_key=key)
 
+    @app.exception_handler(RequestValidationError)
+    async def invalid_request(
+        _request: object, exc: RequestValidationError,
+    ) -> JSONResponse:
+        errors = exc.errors()
+        location = errors[0].get("loc", ()) if errors else ()
+        field = str(location[1]) if len(location) > 1 else ""
+        suffix = f": {field}" if field else ""
+        return JSONResponse(
+            {"error": f"invalid request body{suffix}"},
+            status_code=400,
+        )
+
     @app.get("/health")
     def health() -> dict[str, str]:
         return {"status": "ok"}

bot_bottle/store/db_store.py

@@ -29,8 +29,13 @@ class DbStore:
         """Create and verify the private parent directory."""
         parent = self.db_path.parent
         parent.mkdir(mode=0o700, parents=True, exist_ok=True)
+        if parent.is_symlink():
+            raise PermissionError(f"database directory must not be a symlink: {parent}")
         parent.chmod(0o700)
-        if stat.S_IMODE(parent.stat().st_mode) != 0o700:
+        parent_stat = parent.lstat()
+        if not stat.S_ISDIR(parent_stat.st_mode):
+            raise PermissionError(f"database parent is not a directory: {parent}")
+        if stat.S_IMODE(parent_stat.st_mode) != 0o700:
             raise PermissionError(f"database directory is not mode 0700: {parent}")
 
     def _secure_db_file(self) -> None:
@@ -40,22 +45,34 @@ class DbStore:
         This store contains control-plane identity tokens, so both creation and
         repair are fail-closed rather than best-effort.
         """
+        flags = os.O_RDWR | os.O_CREAT | os.O_NOFOLLOW
+        fd = os.open(
+            self.db_path,
+            flags,
+            stat.S_IRUSR | stat.S_IWUSR,
+        )
         try:
-            fd = os.open(
-                self.db_path,
-                os.O_WRONLY | os.O_CREAT | os.O_EXCL,
-                stat.S_IRUSR | stat.S_IWUSR,
-            )
-        except FileExistsError:
-            pass
-        else:
+            self._secure_open_file(fd)
+        finally:
             os.close(fd)
-        self._chmod()
 
     def _chmod(self) -> None:
         """Enforce and verify the private database mode after every write."""
-        self.db_path.chmod(0o600)
-        if stat.S_IMODE(self.db_path.stat().st_mode) != 0o600:
+        fd = os.open(self.db_path, os.O_RDWR | os.O_NOFOLLOW)
+        try:
+            self._secure_open_file(fd)
+        finally:
+            os.close(fd)
+
+    def _secure_open_file(self, fd: int) -> None:
+        """Pin, validate, and secure an opened database filesystem object."""
+        file_stat = os.fstat(fd)
+        if not stat.S_ISREG(file_stat.st_mode):
+            raise PermissionError(
+                f"database must be a regular file: {self.db_path}"
+            )
+        os.fchmod(fd, stat.S_IRUSR | stat.S_IWUSR)
+        if stat.S_IMODE(os.fstat(fd).st_mode) != 0o600:
             raise PermissionError(f"database is not mode 0600: {self.db_path}")
 
     def _connect(self) -> sqlite3.Connection:

docs/research/agent-sandbox-landscape.md

@@ -32,9 +32,17 @@ not a principled scope exclusion: both are major hosted sandbox platforms and
 belong in this landscape even though they target platform builders rather than
 bot-bottle's local single-operator workflow.
 
+Updated 2026-07-27 after a scan of recent Show HN launches: **Black LLAB,
+Eve, CloudRouter, Nucleus, yolo-cage, and Sandbox Agent SDK** added as a
+dated entrant cohort. They sharpen the comparison on three axes the original
+table underweighted: the browser/preview loop, parallel-agent operator UX, and
+a provider-neutral automation/session API.
+
 ## Summary
 
-The main table compares bot-bottle against fifteen isolation/sandbox tools.
+The main table compares bot-bottle against fifteen canonical
+isolation/sandbox tools; a later section evaluates six recent HN entrants
+without widening an already unwieldy table.
 Governance/pre-action authorization and credential-only layers are covered
 separately because they don't provide VM or container isolation. None
 duplicate bot-bottle's combination of local
@@ -542,6 +550,199 @@ them.
   framework runtime is not compromised.
 - **Maturity**: Specification + reference implementation, 2026.
 
+## Recent HN entrants (added 2026-07-27)
+
+These are grouped by launch date rather than promoted into the main table.
+Several are young or sparsely documented, and putting them beside mature
+runtime platforms with false precision would obscure the useful comparison.
+The HN launch posts are the evidence snapshot; feature claims should be
+rechecked against their repositories before relying on them for a security
+decision.
+
+### Black LLAB
+
+- **Source**: https://github.com/isaacdear/black-llab ;
+  HN launch https://news.ycombinator.com/item?id=47402394
+- **Isolation/locality**: Local Docker environment, with an isolated container
+  created for each agent task. Shared host kernel; no stronger boundary is
+  claimed.
+- **Agent integration**: General local/cloud model workspace. Its headline is
+  dynamic routing of simple prompts to local models and complex prompts to
+  hosted models, with code execution and web scraping inside the task
+  container.
+- **Network/credentials**: No default-deny egress, payload inspection, or
+  host-side credential injection documented in the launch.
+- **Competitive read**: Superficial overlap ("a container per agent task"),
+  but not a direct security-policy competitor. Its useful challenge is the
+  integrated model-selection UX, which bot-bottle intentionally leaves to the
+  selected agent provider.
+- **Maturity**: Early solo project; HN launch received 1 point.
+
+### Eve
+
+- **Source**: https://eve.new/ ;
+  HN launch https://news.ycombinator.com/item?id=47721255
+- **Isolation/locality**: Managed, hosted Linux sandbox per user/session
+  (claimed 2 vCPU, 4 GB RAM, 10 GB disk), with filesystem, code execution,
+  headless Chromium, and service connectors.
+- **Agent integration**: End-user OpenClaw-style agent product. An orchestrator
+  routes subtasks to specialist models and can run parallel subagents that
+  coordinate through a shared filesystem. Web UI and iMessage are primary
+  interaction surfaces.
+- **Network/credentials**: Broad connectors are a product feature; the launch
+  does not document bot-bottle-style default-deny route policy, content DLP,
+  or credentials held outside the sandbox.
+- **Competitive read**: Adjacent, not direct. Eve sells a managed colleague;
+  bot-bottle lets an operator run existing coding-agent CLIs under local
+  containment. Eve nevertheless demonstrates the appeal of background work,
+  live progress, browser capability, and mobile notification.
+- **Maturity**: Commercial hosted product; HN launch received 71 points and
+  39 comments.
+
+### CloudRouter
+
+- **Source**: https://github.com/manaflow-ai/manaflow/tree/main/packages/cloudrouter ;
+  HN launch https://news.ycombinator.com/item?id=47006393
+- **Isolation/locality**: Claude Code or Codex runs locally and provisions
+  remote cloud VMs/GPUs for execution. Project files are uploaded to the VM;
+  each machine exposes auth-protected VNC, VS Code, and Jupyter surfaces.
+- **Agent integration**: A skill plus CLI lets the coding agent itself start,
+  command, inspect, and tear down machines. Browser automation is integrated,
+  including snapshots and screenshots. Parallel disposable compute is the
+  central workflow.
+- **Network/credentials**: The launch emphasizes remote resource isolation and
+  authenticated UI endpoints, not default-deny guest egress, payload DLP, or
+  proxy-held application credentials.
+- **Competitive read**: The closest recent workflow competitor. It directly
+  addresses parallel coding agents, environmental conflict, and closing the
+  browser/test loop, but trades local custody for elastic cloud compute.
+  Cloud VMs and GPUs could be a future bot-bottle backend; they do not replace
+  its manifest/policy layer.
+- **Maturity**: Active open-source monorepo project; HN launch received
+  138 points and 36 comments.
+
+### Nucleus
+
+- **Source**: https://github.com/coproduct-opensource/nucleus ;
+  HN launch https://news.ycombinator.com/item?id=46855770
+- **Isolation/locality**: Firecracker microVM with an enforcing MCP tool proxy.
+- **Agent integration/config**: Compositional permission envelope for
+  read/write/run actions. The envelope is non-escalating and can tighten or
+  terminate, with scoped approval tokens for gated operations.
+- **Network/credentials**: Default-deny egress, DNS allowlist, iptables drift
+  detection, time/budget caps, and hash-chained audit logging are claimed.
+  Remote append-only audit storage and attestation were roadmap items at
+  launch.
+- **Competitive read**: Direct on security architecture, especially
+  non-escalating policy and tamper-evident audit. It is an early execution/tool
+  proxy rather than a provider-neutral, one-command coding-agent product. Its
+  tool-level action envelope is semantically finer than bot-bottle's network
+  boundary; bot-bottle is stronger on turnkey agent/provider integration,
+  credential custody, Git mediation, and long-running operator workflow.
+- **Maturity**: Early OSS experiment; HN launch received 3 points.
+
+### yolo-cage
+
+- **Source**: https://github.com/borenstein/yolo-cage ;
+  HN launch https://news.ycombinator.com/item?id=46706796
+- **Isolation/locality**: Local sandbox for running multiple coding agents in
+  YOLO mode. The launch discussion describes a VM boundary.
+- **Agent integration**: Built around the native Claude Code experience and
+  motivated by running many agents in parallel without permission-prompt
+  fatigue.
+- **Network/Git/credentials**: Strict egress filtering, configurable HTTP
+  middleware, and mediated `git`/`gh` dispatch are the main value. The launch
+  discussion explicitly identifies provider credential handling as unfinished
+  and difficult because Claude state spans multiple host paths.
+- **Competitive read**: The closest new threat-model competitor. It shares
+  bot-bottle's premise that filesystem isolation alone is insufficient and
+  that Git plus authorized HTTP channels need mediation. bot-bottle currently
+  leads on cross-provider support, proxy-held Claude/Codex/forge credentials,
+  typed per-role manifests, content DLP, and supervision. yolo-cage's simpler
+  pitch and narrower Claude-first setup may be easier to explain.
+- **Maturity**: Early local tool; HN launch received 60 points and 76 comments.
+
+### Sandbox Agent SDK
+
+- **Source**: https://github.com/rivet-dev/sandbox-agent ;
+  HN launch https://news.ycombinator.com/item?id=46795584
+- **Isolation/locality**: Does not provide the isolation primitive. It runs
+  inside E2B, Daytona, Modal, Cloudflare Containers, Agent Computer, BoxLite,
+  Docker, or another sandbox provider. Embedded mode can also run locally
+  without a sandbox.
+- **Agent integration**: Provider-neutral Rust server/SDK exposing a common
+  HTTP/SSE/OpenAPI interface across Claude Code, Codex, OpenCode, Cursor, Amp,
+  and Pi, plus a universal event/session schema for external storage and
+  replay. It also exposes filesystem, managed-process, terminal, MCP, skills,
+  custom-tool, and computer-use APIs. TypeScript is the primary SDK surface.
+- **Network/credentials**: Delegated to the chosen sandbox provider.
+- **Credential posture**: Its documented convenience command extracts real
+  OpenAI/Anthropic credentials from local agent configuration and passes them
+  as environment variables into the sandbox. That is materially weaker than
+  bot-bottle's host-side credential custody, but it is an integration choice,
+  not a structural limitation: a sandbox provider could put a credential
+  proxy underneath the same SDK.
+- **Competitive read**: A serious architectural threat despite not supplying
+  isolation. Sandbox Agent is trying to standardize the boundary *above* the
+  sandbox: one client protocol, session model, and UI/control surface across
+  every coding agent and runtime. If that boundary becomes the ecosystem
+  standard, users and application builders may choose a sandbox provider plus
+  Sandbox Agent rather than a vertically integrated launcher. bot-bottle's
+  manifests would then be valuable chiefly as a local policy/backend
+  implementation unless they expose an equally usable control contract.
+- **Maturity**: Apache 2.0, ~1.5k stars and 426 commits at the 2026-07-27
+  check; HN launch received 41 points.
+
+#### Why the Sandbox Agent architecture is strategically different
+
+The manifest and the universal control protocol solve different layers:
+
+- A bot-bottle manifest is a **trusted launch-time policy composition**. It
+  selects the agent role, isolation backend, image, skills, egress routes,
+  credentials, Git mediation, and supervision policy. Crucially, identity and
+  secret references live on the host side of the trust boundary.
+- Sandbox Agent is a **runtime control and observation protocol**. A remote
+  client creates sessions, sends messages, handles permissions, configures
+  skills/MCP, manipulates files/processes/desktops, and streams normalized
+  events. It deliberately delegates sandbox lifecycle, Git management,
+  storage, network policy, and credential security to other products.
+
+That makes it complementary in a component diagram but competitive in product
+architecture. The layer that becomes the stable integration point tends to own
+the ecosystem. Three plausible threat paths matter:
+
+1. **Standard control plane, interchangeable runtimes.** Applications integrate
+   once with Sandbox Agent and treat E2B, Daytona, BoxLite, Docker, or a future
+   local microVM as replaceable compute. A provider that bundles adequate
+   egress and credential custody makes bot-bottle's end-to-end launcher less
+   necessary.
+2. **Policy grows upward.** Sandbox Agent already configures permissions,
+   skills, MCP, custom tools, filesystem/process access, and computer use. If
+   it adds a declarative, host-verifiable policy document, the overlap with
+   agent/bottle manifests becomes substantial even if enforcement remains
+   delegated.
+3. **UI and session ownership.** Its universal transcript schema, Inspector,
+   React components, event replay, and remote terminal/computer APIs can become
+   the natural basis for desktop, web, and mobile agent managers. bot-bottle's
+   security layer could remain stronger while losing the operator surface and
+   distribution channel.
+
+The counter-position is not to claim that manifests and an API are mutually
+exclusive. The defensible split is:
+
+- bot-bottle owns the trusted policy and enforcement plane outside the agent;
+- a provider-neutral protocol owns agent process control and normalized
+  events; and
+- the operator UI consumes both.
+
+This suggests an explicit compatibility decision rather than parallel,
+accidental protocol design: evaluate running Sandbox Agent inside a bottle and
+exposing it only through the authenticated bot-bottle control plane. If its
+schema is suitable, adopting it could turn a threat into an integration while
+keeping manifests as the higher-trust policy source. If it is unsuitable,
+bot-bottle should still publish a stable provider-neutral session/event API so
+frontends do not depend on Claude/Codex/Pi-specific process behavior.
+
 ## Comparison table
 
 *Isolation/sandbox tools only. AGT and OAP are governance layers — see their per-project notes above.*
@@ -616,6 +817,70 @@ would be a *backend* bot-bottle could call, not a competitor to its
 manifest layer. endo-familiar is in a different paradigm entirely:
 capability passing rather than kernel boundaries.
 
+**Recent entrants change two parts of this read.** yolo-cage is closer to the
+actual threat model than agent-safehouse or litterbox: it combines a VM-style
+boundary with mediated Git and filtered HTTP specifically for parallel coding
+agents. Sandbox Agent SDK is the more important strategic entrant even though
+it supplies no isolation. It can become the standard agent-control layer above
+all of these runtimes, including a future bot-bottle backend. CloudRouter is
+the clearest workflow challenge because its browser/desktop/GPU loop makes
+parallel agents visibly more capable, not merely safer.
+
+## Gap evaluation after the 2026-07-27 entrant scan
+
+### Material gaps
+
+1. **A stable provider-neutral control and event protocol.** This is the
+   largest newly visible gap. bot-bottle normalizes launch/provisioning across
+   providers, but an external UI or orchestrator still lacks one documented
+   contract for creating a Claude/Codex/Pi session, sending input, handling
+   permission/supervision events, streaming normalized output, reconnecting,
+   and replaying history. Sandbox Agent SDK addresses exactly this layer and
+   is already portable across many sandbox providers.
+2. **Browser/preview closure.** CloudRouter and Eve make a browser or desktop
+   part of the standard agent environment and expose screenshots/live viewing
+   to the operator. bot-bottle can run dev servers and supports nested
+   containers, but it does not present a first-class browser/computer-use
+   primitive or an auth-protected preview surface. For coding agents expected
+   to verify UI work, this is a real product gap.
+3. **Unified parallel-session operator UX.** Named persistent bottles and
+   supervision provide the substrate, but the recent products make task
+   switching, live progress, notifications, terminal attach, diffs, and
+   session history the product. Security depth will not compensate for a
+   visibly rougher daily loop.
+4. **Normalized transcript persistence and replay.** bot-bottle preserves
+   provider-specific state for resume; it does not expose a provider-neutral
+   event record suitable for audit, replay, analytics, or a web/mobile client.
+   This is both a UX gap and an audit gap.
+
+### Important, but not necessarily bot-bottle features
+
+- **Cloud VM/GPU provisioning.** Valuable for elastic workloads and could be a
+  backend, but it conflicts with the local-custody default and should not
+  displace core policy work.
+- **Automatic model routing.** Black LLAB and Eve sell task-to-model routing.
+  bot-bottle's provider-template boundary can host that choice without making
+  it part of the trusted sandbox policy.
+- **A thousand SaaS connectors.** This broadens capability and blast radius.
+  The bot-bottle-native answer should remain explicit, scoped forge/egress
+  associations rather than connector count as a goal.
+- **SDK-driven sandbox lifecycle as the primary configuration model.** Useful
+  for platform builders, but not a replacement for reviewable, host-owned
+  manifests. A control API and a declarative policy source are compatible;
+  neither should silently become the other.
+
+### Areas where bot-bottle remains ahead
+
+- real provider and forge credentials remain outside the agent process rather
+  than being extracted into its environment;
+- authorized HTTP payloads are scanned, not merely destination-filtered;
+- Git writes traverse a distinct gate with secret scanning and host-held
+  upstream credentials;
+- role policy is host-owned, composable, and separate from untrusted repo
+  content; and
+- local Firecracker/Apple Container execution preserves operator custody
+  without requiring a hosted sandbox platform.
+
 ## Borrowable ideas
 
 ### Already shipped or otherwise addressed
@@ -642,6 +907,19 @@ capability passing rather than kernel boundaries.
 
 ### Still worth considering
 
+- **Sandbox Agent compatibility or an equivalent stable protocol (highest
+  priority):** spike running its server inside a bottle behind bot-bottle's
+  authenticated control plane. Compare its session/event schema, permission
+  model, restore semantics, and provider coverage with current provider
+  adapters. Adopt compatibility if it preserves the host-owned trust boundary;
+  otherwise specify bot-bottle's own stable API before building another UI.
+- **First-class browser/preview loop** (from CloudRouter and Eve): give a
+  bottle an optional browser/computer-use capability plus an operator-visible,
+  authenticated preview/screenshot surface. Treat its network access as part
+  of the bottle policy, not an implicit bypass.
+- **Provider-neutral transcript/event persistence** (from Sandbox Agent SDK):
+  retain enough normalized structure for replay and audit while preserving the
+  provider-native state needed for exact resume.
 - **Live network activity in the supervisor TUI** (from Docker sbx): show
   allowed and blocked connections and let the operator propose policy changes
   from the existing supervision surface.
@@ -652,10 +930,11 @@ capability passing rather than kernel boundaries.
   closer review. This needs a carefully specified trust model before it can be
   more than a heuristic.
 
-Not worth borrowing: the SDK-first programmatic API style of boxlite /
-microsandbox (cuts against the declarative-manifest stance), and the
-hosted-SaaS dashboard model of tilde.run (cuts against the
-"infrastructure I control" goal).
+Not worth borrowing: SDK-first *policy configuration* as used by boxlite /
+microsandbox (cuts against the reviewable declarative-manifest stance), and
+the hosted-SaaS custody model of tilde.run (cuts against the "infrastructure I
+control" goal). A provider-neutral runtime-control API is a separate concern
+and is worth borrowing.
 
 ## Publishing and positioning verdict
 
@@ -679,9 +958,15 @@ bot-bottle remains unusual in combining:
 The practical wedge is “as easy as native yolo, with declarative role policy
 and self-hosted custody,” including scoped access to private LAN/Tailnet
 services that cloud-first runtimes cannot provide without additional network
-plumbing. The main competitive risks are a local wrapper such as claudebox or
-Docker sbx growing a role-manifest layer, and GUI products such as SuperHQ
-adding equivalent policy and audit depth.
+plumbing. The main competitive risks are now:
+
+- a local wrapper such as yolo-cage, claudebox, or Docker sbx growing a
+  role-manifest and credential-custody layer;
+- Sandbox Agent SDK becoming the standard control/session boundary and making
+  the runtime beneath it interchangeable; and
+- GUI products such as SuperHQ or CloudRouter adding equivalent policy and
+  audit depth before bot-bottle closes the browser/preview and
+  parallel-session UX gaps.
 
 ## Caveats
 

docs/research/sandbox-agent-sdk-architecture.md

@@ -0,0 +1,536 @@
+# Sandbox Agent SDK and bot-bottle: protocol versus product
+
+This note asks whether [Sandbox Agent SDK](https://github.com/rivet-dev/sandbox-agent)
+and bot-bottle compete for the same architectural layer, whether bot-bottle
+can productize the turnkey ecosystem/DX layer above it, and how far the
+Docker/OCI analogy actually holds.
+
+Research conducted 2026-07-27. Sandbox Agent SDK was at the `0.4.x` line,
+Apache 2.0, and documented support for Claude Code, Codex, OpenCode, Cursor,
+Amp, and Pi at the time of review.
+
+## Summary
+
+**The projects are complementary at the component boundary and competitive at
+the product boundary.** Sandbox Agent SDK normalizes how software controls a
+coding-agent process inside an arbitrary sandbox. bot-bottle decides what
+sandbox to create, what trusted role and policy it receives, how credentials
+and Git access cross the boundary, how traffic is constrained, and how an
+operator launches and supervises the result.
+
+The Docker analogy is useful with one correction:
+
+- Sandbox Agent SDK is not equivalent to Linux container APIs or OCI itself.
+  It is closer to a **containerd shim plus a portable exec/session API for
+  coding agents**. It adapts incompatible agent processes to one HTTP/SSE
+  contract.
+- A future independent agent-session specification would be the closer OCI
+  analogue.
+- bot-bottle can credibly occupy the **Docker Engine / Compose / Desktop**
+  layer: packaging, policy composition, lifecycle, networking, credentials,
+  storage, operator UX, and a one-command experience above interchangeable
+  agent adapters and isolation runtimes.
+
+That is a viable position, but “turnkey wrapper” undersells it. A thin wrapper
+is replaceable. The valuable product is a **turnkey, policy-first coding-agent
+runtime** whose manifest compiles trusted operator intent into multiple
+enforcement planes. Sandbox Agent SDK may be one internal process-control
+component of that product.
+
+The recommended direction is:
+
+1. Keep the bot-bottle manifest as the host-owned source of trusted policy.
+2. Spike Sandbox Agent SDK as the in-bottle provider/session adapter.
+3. Expose a stable, provider-neutral bot-bottle control API, compatible with
+   Sandbox Agent where practical.
+4. Keep security decisions and authoritative audit outside the sandbox.
+5. Build the ecosystem around policy packs, agent images, skills, backends,
+   operator UI, and trusted integrations—not around a proprietary transcript
+   protocol.
+
+## What each project is today
+
+### Sandbox Agent SDK
+
+Sandbox Agent is a Rust server that runs alongside the coding agent. A client
+connects over HTTP, streams events over SSE, and uses one API across agent
+implementations. Its documented surface includes:
+
+- creating and restoring agent sessions;
+- sending messages and streaming normalized events;
+- handling permissions;
+- configuring MCP servers, skills, and custom tools;
+- filesystem and managed-process APIs;
+- interactive terminal access;
+- computer-use/desktop operations;
+- a universal session/transcript schema;
+- an Inspector UI, React components, CLI, TypeScript SDK, and OpenAPI spec.
+
+It can run in embedded mode or inside E2B, Daytona, Modal, Cloudflare
+Containers, Agent Computer, BoxLite, Docker, and other environments. It
+explicitly leaves these concerns to the caller or sandbox provider:
+
+- sandbox creation and lifecycle;
+- Git repository management;
+- durable session storage;
+- network policy;
+- isolation strength; and
+- secure credential delivery.
+
+Its documented credential convenience path extracts real provider credentials
+from local agent configuration and passes them into the sandbox environment.
+That is convenient but is not an acceptable security boundary for bot-bottle.
+
+Sources:
+
+- [Sandbox Agent repository and architecture](https://github.com/rivet-dev/sandbox-agent)
+- [Sandbox Agent documentation](https://sandboxagent.dev/docs)
+- [HTTP API](https://sandboxagent.dev/docs/api-reference)
+- [Universal session/transcript schema](https://sandboxagent.dev/docs/session-transcript-schema)
+
+### bot-bottle
+
+bot-bottle is a host-side launch, policy, and enforcement system for existing
+coding-agent CLIs. Its current architecture includes:
+
+- agent and bottle manifests with composition via `extends:`;
+- a host-only trust boundary for roles, identity, and secret references;
+- provider templates and plugins for Claude Code, Codex, Pi, and custom
+  providers;
+- Firecracker on KVM Linux and Apple Container on macOS, with Docker fallback;
+- image construction and provider-specific provisioning;
+- default-deny inspected egress with path/method/header policy;
+- payload DLP on authorized channels;
+- real credentials held outside the agent and injected by the gateway;
+- Git mediation, upstream credential custody, and gitleaks scanning;
+- a per-host authenticated orchestrator and shared gateway;
+- named bottle lifecycle, resume, supervision, and audit state; and
+- a CLI/TUI intended to make full-permission agents operationally tolerable.
+
+The provider layer currently normalizes launch-time concerns—command, image,
+prompt delivery, files, skills, environment, verification, and provider-owned
+egress routes. It does **not** yet expose a stable provider-neutral runtime
+contract for sessions, messages, transcripts, terminals, or normalized events.
+That is the gap Sandbox Agent directly illuminates.
+
+Sources in this repository:
+
+- [`README.md`](../../README.md)
+- [`0070-per-host-orchestrator.md`](../prds/0070-per-host-orchestrator.md)
+- [`0026-agent-provider-templates.md`](../prds/0026-agent-provider-templates.md)
+- [`0053-user-provider-plugins.md`](../prds/0053-user-provider-plugins.md)
+- [`agent_provider.py`](../../bot_bottle/agent_provider.py)
+
+## The layer model
+
+The cleanest architecture has four layers:
+
+| Layer | Responsibility | Likely owner |
+|---|---|---|
+| Operator product | Install, select a role, launch, observe, intervene, resume, review changes | bot-bottle |
+| Trusted policy and lifecycle | Compose manifest, choose backend/image, hold credentials, enforce egress/Git, persist authoritative audit | bot-bottle |
+| Agent control protocol | Start provider process, create session, send input, stream normalized events, terminal/computer operations | Sandbox Agent or a compatible protocol |
+| Isolation primitive | VM/container/process boundary, filesystem, CPU/memory, networking substrate | Firecracker, Apple Container, Docker, E2B, Daytona, BoxLite, etc. |
+
+The important boundary is between trusted policy/lifecycle and agent control.
+The agent-control daemon runs in the environment being treated as untrusted.
+It can report what the agent says happened, but it cannot authoritatively prove
+that policy was enforced. Egress decisions, credential custody, Git scanning,
+bottle identity, and security audit must remain outside it.
+
+### Proposed composition
+
+```text
+operator UI / CLI / API
+          |
+          v
+bot-bottle orchestrator  (trusted)
+  - resolves manifest
+  - owns bottle identity and lifecycle
+  - stores authoritative audit
+  - authenticates clients
+          |
+          +--------------------------+
+          |                          |
+          v                          v
+isolation backend              shared gateway  (trusted)
+Firecracker / Apple / Docker   - egress policy + DLP
+          |                    - credential injection
+          |                    - Git mediation
+          v
+bottle / guest  (untrusted)
+  - Sandbox Agent server
+  - Claude Code / Codex / Pi subprocess
+  - workspace, skills, MCP configuration
+```
+
+The bot-bottle manifest would compile into both sides:
+
+- **outside the bottle:** backend, network, egress, credentials, Git,
+  supervision, identity, and authoritative lifecycle;
+- **inside the bottle:** selected provider, prompt, skills, MCP configuration,
+  startup arguments, and non-secret session metadata.
+
+Sandbox Agent should never receive real secrets merely because its API offers
+a credential extraction helper. Provider and forge requests should continue
+to use bot-bottle's placeholder/proxy pattern.
+
+## How accurate is the Docker/OCI analogy?
+
+### The useful part
+
+The container ecosystem separates low-level execution from a product that
+ordinary developers operate. OCI defines interoperable image, runtime, and
+distribution specifications. Docker Engine adds a daemon, API, CLI, object
+model, images, networks, volumes, and lifecycle; Docker Desktop and related
+products add installation, updates, UI, integrations, policy, and team
+workflows.
+
+The same separation can exist for coding agents:
+
+| Container ecosystem | Agent-sandbox ecosystem |
+|---|---|
+| OCI/runtime contract | A future open agent session/event contract |
+| `runc` / runtime adapter | Claude/Codex/Pi adapter |
+| containerd shim and task/exec API | Sandbox Agent server and HTTP/SSE session API |
+| containerd / CRI-style lifecycle | Sandbox-provider lifecycle APIs |
+| Docker Engine / Compose | bot-bottle orchestrator + manifests + backends + gateway |
+| Docker Desktop / Hub ecosystem | bot-bottle desktop/mobile UX, policy packs, agent images, skills, trusted integrations |
+
+Sandbox Agent makes coding-agent processes portable in roughly the way a shim
+makes runtimes consumable through a common lifecycle interface. bot-bottle can
+make the entire safe-agent system usable without asking the operator to
+assemble that plumbing.
+
+Official container references:
+
+- [Open Container Initiative](https://opencontainers.org/)
+- [OCI Runtime Specification](https://github.com/opencontainers/runtime-spec)
+- [Docker Engine architecture](https://docs.docker.com/engine/)
+- [Docker alternative runtimes and containerd shims](https://docs.docker.com/engine/daemon/alternative-runtimes/)
+
+### Where the analogy breaks
+
+1. **Sandbox Agent is an implementation, not an independent standard.**
+   Its OpenAPI document is public, but the project currently owns the server,
+   adapters, schema, and evolution. OCI is an independently governed set of
+   specifications with multiple implementations.
+2. **It sits above, not below, the isolation boundary.** Linux namespaces,
+   cgroups, VMs, and OCI runtimes create the boundary. Sandbox Agent controls a
+   process after some other system has created that boundary.
+3. **It reaches into product territory.** Inspector, React components,
+   computer-use APIs, skills/MCP configuration, transcripts, and restoration
+   are not merely low-level primitives. Sandbox Agent can continue growing
+   upward into the same UI and orchestration space bot-bottle might occupy.
+4. **Coding agents are semantically uneven.** Normalizing a container
+   lifecycle is easier than claiming full behavioral parity across Claude
+   Code, Codex, Cursor, Amp, OpenCode, and Pi. A universal schema can become a
+   lowest common denominator or accumulate provider-specific escape hatches.
+5. **The security contract is not standardized.** An agent-session API says
+   little about whether credentials are visible, egress is controlled, Git is
+   mediated, or audit is trustworthy. Those are core bot-bottle concerns.
+
+The positioning should therefore say “Docker-like product layer above an open
+agent-control protocol,” not “Sandbox Agent is OCI” or “bot-bottle implements
+OCI for agents.”
+
+## Can bot-bottle be the turnkey product layer?
+
+Yes, if it owns substantially more than launch syntax.
+
+The turnkey promise is:
+
+> Choose a trusted role, point it at a project, and run any supported coding
+> agent with full permissions. bot-bottle builds the environment, isolates it,
+> supplies only the capabilities it needs, keeps credentials outside, mediates
+> external writes, and gives the operator one place to watch and intervene.
+
+That product has several defensible jobs:
+
+### 1. Packaging and reproducibility
+
+- provider and toolchain images;
+- pinned, verified build inputs;
+- skills and MCP configuration;
+- role/bottle composition;
+- cached startup and portable environment definitions; and
+- compatibility testing across agents and backends.
+
+### 2. Trusted policy compilation
+
+The manifest is valuable because one reviewable document compiles into:
+
+- an isolation plan;
+- gateway routes and DLP policy;
+- credential slots;
+- Git-gate repositories and identities;
+- provider configuration;
+- supervision behavior; and
+- operator-facing preflight.
+
+Sandbox Agent's runtime configuration does not replace this. The policy must
+be resolved before an untrusted guest or agent-control daemon exists.
+
+### 3. Security enforcement
+
+- dedicated-kernel isolation where available;
+- no direct guest route to the internet;
+- credentials injected outside the agent;
+- content inspection on allowed destinations;
+- Git secrets scanning and upstream-key custody;
+- fail-closed policy resolution; and
+- authoritative host-side audit.
+
+This is the strongest current differentiation from a generic
+“Sandbox Agent + Docker/E2B” assembly.
+
+### 4. Lifecycle and operations
+
+- install and host preflight;
+- image build/update;
+- start, stop, resume, cleanup, and migration;
+- concurrent named agents;
+- state recovery after crashes;
+- live supervision and policy remediation; and
+- backend selection without changing the role definition.
+
+### 5. Ecosystem and DX
+
+A product layer can support:
+
+- curated provider images;
+- signed policy/bottle packs;
+- reusable role templates;
+- skills and MCP bundles;
+- backend plugins;
+- an authenticated desktop/web/mobile operator client;
+- browser/preview integration;
+- normalized transcripts and change review; and
+- team policy distribution and compliance exports.
+
+The analogy to Docker is strongest here: users adopt the coherent workflow and
+ecosystem, not because the low-level process API is proprietary.
+
+## Business and product positioning
+
+“Turnkey wrapper” is understandable internally but weak externally. It implies
+that the hard work lives underneath and that another wrapper can replace it.
+Prefer one of:
+
+- **The policy-first runtime for coding agents**
+- **Run any coding agent with full permissions, without giving it your host or
+  credentials**
+- **A turnkey local control plane for isolated coding agents**
+- **Docker-like packaging and operations for coding agents, with the security
+  boundary outside the agent**
+
+The open/product split could resemble the container ecosystem:
+
+### Open foundation
+
+- manifest schema and composition;
+- local CLI and core orchestrator;
+- provider adapters;
+- Firecracker/Apple Container/Docker backends;
+- gateway policy format and enforcement;
+- Sandbox Agent compatibility;
+- local audit and supervision; and
+- conformance tests for providers/backends/policy.
+
+### Productizable ecosystem/DX
+
+- polished desktop and mobile clients;
+- fleet/remote-host management;
+- signed and curated role/image/policy registry;
+- team policy distribution and administrative controls;
+- durable searchable transcripts and audit exports;
+- SSO, RBAC, retention, and tamper-evident audit;
+- managed update/compatibility channels;
+- remote browser/preview relay;
+- enterprise support; and
+- optional managed build/cache infrastructure.
+
+OCI itself is not the thing Docker sells. Interoperability expands the market;
+the product captures value through reliable packaging, workflow, distribution,
+management, and trust. bot-bottle should follow that logic rather than trying
+to make its session protocol the moat.
+
+## Strategic threat from Sandbox Agent
+
+Sandbox Agent is a real threat for three reasons:
+
+1. **It can become the integration default.** A frontend or agent platform can
+   integrate one API and choose among many agents and sandbox vendors.
+2. **It can own session data and UI.** The universal event schema, Inspector,
+   React components, restoration, terminal, and computer-use APIs give it a
+   natural path toward the operator surface.
+3. **Sandbox providers can move upward.** If E2B, Daytona, BoxLite, or another
+   runtime combines Sandbox Agent with adequate network policy and credential
+   custody, it can offer much of the turnkey stack.
+
+The threat is not that its manifest syntax is better. It currently has no
+equivalent trusted policy composition. The threat is that **the ecosystem may
+standardize around its API before bot-bottle has a stable external control
+surface**. In that world bot-bottle is evaluated as one sandbox provider,
+while the SDK and its consumers own the user relationship.
+
+## Why bot-bottle can still win its layer
+
+Sandbox Agent's scope exclusions align with bot-bottle's deepest work:
+
+- it does not choose or operate the sandbox provider;
+- it does not mediate Git;
+- it does not own network policy;
+- it does not securely deliver credentials;
+- it does not durably store sessions; and
+- it cannot make guest-generated telemetry authoritative.
+
+Those are not incidental features. Together they define the trusted system
+around an untrusted coding agent. bot-bottle also has a narrower and coherent
+initial customer: a developer or small operator who wants existing agent CLIs
+to run locally with broad permissions and bounded consequences.
+
+The durable advantage is therefore:
+
+> Sandbox Agent makes agents controllable. bot-bottle makes them safe and
+> operable.
+
+That sentence remains true only if bot-bottle closes its operator-DX gaps.
+Security without a browser/preview loop, stable API, normalized session view,
+and good parallel-task UX risks becoming an invisible backend feature.
+
+## Integration options
+
+### Option A — Embed Sandbox Agent inside each bottle
+
+bot-bottle launches Sandbox Agent as the provider process supervisor and
+connects it to the host orchestrator through a bottle-scoped authenticated
+channel.
+
+**Benefits**
+
+- immediate provider-neutral session API;
+- more supported agents;
+- normalized streaming and transcripts;
+- terminal, filesystem, process, and computer-use primitives;
+- Inspector/React ecosystem; and
+- less provider-specific reverse engineering in bot-bottle.
+
+**Risks**
+
+- `0.x` API/schema churn;
+- extra binary and release-supply-chain dependency;
+- lowest-common-denominator normalization;
+- conflict with provider-native resume state;
+- an in-guest daemon is attacker-controlled after guest compromise;
+- duplicate orchestration responsibilities; and
+- upstream can move into policy/lifecycle and compete more directly.
+
+**Security rule**
+
+Treat every event and state claim from Sandbox Agent as untrusted telemetry.
+Never delegate egress authorization, credential release, bottle identity,
+authoritative audit, or Git policy to it.
+
+### Option B — Implement a Sandbox Agent-compatible endpoint
+
+bot-bottle maps the external protocol onto its existing provider adapters and
+process model without running the upstream server.
+
+**Benefits**
+
+- ecosystem compatibility with tighter component control;
+- no in-guest daemon dependency; and
+- room to preserve bot-bottle-native lifecycle semantics.
+
+**Risks**
+
+- large and continuing compatibility burden;
+- “full feature coverage” is expensive across all providers;
+- accidental protocol fork; and
+- effort diverted from policy and UX differentiation.
+
+### Option C — Define an independent bot-bottle session API
+
+Build only the control surface bot-bottle needs.
+
+**Benefits**
+
+- clean fit with the trust model and persistent named bottles;
+- no upstream dependency; and
+- deliberate support for supervision and security events.
+
+**Risks**
+
+- recreates a fast-growing open-source project;
+- no existing client ecosystem;
+- slower browser/desktop/mobile work; and
+- increases the chance that Sandbox Agent becomes the de facto standard first.
+
+### Recommendation
+
+Start with **Option A as a bounded compatibility spike**, not a product
+commitment. Do not begin with a clean-room competing protocol.
+
+The spike should answer:
+
+1. Can Claude Code, Codex, and Pi retain exact native resume behavior?
+2. Can Sandbox Agent run without receiving real provider credentials?
+3. Can its server be reached through a bottle-scoped authenticated channel
+   without exposing the orchestrator or broadening guest egress?
+4. Which permission events overlap or conflict with bot-bottle supervision?
+5. Can normalized events be stored while clearly separating untrusted
+   transcript telemetry from authoritative gateway/Git audit?
+6. Can manifest skills, MCP servers, prompt, and startup arguments compile
+   deterministically into its configuration?
+7. Does its versioning policy permit a compatibility contract bot-bottle can
+   support?
+8. What image-size, startup-time, and update burden does the binary add?
+
+If the answers are favorable, adopt it behind a bot-bottle-owned interface and
+pin/test the supported version. If not, implement the smallest compatible
+subset needed by external clients before inventing a wholly separate API.
+
+## Product roadmap implications
+
+The competitor scan and this architecture comparison reorder the likely work:
+
+1. **Provider-neutral control/session compatibility spike**
+2. **Stable authenticated external bot-bottle API**
+3. **Normalized transcript/event persistence**
+4. **Parallel-session operator UI**
+5. **Browser/preview/computer-use capability**
+6. **Policy/image/skill distribution and signing**
+7. **Remote host/fleet management**
+
+This does not mean pausing security work. It means exposing the shipped
+security work through a product surface that can compete with the SDK-plus-
+sandbox ecosystem.
+
+## Decision
+
+Treat Sandbox Agent SDK as a potentially standard **agent process-control
+layer**, not as a sandbox replacement and not as a minor complementary
+library. Position bot-bottle one layer above it:
+
+- manifests express trusted role and environment policy;
+- bot-bottle compiles and enforces that policy across host, gateway, Git, and
+  isolation backends;
+- Sandbox Agent or a compatible protocol controls the selected agent process;
+  and
+- bot-bottle owns the turnkey operator experience.
+
+The Docker analogy is strategically sound when stated as:
+
+> Sandbox Agent can be the portable task/exec protocol; bot-bottle can be the
+> opinionated engine, Compose-like policy layer, and Desktop-like operator
+> product.
+
+It is not sound when stated as:
+
+> Sandbox Agent is OCI and bot-bottle is Docker.
+
+There is no independent OCI-equivalent agent specification yet, and Sandbox
+Agent already reaches into UI/session territory. Compatibility should be
+pursued quickly, while the trusted manifest/enforcement plane and operator
+experience remain the parts bot-bottle deliberately owns.

tests/unit/test_db_store.py

@@ -48,10 +48,24 @@ class TestDbStoreIsMigrated(unittest.TestCase):
         with tempfile.TemporaryDirectory() as d:
             parent = Path(d) / "store"
             parent.mkdir()
-            with patch.object(Path, "chmod", side_effect=OSError("denied")):
+            (parent / "test.db").touch()
+            with patch("os.fchmod", side_effect=OSError("denied")):
                 with self.assertRaisesRegex(OSError, "denied"):
                     _store(parent)
 
+    def test_rejects_database_symlink_without_changing_target(self):
+        with tempfile.TemporaryDirectory() as d:
+            parent = Path(d) / "store"
+            parent.mkdir()
+            target = Path(d) / "target"
+            target.touch(mode=0o644)
+            (parent / "test.db").symlink_to(target)
+
+            with self.assertRaises(OSError):
+                _store(parent)
+
+            self.assertEqual(0o644, stat.S_IMODE(target.stat().st_mode))
+
     def test_returns_false_when_schema_versions_missing(self):
         # DB file exists but has no schema_versions table → OperationalError → False.
         with tempfile.TemporaryDirectory() as d:

tests/unit/test_git_http_backend.py

@@ -5,6 +5,7 @@ import subprocess
 import tempfile
 import threading
 import unittest
+import urllib.error
 import urllib.request
 from pathlib import Path
 from unittest import mock

tests/unit/test_orchestrator_server.py

@@ -70,15 +70,6 @@ def dispatch(
 
     response = asyncio.run(request())
     payload = response.json()
-    if response.status_code == 422:
-        detail = payload.get("detail", []) if isinstance(payload, dict) else []
-        field = ""
-        if isinstance(detail, list) and detail and isinstance(detail[0], dict):
-            location = detail[0].get("loc", ())
-            if isinstance(location, (list, tuple)) and len(location) > 1:
-                field = str(location[1])
-        suffix = f": {field}" if field else ""
-        return 400, {"error": f"invalid request body{suffix}"}
     if isinstance(payload, dict) and "detail" in payload and "error" not in payload:
         payload = {"error": payload["detail"]}
     return response.status_code, payload

tests/unit/test_supervise_edge.py

@@ -140,7 +140,7 @@ class TestStoreGuardBranches(unittest.TestCase):
         with tempfile.TemporaryDirectory() as d:
             db = Path(d) / "q.db"
             store = QueueStore("key", db_path=db)
-            with patch("pathlib.Path.chmod", side_effect=OSError("ro")):
+            with patch("os.fchmod", side_effect=OSError("ro")):
                 with self.assertRaisesRegex(OSError, "ro"):
                     store.migrate()
 
@@ -156,7 +156,7 @@ class TestStoreGuardBranches(unittest.TestCase):
         with tempfile.TemporaryDirectory() as d:
             db = Path(d) / "a.db"
             store = AuditStore(db_path=db)
-            with patch("pathlib.Path.chmod", side_effect=OSError("ro")):
+            with patch("os.fchmod", side_effect=OSError("ro")):
                 with self.assertRaisesRegex(OSError, "ro"):
                     store.migrate()