Commit Graph

21 Commits

Author SHA1 Message Date
imccyu
8cbdd5b9d0 refactor(session): route construction through Session.create 2026-08-05 11:56:14 +08:00
Tianyi Cui
e088cfa59d refactor(sandbox-policy): remove capability family registries 2026-07-31 13:49:41 +08:00
NI0317
8b4cbe4293 feat(system-prompt): cache dynamic policy context 2026-07-30 22:09:15 +08:00
NI0317
87a4aaa32e feat(sandbox-policy): describe enforced file families 2026-07-30 18:51:29 +08:00
NI0317
7407c26bc1 feat(sandbox-policy): expose current file policy 2026-07-30 15:48:05 +08:00
Tianyi Cui
cfceb8452b subagent: seed inherited policy events at creation
The parent implementation introduced sandboxMode and approvalPolicy as generic SessionHeader fields, then propagated those fields through both persistence backends, session-query indexes, collision checks, policy-specific seed-boundary folds, catalogs, and a broad test matrix. That storage plane is unnecessary: Session already accepts a validated constructor seed, and persistence captures that seed when the session is announced before committing its first batch.

Capture each parent override synchronously at delegation, append source-tagged sandbox/mode and approval/policy records after the optional fork prefix, and create the child with that combined seed. Keeping header.seedLength at the original fork-prefix length preserves lineage while ordinary last-event-wins folds make the inherited records outrank stale parent history and remain subordinate to later child switches. Unswitched parents still stamp nothing, so children continue to follow deployment defaults.

Remove the generic header fields and every persistence/query/schema branch built around them. Collapse the inheritance suite from ten leaking scenarios to four owned-context cases covering real filesystem confinement, stale fork precedence, delegation-time capture, and the no-override path. The assembled headless snapshot now asserts the persisted inheritance event directly.

This keeps the security behavior while restoring policy ownership to the existing event log and deleting the speculative durability machinery that the original tests did not exercise.
2026-07-28 21:31:17 +08:00
kingwl
290e1acc45 policy: guard adoption baselines, resolve-time validation, and inherited-delta narration
Review fixes (ds-review-bot on #623):

- Persistence adoption compares the immutable policy baselines: onCreated's
  ownerless claim and adoptLivePrefix retain the STORED header, so a
  same-id live session with a conflicting baseline now rejects as a
  collision instead of appending under read-only and resuming under the
  stored danger-full-access.
- resolve() resolves the session override BEFORE applying an explicit
  approved mode: the one-shot grant no longer bypasses the unconditional
  durable-header validation.
- The approval narrator attributes positionally over the session's OWN
  events (past the seed boundary): a fork child whose baseline delta has
  no own override narrates 'inherited from the delegating session' instead
  of misattributing a stale seed-carried switch to the user or the
  operator.

Red-first: baseline-conflict adoption in the shared coordinator contract
(both backends), resolve-with-explicit-mode validation, and the fork-child
narration attribution case.
2026-07-26 23:56:41 +08:00
kingwl
9aaa4a871f policy: reject out-of-range seed boundaries; carry baselines through session-query
Review fixes (ds-review-bot on #623):

- overrideOf (both knobs) rejects a seedLength past the log end before
  slicing: a malformed durable boundary would otherwise empty the
  own-switch slice until the log outgrew it, letting a wide baseline
  shadow a REAL later tightening. Malformed durable metadata fails loud,
  never open.
- The session-query derived index carries the two baseline fields end to
  end: schema columns on both session tables (SESSION_QUERY_SQLITE_SCHEMA
  _VERSION 6 — derived, rebuilds in place), inserts, header selects, the
  candidates CTE, rowHeader, sameHeader, and the cross-source
  assertSessionHeadersCompatible — so a search hit's header keeps the
  child's inherited confinement and conflicting live/persisted baselines
  reject.

Red-first: out-of-range seedLength tests in both policy suites;
baseline round-trip and live/persisted baseline-conflict tests in the
session-query sqlite suite.
2026-07-26 23:31:01 +08:00
kingwl
99f5fab7bc policy: scope seed-boundary slicing to delegation children
Review fix (ds-review-bot on #623): the unconditional slice regressed the
public SessionStore.fork path — a generic fork child gets seedLength but no
policy baseline, so slicing discarded its seed-carried sandbox/approval
switches and silently widened it to the deployment defaults (a forked
read-only/never parent produced a workspace-write/ask child).

overrideOf now branches on baseline presence: with a header baseline (a
delegation child) the fold covers only own post-seed switches — the
baseline captured from the parent's FULL log subsumes seed history; without
one, the whole log — seeded switches ARE the replayed inherited truth. The
permission preset fold scopes the same way. Red-first: generic-fork
seed-carried override tests in both policy suites.
2026-07-26 23:06:15 +08:00
kingwl
f505bd9258 policy: resolve every knob consumer through the shared override chain
Review fixes (ds-review-bot warnings on #623):

- One chain, every consumer: the override resolution (own post-seed
  switches ?? header baseline, closed-vocabulary validated) moves into pure
  exports (sandboxOverrideOf / approvalOverrideOf); the services delegate,
  and the permission presets consume them — current(session) and set()
  now see inherited baselines, so a child inheriting danger-full-access
  gets REAL knob switches when workspace-write is selected instead of a
  silent no-op, and a seed-carried preset selection is subsumed by the
  baseline. current(events) becomes current(session) (pre-release; the
  only callers were tests).
- Unconditional durable validation: a malformed header baseline fails
  loud on every read, no longer shadowed by an own switch.
- The two policy peers are declared optional (peerDependenciesMeta), so a
  thin spawn/fork deployment without policy plugins can consume the
  driver; verify-runtime-closure honors the flag.

Red-first: inherited-preset derive/switch-away and seeded-selection tests
in the permission suite; malformed-baseline-with-own-switch tests in both
policy suites.
2026-07-26 22:02:02 +08:00
kingwl
c53e9c90db subagent: carry inherited policy overrides in the child session header
Review fix (ds-review-bot critical #2 on #623): the first-turn event stamp
had a durability hole no turn anchoring can close — an idle SessionStart-
style injection persists a complete one-shot turn before any prompt turn
opens, so a crash in that window left a resumable-looking child with no
inherited policy, falling back to a possibly wider deployment default.

The captured overrides now ride the child's creation meta into its
immutable SessionHeader (sandboxMode/approvalPolicy, neutral strings at the
session boundary — the delegationDepth precedent), durable from the moment
the session exists: no listener ordering can starve the baseline and no
crash window can lose it. overrideOf(session) on both policy services
resolves fold(events past header.seedLength) ?? header baseline, validating
against the closed vocabulary on read; stampOverride and the prompt-submit
listener machinery are deleted. The header field rides both persistence
backends (JSONL header line; SQLite sessions columns, SCHEMA_VERSION 11 —
pre-release, no migration). pty-local reads through overrideOf so PTY
spawns see the baseline too.

Red-first: header-durability-before-any-turn test (the injection crash
window shape), baseline/seed-boundary/closed-vocabulary contract tests in
both service suites; the real-wall suite (race, veto, fork stale-seed,
grandchild) re-anchored on header assertions and green. The Agent Note's
Alternatives now records the superseded event-stamping iteration with the
review evidence; bilingual docs updated.
2026-07-26 18:16:45 +08:00
kingwl
933e889fb8 Merge remote-tracking branch 'origin/master' into feature/subagent-policy-inheritance
# Conflicts:
#	docs/event-producer-consumer.md
2026-07-25 11:01:40 +08:00
kingwl
6fa2377e34 subagent: capture overrides at delegation; stamp ahead of prompt vetoes
Review fixes (ds-review-bot on #623):

- Capture-at-delegation: the driver now reads overrideOf(parent.session)
  for both knobs synchronously before its first await, and the prompt-submit
  listener stamps those captured values — a parent switch racing the child's
  asynchronous creation belongs to the parent's future, not the child. The
  inheritOverride(parent, child) service method is split into its two halves
  (overrideOf / stampOverride) accordingly.
- Veto safety: the one-shot prompt-submit listener registers with
  prepend: true, so a veto-capable listener (a denying UserPromptSubmit
  hook) cannot close the child's first turn without the durable stamp.

Both regressions are pinned red-first in inheritance.spec.ts: the
delegation-vs-late-switch race (delegate tool flips the caller wider while
the creation transaction is pending) and a blocking prompt-submit listener
(stamp survives a promptless first turn). Service contract tests renamed to
the split API; READMEs and the bilingual Agent Note updated.
2026-07-25 10:51:25 +08:00
kingwl
669771097d subagent: inherit parent sandbox/approval overrides in in-process children
Per-session policy overrides (sandbox/mode, approval/policy) never crossed
the delegation boundary: a spawn child of a read-only-switched parent ran
under the wider deployment default, and a fork child missed any switch made
after its seed boundary — delegation was a bypass channel for a user's
tightening.

The in-process driver now snapshots the delegating parent's override chain
and stamps it onto the child through the canonical write paths
(SandboxPolicyService.inheritOverride / ApprovalService.inheritOverride),
anchored inside the child's first turn via a one-shot agent/prompt-submit
listener: turn-enclosed (durable), ahead of the first request (an inherited
'never' reaches the child's first system prompt), and positioned after any
stale fork-seed switch so the ordinary last-event-wins fold resolves it.
Only overrides are copied — an unswitched parent stamps nothing and the
child follows the live deployment default; both services are consumed
opportunistically, so compositions without them delegate unchanged. Nesting
composes by construction (each stamp folds the already-stamped parent log).

Evidence: inheritance.spec.ts drives scripted-model children into the real
dsh-fs-sandbox fence through the real write tool (disk-state + denial-marker
assertions; spawn, stale-seed fork, grandchild, escalation fail-closed, and
no-stamp guards), inheritOverride contract tests in both service suites, and
the recorded subagent-sandbox-inheritance ACP snapshot (read-only preset →
delegate → child denied, replayed keylessly).

See .agents/notes/implemented/feature/2026-07-25-subagent-policy-inheritance.md.
2026-07-25 04:06:19 +08:00
Tianyi Cui
f9a638b8a6 Stabilize master CI across platforms 2026-07-25 00:10:37 +08:00
Tianyi Cui
c1d3036274 Merge remote-tracking branch 'origin/master' into codex/session-scoped-sandbox-roots
# Conflicts:
#	examples/acp-agent/tests/acp.snapshot.ts
#	packages/examples/agent-spine-demo/package.json
#	pnpm-lock.yaml
2026-07-21 20:00:55 +08:00
Tianyi Cui
ae98294ec5 fix(sandbox): preserve filesystem cwd semantics 2026-07-21 19:53:02 +08:00
Tianyi Cui
504fbf59f3 fix(invariants): replay histories and pack companions 2026-07-21 17:46:43 +08:00
Tianyi Cui
ff21f91a39 fix(sandbox): resolve workspace roots per session 2026-07-21 00:44:28 +08:00
Tianyi Cui
f78b17a352 Merge branch 'codex/invariant-package-registration-gate' into codex/package-invariant-checks 2026-07-20 19:55:46 +08:00
kingwl
2dc62497ce feat(sandbox): cross-family file sandbox — one policy home, sandboxed fs provider, fs escalation parity
Extend SandboxMode enforcement from bash to the filesystem tools, the sandbox
RFC's deferred cross-family phase.

- dsh-sandbox-policy (new, ctx.sandboxPolicy): the single home for the
  deployment default mode + workspaceRoot and the per-session override event,
  renamed bash/sandbox-mode -> sandbox/mode and moved here with its fold/setter.
  Decouples the bash seam from dsh-session.
- dsh-fs-sandbox (new): SandboxedFileSystem extends LocalFileSystem and fences
  write/edit by the per-call mode (read-only denies, workspace-write contains to
  the workspace + temp roots via the shared writableRoots, danger passes
  through); reads pass through. Structured FS_SANDBOX_DENIED; in-lock parent
  re-canonicalization. A policy fence in trusted code, not a kernel boundary.
- dsh-sandbox: the shared escalation kit (writableRoots, the strictly-wider
  ladder, denial/hint markers, approveEscalation) both tool families use;
  approveEscalation takes a structural approver so dsh-sandbox gains no
  approval/agent dependency, and both tools stay duplication-free.
- tool-fs: write/edit advertise sandbox_permissions/justification under a
  confining ctx.fs, map FS_SANDBOX_DENIED to the shared [sandbox: ...] marker,
  and resolve the same one-approved-wider retry.
- examples/acp-agent: composes sandbox-policy + fs-sandbox, drops the gating
  that disabled the fs stack under confined modes.

RFC docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md; the old
sandbox RFC's In-process/deferred/FAQ sections updated to shipped fact.
2026-07-14 20:05:57 +08:00