Commit Graph

61 Commits

Author SHA1 Message Date
Hypatia May
f27bdb2be3 Merge remote-tracking branch 'origin/master' into fix/subagent-empty-terminal-message-output
# Conflicts:
#	docs/event-producer-consumer.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/event-producer-consumer.zh.md
#	docs/subsystems/subagent.i18n.yaml
#	docs/subsystems/subagent.md
#	docs/subsystems/subagent.zh.md
2026-08-10 22:59:23 +08:00
Hypatia May
4f23fa84cc fix(subagent): complete output selection contract 2026-08-10 22:19:14 +08:00
Hypatia May
501c3a8ab6 fix(subagent): pin delegated child approvals to 'never' within the inherited sandbox scope
A delegated in-process child now acts only within the sandbox scope fixed
at delegation: captureDelegatedPolicyOverrides still snapshots the parent's
explicit sandbox override but pins the child approval policy to 'never'
(instead of inheriting the parent's), so every child ask — sandbox_permissions
escalations included — is rejected deterministically by ApprovalService
before any answerer, with the audit pair still logged. Every in-process
child additionally receives the scoped subagent:delegation runtime-context
statement telling it to report a scope limitation instead of retrying.

Supersedes the approval half of the policy-inheritance decision (new Agent
Note cross-linked from both prior notes and the approval-seam Q&A); refreshed
child snapshot fixtures carry the pinned event, and
subagent-published-run-failure now persists a one-event child log.
2026-08-10 19:17:37 +08:00
Hypatia May
64e0fbfd6d fix(subagent): inherit parent policy overrides in continuable children
A continuable background child (the default backgroundMode for both
delegation tools) never received the parent session's explicit
sandbox/approval overrides: materialization applied only child
composition, so a danger-full-access parent produced workspace-write
children whose every out-of-workspace operation raised an approval
prompt.

Move the one-shot driver's capture/append pair into the shared
child-agent module (captureDelegatedPolicyOverrides /
appendDelegatedPolicyOverrides) and call it from both paths:
startContinuable captures before its first await, only fresh
materialization appends the source-tagged events (after any fork seed),
and a cold resume replays the persisted delegation events instead of
re-capturing the parent.

Adds the continuable inheritance unit suite, the ACP snapshot scenario
subagent-continuable-inheritance (fails without the fix), the
continuable policy-inheritance Agent Note, and the seam-level README
contract, with bilingual counterparts.

Fixes #1692
2026-08-10 12:16:19 +08:00
Hypatia May
1db1cda464 fix(subagent): keep output past an empty terminal message with one selection rule
A max-tokens step that assembled only tool-call blocks appends an
EMPTY-content assistant/message (the usage host). Three consumers each
hand-rolled output selection and all let it erase the child's real
answer: the in-process readResult and the Activation subagent/end
capture took the last message unfiltered, and the SDK backend let any
message beat its streamed-text fallback; the in-process driver also had
no streamed-text fallback for cancelled turns.

dsh-subagent now owns the canonical rule in src/assistant-output.ts
(last non-empty assistant message, else the accumulated text-delta
stream) and all three consumers apply it. Regression tests in all three
packages fail under the previous selections.

Closes #1514
2026-08-10 11:16:29 +08:00
_Kerman
a6baddaaac refactor: remove per-followup result attribution 2026-07-30 16:48:28 +08:00
Tianyi Cui
739647afc0 fix(subagent): publish inherited policy facts to telemetry
Inherited sandbox and approval events were part of the constructor seed. Session.firstLiveSeq classifies every constructor event as replayed history, so telemetry adoption skipped these child-only creation facts even though no parent or prior process had exported them.

Capture the parent overrides at the same synchronous delegation boundary, but append the events during the child factory setup while the session is still unpublished. They remain ordered after fork history, persist with the first child batch, and retain last-event-wins behavior while landing on the live side of the telemetry boundary. This uses the existing setup and session append contracts instead of adding another seed category or telemetry special case.

Add regression coverage for exporting an unpublished suffix without re-exporting constructor history, assert the spawn and fork firstLiveSeq boundaries, and restore the public seed documentation to replay/fork history only.
2026-07-29 00:39:56 +08:00
Tianyi Cui
6d389d261e docs(policy): describe constructor-seeded inheritance
The implementation no longer stores inherited policy in SessionHeader or resolves a second baseline chain, but the feature, sandbox, and approval notes still described that machinery. Keeping those claims would make the smaller design look incomplete and invite reintroduction of the generic persistence surface.

Rewrite the owning feature note around the actual delegation snapshot: source-tagged policy events follow the optional fork prefix, ordinary last-event-wins folds establish precedence, and persistence captures the constructor seed with the first materialized batch. Condense the alternatives and consequences to the decisions and coverage that remain load-bearing.

Align the sandbox and approval notes plus the subagent-inprocess consumer README with that contract. Update the four Chinese counterparts minimally and re-record each pairing hash so both languages describe the same shipped mechanism.
2026-07-28 21:51:13 +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
2f93614efb Merge remote-tracking branch 'origin/master' into feature/subagent-policy-inheritance
# Conflicts:
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	packages/subagent/subagent-inprocess/README.i18n.yaml
2026-07-28 18:37:46 +08:00
kingwl
d69e1ada97 Merge remote-tracking branch 'origin/master' into feature/subagent-policy-inheritance
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/persistence.i18n.yaml
#	docs/persistence-catalog.md
#	packages/core/session/README.i18n.yaml
#	packages/sandbox/sandbox-policy/README.i18n.yaml
#	packages/subagent/subagent-inprocess/README.i18n.yaml
2026-07-28 18:19:30 +08:00
Yichen Jiang
5358168787 feat(sdk): support max output tokens 2026-07-28 17:36:44 +08:00
_Kerman
cee0666a4d refactor(session): remove synthetic log-only turns 2026-07-28 14:41:51 +08:00
kingwl
bc3e776225 Merge remote-tracking branch 'origin/master' into feature/subagent-policy-inheritance
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml
#	docs/cordis-catalog/services.md
#	docs/persistence-catalog.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	packages/core/session/README.i18n.yaml
#	packages/subagent/subagent-inprocess/README.i18n.yaml
#	packages/ui/user-approval/src/index.ts
2026-07-28 11:19:46 +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
_Kerman
8117f61396 Merge remote-tracking branch 'origin/master' into xtr/agent-loop-message-machine
# Conflicts:
#	packages/context/workspace-context/README.md
#	packages/llm/llm-retry/README.md
#	packages/session-persistence/session-checkpoint-policy/README.md
#	scripts/type-equiv.manifest.json
2026-07-26 16:45:27 +08:00
kingwl
be5f76b6c6 Merge remote-tracking branch 'origin/master' into feature/subagent-policy-inheritance
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml
#	examples/acp-agent/tests/acp.snapshot.ts
2026-07-26 16:12:38 +08:00
Tianyi Cui
226dc7a249 docs: translate remaining READMEs 2026-07-26 05:06:39 +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
_Kerman
992cf894af refactor(agent): unify sourced message delivery 2026-07-24 22:38:50 +08:00
Turtle
b02b438667 refactor(agent): align delivery method names 2026-07-24 15:08:36 +08:00
Tianyi Cui
0dfd9545a6 Merge branch 'codex/tool-json-schema-dsl' into codex/canonical-tool-output
# Conflicts:
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/persistence-catalog.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-write/session.jsonl
#	packages/ui/tui/src/index.ts
#	scripts/type-equiv.manifest.json
2026-07-22 00:23:00 +08:00
Tianyi Cui
5d411f9c4e fix(session-title): preserve agent turn outcomes 2026-07-21 15:49:37 +08:00
Tianyi Cui
66c36e7325 feat: add canonical typed tool outputs 2026-07-21 03:22:14 +08:00
Yichen Jiang
f2a813b791 Merge remote-tracking branch 'origin/master' into fix/subagent-depth-budget 2026-07-20 15:15:31 +08:00
Tianyi Cui
a278374e8f docs: structure model experience fields 2026-07-19 18:08:42 +08:00
Tianyi Cui
bcc920369c docs: document package KV cache effects 2026-07-19 17:39:50 +08:00
Yichen Jiang
0d00106fa8 fix(session): persist the delegation depth in the session header
A subagent child's recursion depth lived only in runtime AgentOptions,
so a persisted child came back from resume counted as top-level and
maxDepth stopped binding after every restart. Add
SessionHeader.delegationDepth, round-trip it through the JSONL and
SQLite backends (SQLite schema v5), restore it on agent-loop resume,
and write it when the in-process backends create a child. The seam now
owns the shared depth vocabulary (delegationDepthOf): the persisted
header is authoritative and monotone — runtime options may deepen it
but never lower it.
2026-07-19 17:20:36 +08:00
Tianyi Cui
ab6faf78ba Merge branch 'codex/simp-hide-concrete-agent-loop' into codex/simp-hide-subagent-internals 2026-07-14 15:41:34 +08:00
Tianyi Cui
f85b831bd2 refactor: hide subagent implementation helpers 2026-07-14 02:41:23 +08:00
Tianyi Cui
eed43abe66 docs: address final model experience review 2026-07-14 00:22:52 +08:00
Tianyi Cui
d77f797d89 docs: replace model experience tables with sections 2026-07-13 22:26:33 +08:00
Tianyi Cui
646f3d2d0c docs: apply verbatim model experience guidance repo-wide 2026-07-13 21:33:23 +08:00
Tianyi Cui
7b539a0f8b docs: align model experience with runtime visibility 2026-07-13 15:00:47 +08:00
Tianyi Cui
8ee569d6bf Merge remote-tracking branch 'origin/codex/package-readme-limitations-audit-20260712' into codex/model-experience-readmes-20260712
# Conflicts:
#	packages/core/tools/README.md
2026-07-13 13:48:43 +08:00
Tianyi Cui
7499fb677a Merge commit '09d5549b92f9aa9752c480a2bfaa0fcc24e05e91' into codex/package-readme-limitations-audit-20260712 2026-07-13 13:22:05 +08:00
Tianyi Cui
e04ec07345 refactor(core): remove owner-final assembly machinery 2026-07-13 13:09:41 +08:00
Tianyi Cui
23850b4ad9 docs: align model experience with scoped runtime 2026-07-12 23:59:05 +08:00
Tianyi Cui
5158cc3e0b Merge remote-tracking branch 'origin/codex/package-readme-limitations-audit-20260712' into codex/model-experience-readmes-20260712
# Conflicts:
#	packages/AGENTS.md
2026-07-12 23:54:00 +08:00
Tianyi Cui
6967c584d1 Merge remote-tracking branch 'origin/worktree-agent-scope-design' into codex/package-readme-limitations-audit-20260712
# Conflicts:
#	packages/core/scope/README.md
#	packages/session-persistence/session-persistence-jsonl/README.md
#	packages/session-persistence/session-persistence-sqlite/README.md
#	packages/subagent/subagent-acp/README.md
#	packages/subagent/subagent-fork/README.md
#	packages/subagent/subagent-inprocess/README.md
#	packages/subagent/subagent/README.md
#	packages/subagent/tool-subagent/README.md
#	packages/support/invariants/README.md
#	packages/support/subagent-mock/README.md
#	packages/workflow/workflow-workerthread/README.md
#	packages/workflow/workflow/README.md
2026-07-12 23:35:47 +08:00
Tianyi Cui
bb3f6bd736 refactor(subagent): unify async readiness and cancellation 2026-07-12 22:41:59 +08:00
Tianyi Cui
cb03c8c284 fix(scope): align trust and input boundaries
Rewrite the agent-scope RFC with executable examples and an explicit security non-goal. Harden subagent scalar and depth validation, and pin live tool-filter semantics across code, tests, and generated docs.
2026-07-12 11:17:57 +08:00
Tianyi Cui
d427478c44 fix(subagent): validate direct depth boundaries 2026-07-12 10:48:20 +08:00
Tianyi Cui
c5b1a7941f fix(scope): harden lifecycle ownership foundation
Make Cordis construction and teardown ownership reentrancy-safe, then carry caller and provider ownership through reservation, setup, publication, quiescence, and sentinel retirement.

Stabilize registry carriers and factory/workflow boundaries, add adversarial lifecycle regressions, and align the rewritten RFC plus generated contracts with the enforced behavior.
2026-07-12 08:57:05 +08:00
Tianyi Cui
a9cb70d896 fix(scope): harden final ownership boundaries 2026-07-12 05:13:17 +08:00
Tianyi Cui
36b8370027 fix(scope): close remaining ownership boundaries 2026-07-12 03:51:55 +08:00
Tianyi Cui
b5cd511f35 docs: address model experience review 2026-07-12 02:55:26 +08:00
Tianyi Cui
a08485fc80 Merge remote-tracking branch 'origin/codex/package-readme-limitations-audit-20260712' into codex/model-experience-readmes-20260712
# Conflicts:
#	docs/cookbook/adding-a-package.md
#	docs/rfc/INDEX.md
#	package.json
#	packages/AGENTS.md
#	packages/bash/bash-sandbox/README.md
#	packages/sandbox/sandbox-local/README.md
#	packages/sandbox/sandbox/README.md
#	packages/session-persistence/session-persistence-sqlite/README.md
#	packages/support/acp-snapshot/README.md
#	packages/ui/app-boot/README.md
#	packages/ui/user-approval/README.md
#	packages/workflow/tool-workflow/README.md
2026-07-12 02:48:49 +08:00