Commit Graph
19 Commits
Author SHA1 Message Date
Tianyi Cui 5c783f3677 Merge branch 'codex/code-mode-typed-results' into codex/code-mode-complete-result-card
# Conflicts:
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.expected.jsonl
#	examples/tui-agent/tests/snapshots/code-mode/terminal.expected.txt
2026-07-22 00:36:06 +08:00
Tianyi Cui ec8e3065ce Merge branch 'codex/canonical-tool-output' into codex/code-mode-typed-results
# Conflicts:
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
2026-07-22 00:29:00 +08:00
Tianyi Cui 449e3cf298 fix(tools): make code result cards authoritative 2026-07-21 18:38:22 +08:00
Tianyi Cui 7c2fb0a6fe fix: keep Code Mode result cards complete 2026-07-21 04:55:56 +08:00
Tianyi Cui c1d7b0df81 feat: return typed values from Code Mode 2026-07-21 04:37:09 +08:00
Tianyi Cui f71f96d292 feat(session-title): integrate queries ACP and TUI 2026-07-21 01:53:37 +08:00
Tianyi Cui 41d3e78d3a test(snapshots): require explicit delegation depth 2026-07-20 17:59:13 +08:00
Yichen Jiang 162da52082 Merge branch 'master' into worktree/provider-routed-llm-adapters 2026-07-15 15:42:19 +08:00
Yichen Jiang 35cae1d389 Merge remote-tracking branch 'origin/master' into worktree/provider-routed-llm-adapters
# Conflicts:
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.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/advanced-toolchain/session.jsonl
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
2026-07-15 10:15:06 +08:00
Tianyi Cui aba1b18eac Merge branch 'codex/simp-prune-tools-prompt-surface' into codex/simp-prune-code-runtime-surface 2026-07-14 23:45:39 +08:00
Tianyi Cui 8ffcef7db9 test(snapshot): split pinned schemas into sidecars 2026-07-14 23:11:21 +08:00
Yichen Jiang e547980d77 feat(llm): route adapters by provider 2026-07-14 21:57:52 +08:00
Tianyi Cui a11396e43c test: refresh code runtime snapshots 2026-07-14 03:09:53 +08:00
Tianyi Cui 9339622d3b test(acp): snapshot system prompts as Markdown 2026-07-11 22:24:20 +08:00
Tianyi Cui 58a5088feb Merge remote-tracking branch 'origin/master' into workflow-vm-to-workerthread
# Conflicts:
#	docs/config-catalog.md
#	docs/event-producer-consumer.md
#	packages/core/tools/tests/gen-tool-catalog.spec.ts
2026-07-09 23:48:17 +08:00
Tianyi Cui 30bc7f6a1d fix: the run_code program IS the execute-card title (root cause: Zed shows nothing else)
Systematic trace through Zed (crates/agent_ui thread_view.rs +
crates/acp_thread): kind:execute routes a tool call onto the
terminal-card layout, whose header (render_collapsible_command) has NO
disclosure toggle, whose body content renders only when is_open — a
flag only a real terminal entity can ever set — and which suppresses
the Raw Input view outright. Every prior attempt (rawInput, pending
content, completed content) targeted slots that layout structurally
never renders; the one slot it always shows is the TITLE, which said
"Run code". codex-acp confirms the idiom: execute cards are titled
with the command itself.

presentCall now titles the card with the program (rawInput kept as the
canonical input slot); presentResult omits the title — an update
replaces only provided fields, so the program header persists — and
carries the captured output as content. Goldens re-recorded; the unit
test pins title-carries-program on both frames.
2026-07-09 22:41:57 +08:00
Tianyi Cui f505776eee fix: keep the program on the COMPLETED run_code card (agent review follow-up)
The previous commit put the fenced program only on the pending card —
but an ACP tool_call_update's content REPLACES the card content (Zed
truncates to the new list, crates/acp_thread update_fields), so the
code vanished the moment the run completed and was effectively never
visible. presentResult now re-carries the fenced program before the
captured output via a shared fencedProgram helper; the completed card
body is program + output, rendered by Zed as syntax-highlighted
markdown behind the card disclosure. Goldens re-recorded (filtered
this time: DSH_SNAPSHOT=record vitest -u -t mode-turn); unit test pins
the two-block result content.
2026-07-09 22:04:52 +08:00
Tianyi Cui 2c03b2bc29 feat: surface the run_code program in the ACP tool-call card
The generated program rode only rawInput — the detail/expanded slot
many ACP clients never open — so the code a run executed was invisible
in the UI stream. presentCall now also carries it as a fenced ts block
in the card's content, which the bridge already forwards as tool_call
content. The two code-mode snapshot goldens are re-recorded live and
replay green; the presentation unit test pins the fenced block.
2026-07-09 20:56:44 +08:00
Tianyi Cui b59d245c7c feat: Code Mode — the registry's mode config, the SDK codegen, and the run_code bridge
The dsh-tools half of the Code Mode RFC (its fourth, final change): the
registry gains its first config — mode: native | code | both — and OWNS how
its tools reach the model. 'code' contributes exactly one wire tool,
run_code, plus a lazy tools:sdk prompt section declaring every other tool
as a generated TypeScript API (jsonSchemaToTs: total over the defineTool
subset, unknown degradation, lexicographic byte-identical rendering);
'both' ships both representations; 'native' is byte-for-byte the old
behavior. Non-native modes fail every assembly loudly without a
typescript-language ctx.codeRuntime.

run_code's dispatch bridge: JSON-normalizes each binding argument before
dispatch (what dispatches is what the tool/code-dispatch event logs — the
append can never fail on payload shape; BigInt/circulars reject that one
call), serializes all program tool calls through a per-run queue (even
Promise.all — no concurrency-safety metadata yet), routes every sub-call
through tools/pre-execute → tools/post-execute (a deny rejects the
program-side promise), drops sub-call additionalContext (no safe outlet
mid-run; pinned), owns a run-scoped abort that follows the outer signal in
and fires on settlement (in-flight sub-dispatch aborted, queued abandoned,
queue drained before returning), and converts a failed run into
CodeRunFailedError → a structured isError carrying kind + captured logs.
tool/code-dispatch joins SessionEventMap by declaration merging (log-only;
deriveMessages ignores it).

The composed surface: the tools config forwards through agent-core and
both app packages; examples/code-agent + demo:code run the worker runtime
under mode code (keyless boot smoke + a with-key e2e proving the collapsed
[run_code] header, the dispatch events, and the file the program wrote);
two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK
section, collapsed header, dispatch events, and result card — each its own
header-pinning class (the harness gains per-scenario config overlays and
per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the
RFC (moved to implemented/, restructured to decision-era headings) updated
in the same change.
2026-07-08 12:58:23 +08:00