Files
bot-bottle/claude_bottle/backend/docker/capability_apply.py
T
didericis ef5d2f9a4d
test / unit (pull_request) Successful in 17s
test / integration (pull_request) Successful in 1m31s
feat(state): preserve on crash + always snapshot transcript
Extends the preserve-on-capability-block design to also preserve
state on agent crash, and snapshots the transcript on every
teardown so any resume (crash or capability-block) gets a warm
claude session — not a cold start.

- capability_apply: rename _snapshot_transcript → snapshot_transcript
  (public; reused below). No behavior change in the capability path.
- cli/start.py: capture bottle.exec_claude's exit code; while the
  container is still alive (inside the launch context):
    * always snapshot_transcript(identity)
    * if exit_code != 0, mark_preserved(identity)
  Then the existing _settle_state runs after teardown.

Now the preservation matrix is:

  exit 0   (clean)          → snapshot + cleanup state
  exit ≠0  (crash, Ctrl-C)  → snapshot + preserve + show resume hint
  capability-block          → (already snapshotted/preserved by apply
                               before teardown; this path is a no-op
                               because the container is already gone
                               by the time exec_claude returns)

snapshot_transcript is best-effort — capability-block's earlier
snapshot is not clobbered when the container is already torn down,
and a missing /home/node/.claude is a warn + skip.

Tested behavior: clean exit doesn't preserve, non-zero exit
(including SIGINT/130 and SIGKILL/137) preserves; empty identity
no-ops both helpers.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-25 07:05:23 -04:00

225 lines
8.3 KiB
Python

"""capability_apply — host-side orchestrator for capability-block
remediation (PRD 0016).
On approval of a capability-block proposal, the dashboard calls
apply_capability_change(slug, new_dockerfile) which:
1. Snapshots the agent's transcript dir to
~/.claude-bottle/state/<slug>/transcript/ (best-effort).
2. Pushes the agent's working tree via `git push` (best-effort —
no upstream / no commits / no git repo all skip with a log).
3. Writes the new Dockerfile to
~/.claude-bottle/state/<slug>/Dockerfile (PRD 0016 Phase 1
state). The next `cli.py start <agent>` picks it up.
4. Force-removes the agent container + all sidecars + the
per-bottle networks. Idempotent — missing resources are not
errors.
Returns (before, after) Dockerfile contents so the dashboard can
record / render the diff. (capability-block has no audit log per
PRD 0013 — the per-bottle Dockerfile state is its own record.)
This is "fire-and-forget" from the agent's perspective: by the time
the dashboard writes the response file the supervise sidecar is
gone, so the agent's tool call connection drops without ever
receiving the response. The replacement agent (next manual
`cli.py start`) sees the new Dockerfile and starts from there.
v1 does not auto-relaunch — see PRD 0016's capability-block return
semantics open question.
"""
from __future__ import annotations
import os
import shutil
import subprocess
from pathlib import Path
from ...log import info, warn
from .bottle_state import (
mark_preserved,
per_bottle_dockerfile,
per_bottle_dockerfile_path,
transcript_snapshot_dir,
write_per_bottle_dockerfile,
)
# Agent home inside the container (per the repo Dockerfile's
# `USER node` + `WORKDIR /home/node`). Used to locate the transcript
# dir + the workspace dir for git push.
_AGENT_HOME_IN_CONTAINER = "/home/node"
_AGENT_TRANSCRIPT_IN_CONTAINER = f"{_AGENT_HOME_IN_CONTAINER}/.claude"
_AGENT_WORKSPACE_IN_CONTAINER = f"{_AGENT_HOME_IN_CONTAINER}/workspace"
# Per-bottle resource name patterns (mirroring prepare.py /
# the various sidecar modules). The agent container's name is the
# slug with no infix; sidecars carry an infix like cred-proxy.
def _agent_container_name(slug: str) -> str:
return f"claude-bottle-{slug}"
def _per_bottle_container_names(slug: str) -> list[str]:
"""All container names that belong to this bottle. Missing
containers are silently skipped by the teardown helper, so it's
fine to include names that don't exist for a given bottle."""
return [
_agent_container_name(slug),
f"claude-bottle-cred-proxy-{slug}",
f"claude-bottle-pipelock-{slug}",
f"claude-bottle-git-gate-{slug}",
f"claude-bottle-supervise-{slug}",
]
def _per_bottle_network_names(slug: str) -> list[str]:
return [
f"claude-bottle-net-{slug}",
f"claude-bottle-egress-{slug}",
]
class CapabilityApplyError(RuntimeError):
"""Raised when the apply fails in a way that should keep the
proposal pending (so the operator can retry). Best-effort
failures (transcript snapshot, git push) do not raise — they
just log and proceed."""
# --- Public helpers --------------------------------------------------------
def fetch_current_dockerfile(slug: str) -> str:
"""Return the Dockerfile content the next `cli.py start <agent>`
would use for this bottle. If a per-bottle override exists, that
one; otherwise the repo's Dockerfile.
Used by the operator-edit verb to show the current source of
truth, and by apply_capability_change for the before-diff."""
override = per_bottle_dockerfile(slug)
if override is not None:
return override
repo_dockerfile = _repo_dockerfile_path()
if repo_dockerfile.is_file():
return repo_dockerfile.read_text()
raise CapabilityApplyError(
f"no per-bottle Dockerfile for {slug} and no repo Dockerfile at "
f"{repo_dockerfile}"
)
def apply_capability_change(slug: str, new_dockerfile: str) -> tuple[str, str]:
"""End-to-end capability-block remediation. See module docstring
for the sequence. Returns (before, after) Dockerfile content."""
if not new_dockerfile.strip():
raise CapabilityApplyError("proposed Dockerfile is empty")
before = fetch_current_dockerfile(slug)
snapshot_transcript(slug)
_push_working_tree(slug)
write_per_bottle_dockerfile(slug, new_dockerfile)
# Set the preserve marker BEFORE teardown so cli.py's session-end
# cleanup sees it and keeps the state dir intact for the
# operator's `cli.py resume <identity>`. Without the marker the
# state dir would be deleted as part of normal session end.
mark_preserved(slug)
_teardown_bottle(slug)
return before, new_dockerfile
# --- Internals -------------------------------------------------------------
def _repo_dockerfile_path() -> Path:
"""Path to the repo's Dockerfile (one dir above this module's
package root). Resolved at call time so the path is correct
regardless of where this module is imported from."""
# claude_bottle/backend/docker/capability_apply.py -> repo root
return Path(__file__).resolve().parent.parent.parent.parent / "Dockerfile"
def snapshot_transcript(slug: str) -> None:
"""`docker cp` /home/node/.claude out of the agent container into
~/.claude-bottle/state/<slug>/transcript/. Best-effort: missing
container, missing dir, or cp error all log a warning and return.
The transcript is what `claude --resume` reads to pick up where
the agent left off.
Called from two places:
- capability-apply, before tearing the bottle down.
- cli.py's session-end path, before the launch context closes,
so a crash or normal exit also leaves a transcript on disk
(deleted along with the state dir on clean exit, kept on
crash or capability-block per the preserve marker)."""
container = _agent_container_name(slug)
dest = transcript_snapshot_dir(slug)
if dest.exists():
# Remove any prior snapshot so the new one is a clean copy.
shutil.rmtree(dest, ignore_errors=True)
dest.parent.mkdir(parents=True, exist_ok=True)
r = subprocess.run(
["docker", "cp", f"{container}:{_AGENT_TRANSCRIPT_IN_CONTAINER}", str(dest)],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
warn(
f"transcript snapshot skipped "
f"({(r.stderr or '').strip() or 'no transcript dir in container?'})"
)
return
info(f"transcript snapshotted to {dest}")
def _push_working_tree(slug: str) -> None:
"""`docker exec <agent> git push` from /home/node/workspace.
Best-effort: not-a-git-repo, no upstream, nothing-to-push, no
network all log a warning and return. The replacement bottle
will pick up whatever's actually upstream."""
container = _agent_container_name(slug)
r = subprocess.run(
[
"docker", "exec", container, "sh", "-c",
f"cd {_AGENT_WORKSPACE_IN_CONTAINER} && "
f"git rev-parse --is-inside-work-tree >/dev/null 2>&1 && "
f"git push origin HEAD 2>&1 || true",
],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
warn(
f"capability-apply: git push skipped "
f"({(r.stderr or '').strip() or 'docker exec failed'})"
)
return
output = (r.stdout or "").strip()
if output:
info(f"capability-apply: git push: {output}")
else:
info("capability-apply: git push ran (no output — likely not a git workspace)")
def _teardown_bottle(slug: str) -> None:
"""Force-remove all per-bottle docker resources. Idempotent —
`docker rm -f` / `docker network rm` silently ignore missing
names, so this can be called even mid-rebuild."""
info(f"capability-apply: tearing down bottle {slug}")
for name in _per_bottle_container_names(slug):
subprocess.run(
["docker", "rm", "-f", name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
for net in _per_bottle_network_names(slug):
subprocess.run(
["docker", "network", "rm", net],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
__all__ = [
"CapabilityApplyError",
"apply_capability_change",
"fetch_current_dockerfile",
"snapshot_transcript",
]