Tianyi Cui
41d3e78d3a
test(snapshots): require explicit delegation depth
2026-07-20 17:59:13 +08:00
Tianyi Cui
0893aaa7cb
test: rename golden snapshot files to expected
2026-07-19 17:45:49 +08:00
Tianyi Cui
35473c2701
Merge branch 'codex/simp-unify-agent-session-id' into codex/simp-ui-identity-residue
...
# Conflicts:
# AGENTS.md
# docs/config-catalog.md
# docs/event-producer-consumer.md
# examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
# examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
# examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl
# examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl
# packages/ui/acp/README.md
# packages/ui/acp/src/index.ts
# packages/ui/jsonrpc/README.md
# packages/ui/jsonrpc/src/server.ts
2026-07-18 12:25:33 +08:00
Yichen Jiang
f1d39921c9
feat(acp): advertise and switch llm models
2026-07-15 13:33:42 +08:00
Tianyi Cui
5409452cc7
test: refresh snapshots after master merge
2026-07-14 19:30:29 +08:00
Tianyi Cui
f0fc20ca42
docs: align prose with runtime contracts
2026-07-14 16:21:41 +08:00
Tianyi Cui
1ab64dba62
Merge remote-tracking branch 'origin/master' into codex/trim-ai-prose
...
# Conflicts:
# docs/config-catalog.md
# docs/development.i18n.yaml
# docs/development.zh.md
# docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md
# docs/rfc/implemented/feature/2026-07-06-sandbox.md
# examples/AGENTS.md
# examples/README.md
# examples/acp-agent/README.md
# examples/acp-agent/cordis.yml
# examples/acp-agent/tests/acp.e2e.ts
# examples/acp-agent/tests/escalation.e2e.ts
# examples/sandbox-acp-agent/README.md
# examples/sandbox-acp-agent/cordis.snapshot.yml
# examples/sandbox-acp-agent/cordis.yml
# examples/sandbox-acp-agent/tests/acp.snapshot.ts
# packages/ui/acp-agent/src/bin.ts
# packages/ui/acp/README.md
# packages/ui/jsonrpc-agent/README.md
# packages/ui/jsonrpc-agent/src/bin.ts
# scripts/verify-translation-pairing.ts
2026-07-14 12:34:14 +08:00
Tianyi Cui
e3d7bb62d8
fix(permission): address human review feedback
2026-07-14 01:09:44 +08:00
Tianyi Cui
74f61c89e3
test(hooks): snapshot the CC + Codex hook matrix end-to-end
...
Load both hook bridges in the ACP example (dsh-hooks-claude → ./hooks.json,
dsh-hooks-codex → ./codex-hooks.json) so the full-transcript snapshot tier can
exercise each dialect against the real app. An absent config file is a silent
no-op, so a scenario carries only the file it needs and the other bridge
vanishes — verified byte-identical against every pre-existing snapshot.
Add a scenario per hook point × its headline Decision outcome, both dialects:
UserPromptSubmit block (authored, keyless) + context-fold, PreToolUse deny/ask,
PostToolUse block/context, Stop force-continue. The mid-turn scenarios are
recorded against the real API with the hook active, so the model's reaction to
a denied/blocked/force-continued turn is part of the replayed transcript.
SessionStart and SubagentStart are deliberately excluded (detached best-effort
inject races the log position — a recorded golden fails 10/10 on its own
replay), as is SubagentStop (observe-only, zero transcript footprint — a golden
could never be proven to fail). Both stay on the bridges' unit coverage. See
docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md.
2026-07-04 00:40:35 +08:00
