Commit Graph

246 Commits

Author SHA1 Message Date
Hypatia May
9a8a2fc206 Merge branch 'feat/subagent-report-semantics' into feat/subagent-settlement-delivery
# Conflicts:
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/headless-agent/tests/snapshots/compaction-recovery/session.jsonl
#	examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
2026-08-11 13:55:11 +08:00
Hypatia May
d4c125ceee Merge commit '580051aeb594e683b6fe088b04d9bffe4c4b5b62' into feat/subagent-report-semantics 2026-08-11 13:50:44 +08:00
hypatiamay
c76570a3b8 Merge pull request #2138 from deepseek-harness/feat/parallel-subagent-calls
feat(subagent): sibling delegations are concurrency-safe
2026-08-11 13:24:43 +08:00
Hypatia May
9340604ea5 Merge branch 'feat/subagent-report-semantics' into feat/subagent-settlement-delivery 2026-08-11 13:02:22 +08:00
Hypatia May
dbcbdfa9ce Merge commit '7baf2c33efb98eeea690c5ac58579c95dc52edd1' into feat/subagent-report-semantics 2026-08-11 13:01:29 +08:00
Hypatia May
a26d03960a feat(subagent): sibling delegations are concurrency-safe
One assistant message carrying several subagent calls now overlaps them
under the rolling pool (maxParallelToolCalls) instead of serializing each
foreground delegation behind an exclusive barrier; results still commit
in model order.

tool-subagent declares isConcurrencySafe: () => true for every call form:
children work in their own sessions, a run never mutates the parent
session, and sibling workspace coordination already belongs to the model
for background, continuable, and workflow children. The former
serial-execution pin flips to a parallel pin plus a gated genuine-overlap
test, and the authored subagent-parallel snapshot pins the assembled
transcript (tool/call, tool/call, tool/result, tool/result) with
interchangeable twin children, which replay race-free under the existing
first-call binding and createdAt harvest ordering.

The provider seam now requires concurrent starts and continuable
preparations for distinct children to isolate operation-local state,
cancellation, settlement, and cleanup; a continuable gate test proves a
cancelled preparation leaves no Agent or durable Session while its
sibling persists independently.

Closes deepseek-harness/deepseek-harness#1489
2026-08-11 12:41:24 +08:00
Hypatia May
85dd22fd4f feat(subagent): deliver continuable child settlement to parents
A continuable child that stopped without reporting — an error, a token
ceiling, cancellation, teardown — left its parent nothing to act on.
The continuation manager now delivers an unconditional settlement
notice to the durable direct parent before releasing ownership, folding
consumed work (foldConsumedWork supersedes findLastMessageTurnEnd) so a
claimed-but-unrun prompt reads as aborted rather than completed, waking
an idle parent, steering a busy one, and never waking a closing tree.
2026-08-11 12:31:49 +08:00
Hypatia May
76cf6cbd0b feat(subagent): make final reports the continuable return contract
A continuable child could finish without giving its parent a usable
result: the report tool was described as optional and its default
delivery stayed quiet. Install the child-scoped report obligation (tool
description plus the tool:report prompt section), default reportDelivery
to wakeup, bind shipped subagent_fork delegations to one-shot so fork
keeps its prefix reuse, and extend the ACP snapshot harness to pin child
system prompts alongside child tool schemas.
2026-08-11 11:50:39 +08:00
creatixchu
a82253bb36 Merge remote-tracking branch 'origin/master' into feat/read-image-context 2026-08-11 11:20:47 +08:00
hypatiamay
fea054a1bd Merge pull request #2127 from deepseek-harness/fix/subagent-empty-terminal-message-output
fix(subagent): keep output past an empty terminal message with one selection rule
2026-08-11 11:19:44 +08:00
creatixchu
c1f0a6a683 Merge remote-tracking branch 'origin/master' into feat/read-image-context
# Conflicts:
#	apps/cli/tests/web-agent-presets.e2e.ts
#	packages/fs/tool-fs/package.json
2026-08-11 10:12:14 +08:00
pku-xht
396925ad4c Merge pull request #2137 from deepseek-harness/codex/product-subagent-presets
feat(agent-presets): add Codex and Claude Code subagent tools
2026-08-10 23:43:23 +08:00
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
084638af47 Merge remote-tracking branch 'origin/master' into fix/subagent-empty-terminal-message-output 2026-08-10 21:59:42 +08:00
Hypatia May
2b2899b4ce Merge remote-tracking branch 'origin/master' into fix/continuable-subagent-policy-inheritance
# Conflicts:
#	docs/module-graph.i18n.yaml
#	docs/module-graph.md
#	docs/module-graph.zh.md
#	packages/subagent/subagent-inprocess/src/index.ts
#	packages/subagent/subagent/package.json
#	packages/subagent/subagent/src/child-agent.ts
#	packages/subagent/subagent/src/continuation.ts
#	packages/subagent/subagent/tsconfig.json
2026-08-10 21:42:45 +08:00
pku-xht
e6b6f1a047 Merge master at 35eeb4a112 2026-08-10 20:25:58 +08:00
creatixchu
2b90207770 Merge remote-tracking branch 'origin/master' into feat/read-image-context
# Conflicts:
#	docs/config-catalog.i18n.yaml
#	docs/config-catalog.md
#	docs/config-catalog.zh.md
#	packages/support/llm-replay/src/index.ts
#	packages/support/llm-replay/tests/llm-replay.spec.ts
2026-08-10 20:25:25 +08:00
creatixchu
b07844dd4c Merge branch 'master' into feat/read-image-context
# Conflicts:
#	docs/module-graph.i18n.yaml
#	docs/module-graph.md
#	docs/module-graph.zh.md
2026-08-10 19:01:47 +08:00
Hypatia May
08e4f1b17c Merge remote-tracking branch 'origin/master' into fix/subagent-empty-terminal-message-output 2026-08-10 17:11:30 +08:00
ZiyaZhang
c969d69f10 Merge latest master into PR branch 2026-08-10 02:10:57 -07:00
pku-xht
14dc8cd349 docs(agent-presets): record shared product provider placement 2026-08-10 16:57:56 +08:00
Hypatia May
1ac58714d1 Merge remote-tracking branch 'origin/master' into fix/continuable-subagent-policy-inheritance 2026-08-10 16:54:44 +08:00
Turtle
a27efdef36 docs: make technical prose concrete 2026-08-10 16:34:20 +08:00
ZiyaZhang
191c7625a4 Merge master and repair CI for bounded diff basis 2026-08-10 01:18:38 -07:00
Hypatia May
ea47c32805 review: one fold implementation, uniform end-edge absence, partial text in tool errors, snapshot scenario
Address ds-review-bot on #2127:

- assistant-output: the rule has ONE implementation, the incremental
  AssistantOutputFold (push/pushText/collect); finalAssistantOutput folds a
  complete suffix, the SDK backend folds notification events, and the ACP
  backend folds raw chunk text into the same streamed fallback.
- subagent/end.lastAssistantMessage: 'no output' is encoded once — absent,
  never [], on both lifecycle shapes (observeRun now omits empty output).
- tool-subagent: a non-completed foreground result stays isError but appends
  the child's preserved partial text after the stop-reason headline.
- Authored keyless snapshot scenario subagent-max-tokens-partial pins the
  assembled transcript: the child's committed log carries the usage-only
  empty message and the parent's tool result carries the partial answer.
- Rule-boundary sentence (message wins over later streamed text) and the
  consumer half recorded in the Agent Note; comments trimmed to pointers.
2026-08-10 16:09:04 +08:00
creatixchu
1861a3fc7c feat(fs): add a minimal read_image tool over the attachment and fs seams
The model reads a PNG/JPEG/WebP/GIF file, the bytes commit through the
durable attachment lifecycle, and the tool result carries the real
ImageBlock so the image enters context from the next request onward.
FileSystem gains a bounded readBytes primitive (local + E2B providers);
registration is conditional on the attachment store, and a strict
execution gate refuses routes that do not declare image input, so a
text route's durable history stays free of image blocks. llm-replay
models may declare inputModalities, letting keyless ACP snapshots pin
both the sha256-referenced success and the verbatim refusal.

Supersedes the withdrawn route-scoped design of PR #598; the decision
record is .agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md.
2026-08-10 15:09:07 +08:00
pku-xht
b1d67a6935 feat(agent-presets): add Codex and Claude Code subagent tools 2026-08-10 12:45:05 +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
Tianyi Cui
ceba53edd7 fix(fs): observe absence before guarded recreation 2026-08-09 17:43:53 +08:00
Turtle
dda02250f5 docs: reserve seam for complete capabilities 2026-08-09 17:26:57 +08:00
ZiyaZhang
1a6037c9fb Merge remote-tracking branch 'origin/master' into fs-overwrite-diff-bound-v2
# Conflicts:
#	docs/subsystems/lsp.i18n.yaml
#	packages/fs/fs-local/README.i18n.yaml
#	packages/fs/fs-local/README.md
#	packages/fs/fs-local/README.zh.md
#	packages/fs/fs-local/src/index.ts
2026-08-08 12:20:09 -07:00
ZiyaZhang
9a299f9827 fix(fs-local): degrade basis I/O failures to null
Descriptor-phase errnos in readTextForDiff fold to before: null so a file
deleted or made unreadable after the caller's preflight cannot fail the
committed write; cancellation and non-errno faults still propagate. Drops
the now-covered isFile v8 ignore, extends llm-replay with catalog
capability parity (defaultMaxTokens/reasoningEfforts), and records the
fs-write-overwrite-bounded keyless snapshot pinning the over-limit
whole-file fallback through the real acp-agent composition.
2026-08-08 11:49:42 -07:00
Tianyi Cui
07fbc2cda8 test(subagent): execute control tools in ACP replay 2026-08-08 21:05:58 +08:00
Tianyi Cui
dc64c5f1c2 fix: guard human interaction by runtime ownership 2026-08-08 15:30:08 +08:00
Tianyi Cui
6d09c315b9 cleanup: remove private repository references 2026-08-08 01:10:57 +08:00
Tianyi Cui
a8a12ffc23 cleanup: replace FIXMEs with tracked issues 2026-08-08 00:04:55 +08:00
fz
dccd6bf79f Merge remote-tracking branch 'origin/master' into codex/fix-compact-agents-reinjection
# Conflicts:
#	.agents/notes/implemented/feature/2026-06-24-workspace-context.i18n.yaml
#	.agents/notes/implemented/feature/2026-06-24-workspace-context.md
#	.agents/notes/implemented/feature/2026-06-24-workspace-context.zh.md
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/cordis-catalog/events.md
#	docs/core-data-structures/system-prompt.i18n.yaml
#	docs/event-producer-consumer.md
#	examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
#	packages/context/workspace-context/README.i18n.yaml
#	packages/context/workspace-context/README.md
#	packages/context/workspace-context/README.zh.md
#	packages/context/workspace-context/src/index.ts
#	packages/context/workspace-context/tests/workspace-context.spec.ts
#	packages/core/agent-loop/README.i18n.yaml
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent/README.i18n.yaml
#	packages/core/agent/README.md
#	packages/core/agent/README.zh.md
#	packages/core/agent/tests/agent.spec.ts
#	packages/core/system-prompt/README.i18n.yaml
2026-08-06 10:16:16 +08:00
_Kerman
289a23421d Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-06-sandbox.md
#	.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md
#	packages/host/apiproxy/README.i18n.yaml
2026-08-05 15:34:19 +08:00
kingwl
75bd2b8aaa Merge remote-tracking branch 'origin/master' into fix/landlock-runner-failure-classification
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md
#	docs/core-data-structures/sandbox.i18n.yaml
#	docs/core-data-structures/sandbox.zh.md
#	docs/postmortem/README.i18n.yaml
#	docs/postmortem/README.zh.md
#	examples/acp-agent/tests/acp.snapshot.ts
#	native/landlock-run/README.i18n.yaml
#	packages/sandbox/sandbox-local/README.i18n.yaml
#	packages/sandbox/sandbox-local/README.zh.md
#	packages/sandbox/sandbox/README.i18n.yaml
2026-08-05 13:17:38 +08:00
_Kerman
97e7d68340 Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification
# Conflicts:
#	examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl
2026-08-05 10:39:18 +08:00
Hypatia May
96ba98c99e fix(sandbox): require runner-specific spawn evidence 2026-08-04 14:47:46 +08:00
_Kerman
eaa497d735 Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification
# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml
#	examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl
#	packages/ui/tui/README.i18n.yaml
#	packages/ui/tui/src/components/dialogs.ts
#	packages/ui/tui/tests/tui.spec.ts
2026-08-04 10:52:45 +08:00
Hypatia May
71aafeb858 Merge origin/master into fix/landlock-runner-failure-classification 2026-08-04 09:14:13 +08:00
Hypatia May
6343d8f6e6 fix(sandbox): evidence-gate runner failures (round 1) 2026-08-03 17:31:08 +08:00
_Kerman
cb2f01f48c refactor(agent-loop): drop the steering/message session event
Steer, inject, and followup now land as durable user/message events on the
session surface; the steering/message event type and its ConversationNode
kind are removed from the client projection. Update tests, docs, generated
catalogs, and agent notes to match, and align the steering e2e fixture and
prompt inventory assertions with the durable user/message landing.
2026-08-03 16:04:26 +08:00
_Kerman
f4a2e0d10a fix(agent): align consumers with inbox lifecycle 2026-08-03 13:14:24 +08:00
_Kerman
dc1d542092 Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification
# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-31-goal-owned-durable-events.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.i18n.yaml
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.i18n.yaml
#	docs/core-data-structures/core.md
#	docs/core-data-structures/core.zh.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	docs/persistence-catalog.md
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl
#	examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl
#	examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl
#	examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl
#	examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
#	examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl
#	examples/jsonrpc-agent/tests/snapshots/subagent-spawn/notifications.expected.jsonl
#	examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl
#	packages/acp/acp/README.i18n.yaml
#	packages/acp/acp/src/index.ts
#	packages/client/connection/src/client/index.ts
#	packages/client/runtime/README.i18n.yaml
#	packages/client/runtime/README.md
#	packages/client/runtime/README.zh.md
#	packages/client/runtime/src/client/sessions/conversation.ts
#	packages/client/runtime/src/client/sessions/session.ts
#	packages/client/runtime/tests/queue-store.spec.ts
#	packages/client/ui-conversation/src/client/input/contract.ts
#	packages/client/ui-goal/README.i18n.yaml
#	packages/compact/compact-basic/src/index.ts
#	packages/context/time-context/tests/time-context.spec.ts
#	packages/context/tmux-context/tests/tmux-context.spec.ts
#	packages/context/workspace-context/tests/workspace-context.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/README.i18n.yaml
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/README.zh.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent-loop/tests/agent.spec.ts
#	packages/core/agent-loop/tests/loop.spec.ts
#	packages/core/agent/README.i18n.yaml
#	packages/core/agent/README.md
#	packages/core/agent/README.zh.md
#	packages/core/agent/src/types.ts
#	packages/core/session/README.i18n.yaml
#	packages/core/session/README.md
#	packages/core/session/README.zh.md
#	packages/goal/command-goal/tests/command-goal.spec.ts
#	packages/goal/goal/tests/goal.spec.ts
#	packages/goal/tool-goal/README.i18n.yaml
#	packages/goal/tool-goal/README.md
#	packages/goal/tool-goal/README.zh.md
#	packages/host/apiproxy/README.i18n.yaml
#	packages/host/apiproxy/README.md
#	packages/host/apiproxy/README.zh.md
#	packages/host/apiproxy/src/api-proxy.ts
#	packages/host/apiproxy/src/api/events.schema.ts
#	packages/host/apiproxy/src/api/events.ts
#	packages/host/apiproxy/src/api/rpc.ts
#	packages/host/apiproxy/tests/api-proxy-commands.spec.ts
#	packages/host/apiproxy/tests/api-proxy-projections.spec.ts
#	packages/host/apiproxy/tests/rpc-schemas.spec.ts
#	packages/pty/pty-local/tests/index.spec.ts
#	packages/pty/pty-local/tests/local.spec.ts
#	packages/pty/tool-pty/tests/loader-composition.spec.ts
#	packages/pty/tool-pty/tests/tools.spec.ts
#	packages/session-persistence/session-checkpoint-policy/src/index.ts
#	packages/session-persistence/session-persistence/tests/coordinator-contract.ts
#	packages/skill/tool-skill/tests/tool-skill.spec.ts
#	packages/subagent/subagent-inprocess/README.i18n.yaml
#	packages/subagent/subagent-inprocess/README.md
#	packages/subagent/subagent-inprocess/README.zh.md
#	packages/subagent/subagent-inprocess/src/index.ts
#	packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts
#	packages/support/acp-snapshot/src/harness.ts
#	packages/ui/tui/tests/tui.spec.ts
2026-08-03 10:56:09 +08:00
Huanqi Cao
b2838fb2be fix(pwsh): close the remaining review threads
- scrubbedParentEnv folds case before the DSH_ prefix check (Windows env
  names are case-insensitive; a parent dsh_* entry read back as \*
  in the child) and the service spec pins the lowercase probe.
- The acp.snapshot.ts pwsh probe follows resolvePwshPath() like the package
  suites, so a Windows host with only an install-location pwsh still runs
  the scenario.
- pwsh-tool-turn is re-recorded around [Console]::Out.Write('PWSH_OK'):
  the fixture carries no platform newline, so one recording replays on
  Windows and POSIX alike (record + refresh; replay-verified keyless).
- The pwsh-local Known Limitations bullet drops the self-defeating no-op
  advice: & { } is scoped to param(...), using/#requires scripts run from a
  file (both languages, pairing re-recorded).
- The capability-seams graph moves ctx.bashEnv ownership to bash-env and
  lists pwsh-local/tool-pwsh on the ctx.bash seam (source updated,
  docs regenerated).
- The tool-bash presenter fixture retires the stale 'command aborted'
  literal for the shipped 'tool call aborted' message.
2026-08-02 21:46:53 +08:00
Huanqi Cao
ed39ff096f test(fixtures): pin the TOOL_ABORTED message and keep the pwsh fixture replayable; restore trimmed testing.md clauses 2026-08-02 20:07:26 +08:00