|
|
@@ -1,125 +1,33 @@
|
|
|
-# Snapshot-test REPLAY config: the acp-agent plugin tree with the model backend
|
|
|
-# swapped to llm-replay (serves a recorded session JSONL — no API key, no
|
|
|
-# network). The dsh-acp-agent bin selects this file for DSH_SNAPSHOT=replay.
|
|
|
+# Snapshot-test REPLAY overlay: the SAME app tree as cordis.yml, derived from
|
|
|
+# it by an include — the one difference is the model backend. A keyless replay
|
|
|
+# run cannot boot the real adapter (llm-deepseek's apply() throws without
|
|
|
+# DEEPSEEK_API_KEY), so the include patches the live tree at load time: the
|
|
|
+# llm-deepseek entry is disabled by id, and the llm-replay entry (which serves
|
|
|
+# a recorded session JSONL — no API key, no network) is inserted. Every other
|
|
|
+# entry — the app, the bash executor, the fs/subagent/todo tools, both hook
|
|
|
+# bridges, the system prompt — IS the live tree, so replay exercises exactly
|
|
|
+# what ships and an app-shape change lands once, in cordis.yml.
|
|
|
#
|
|
|
-# Same app as cordis.yml (@deepseek-ai/dsh-acp-agent: the agent-core spine +
|
|
|
-# JSONL persistence + the ACP bridge) — only the LLM backend differs: llm-replay
|
|
|
-# here, llm-deepseek there. It can't reuse the real adapter because llm-deepseek's
|
|
|
-# apply() throws without DEEPSEEK_API_KEY, killing a keyless replay run at boot.
|
|
|
-#
|
|
|
-# stdout is reserved for the ACP JSON-RPC protocol — no stdout logger (the app
|
|
|
-# package omits it). The replay fixture path comes from $DSH_SNAPSHOT_FILE (and
|
|
|
-# an optional $DSH_SNAPSHOT_OVERRIDE sidecar), set by the snapshot harness.
|
|
|
-
|
|
|
-# The replay adapter: short-circuits llm/stream with the recorded log's chunks,
|
|
|
-# in place of llm-deepseek.
|
|
|
-- id: llm-replay
|
|
|
- name: '@deepseek-ai/dsh-llm-replay'
|
|
|
-
|
|
|
-# Local bash executor for agent-core's tool-bash schema.
|
|
|
-# FIXME(config-comments): keep this executor note from implying bash is the
|
|
|
-# whole tool set; filesystem, subagent, and todo_write are loaded below.
|
|
|
-- id: bash
|
|
|
- name: '@deepseek-ai/dsh-bash-local'
|
|
|
- config:
|
|
|
- timeoutMs: 60000
|
|
|
-
|
|
|
-# The ACP server app — identical to cordis.yml's entry.
|
|
|
-- id: acp-agent
|
|
|
- name: '@deepseek-ai/dsh-acp-agent'
|
|
|
- config:
|
|
|
- model: deepseek-v4-flash
|
|
|
- persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
|
|
|
- systemPrompt: |
|
|
|
- You are a coding assistant driven over the Agent Client Protocol.
|
|
|
-
|
|
|
- Your tools are read/write/edit for file operations, bash (plus
|
|
|
- bash_output/bash_kill for background tasks), and subagent. Use read to
|
|
|
- inspect UTF-8 text files, write to create or replace files, and edit for
|
|
|
- targeted literal replacements. Use bash for shell commands, tests,
|
|
|
- searches, and operations that are not ordinary file reads or edits. Each
|
|
|
- bash call runs in a fresh shell — pass workdir instead of cd. Check the
|
|
|
- [exit code: N] marker; verify your work. Keep answers brief and factual.
|
|
|
-
|
|
|
- Use the subagent tool to delegate a focused, self-contained subtask to
|
|
|
- a fresh child agent (it works in its own context and returns only its
|
|
|
- final result) — give it a complete, standalone instruction. Use
|
|
|
- subagent_fork instead when the subtask needs THIS conversation's
|
|
|
- context: the child inherits the log so far.
|
|
|
-
|
|
|
- For multi-step work, use the todo_write tool to track a task list:
|
|
|
- send the WHOLE list each call (it replaces the previous one), keep at
|
|
|
- most one task in_progress (exactly one while work remains), and mark a
|
|
|
- task completed as soon as it is done. Skip it for trivial single-step
|
|
|
- tasks.
|
|
|
-
|
|
|
-# The subagent seam + both in-process backends + two model-facing tools —
|
|
|
-# identical to cordis.yml's wiring (only the LLM backend differs above): spawn
|
|
|
-# and fork are each reachable via a dsh-tool-subagent bound to it with a distinct
|
|
|
-# toolName (subagent → spawn, subagent_fork → fork).
|
|
|
-- id: subagent
|
|
|
- name: '@deepseek-ai/dsh-subagent'
|
|
|
-
|
|
|
-- id: subagent-spawn
|
|
|
- name: '@deepseek-ai/dsh-subagent-spawn'
|
|
|
- config:
|
|
|
- providerName: spawn
|
|
|
-
|
|
|
-- id: subagent-fork
|
|
|
- name: '@deepseek-ai/dsh-subagent-fork'
|
|
|
- config:
|
|
|
- providerName: fork
|
|
|
-
|
|
|
-- id: tool-subagent
|
|
|
- name: '@deepseek-ai/dsh-tool-subagent'
|
|
|
- config:
|
|
|
- provider: spawn
|
|
|
- toolName: subagent
|
|
|
-
|
|
|
-- id: tool-subagent-fork
|
|
|
- name: '@deepseek-ai/dsh-tool-subagent'
|
|
|
- config:
|
|
|
- provider: fork
|
|
|
- toolName: subagent_fork
|
|
|
-
|
|
|
-# The model-facing todo_write tool — identical to cordis.yml's wiring, so a
|
|
|
-# replayed todo_write tool call resolves to a real tool during snapshot replay.
|
|
|
-- id: tool-todo
|
|
|
- name: '@deepseek-ai/dsh-tool-todo'
|
|
|
-
|
|
|
-# Filesystem capability stack — identical to cordis.yml's wiring, so replayed
|
|
|
-# read/write/edit tool calls resolve to the real tools during snapshot replay.
|
|
|
-- id: fs-local
|
|
|
- name: '@deepseek-ai/dsh-fs-local'
|
|
|
- config:
|
|
|
- cwd: !!js process.cwd()
|
|
|
-
|
|
|
-- id: fs-policy
|
|
|
- name: '@deepseek-ai/dsh-fs-policy'
|
|
|
-
|
|
|
-- id: tool-fs
|
|
|
- name: '@deepseek-ai/dsh-tool-fs'
|
|
|
-
|
|
|
-# The Claude Code hook bridge. `configPath` is read ONCE at load and resolves
|
|
|
-# `./hooks.json` against the PROCESS cwd (not per-session) — in these snapshot
|
|
|
-# runs the harness launches the subprocess with process cwd = the scenario's temp
|
|
|
-# workspace, so a scenario that ships `workspace/hooks.json` (copied into that cwd
|
|
|
-# before the run) exercises the hooks path end-to-end; every other scenario has no
|
|
|
-# such file, so the parse fails-soft and the bridge registers nothing (a silent
|
|
|
-# no-op — the ACP app loads no logger exporter, so the warning never reaches
|
|
|
-# stdout). Hooks themselves run in the session cwd (the bridge passes it as workdir).
|
|
|
-- id: hooks-claude
|
|
|
- name: '@deepseek-ai/dsh-hooks-claude'
|
|
|
- config:
|
|
|
- configPath: ./hooks.json
|
|
|
-
|
|
|
-# The Codex hook bridge, loaded alongside the Claude one (symmetric with
|
|
|
-# cordis.yml so a recorded Codex scenario fires the hook during recording too). It
|
|
|
-# reads its OWN file `./codex-hooks.json` (Codex's dialect) — the two bridges
|
|
|
-# cannot share one config. Same fails-soft-when-absent contract: a scenario that
|
|
|
-# ships `workspace/codex-hooks.json` exercises the Codex path end-to-end; a
|
|
|
-# scenario without one registers nothing (a silent no-op, never reaching stdout).
|
|
|
-- id: hooks-codex
|
|
|
- name: '@deepseek-ai/dsh-hooks-codex'
|
|
|
- config:
|
|
|
- configPath: ./codex-hooks.json
|
|
|
+# The dsh-acp-agent bin selects this file for DSH_SNAPSHOT=replay. The replay
|
|
|
+# fixture path comes from $DSH_SNAPSHOT_FILE (and an optional
|
|
|
+# $DSH_SNAPSHOT_OVERRIDE sidecar), set by the snapshot harness. stdout stays
|
|
|
+# reserved for the ACP JSON-RPC protocol (the app package loads no stdout
|
|
|
+# logger). Patches apply when the include loads the file — a one-shot replay
|
|
|
+# boot, so the load-time-only patch semantics are exactly enough.
|
|
|
+- id: base
|
|
|
+ name: '@cordisjs/plugin-include'
|
|
|
+ config:
|
|
|
+ path: ./cordis.yml
|
|
|
+ patches:
|
|
|
+ # The name is an assertion, not an override: the include skips the patch
|
|
|
+ # (warning if a logger exists) when the id points at a different plugin,
|
|
|
+ # so this can never disable the wrong entry. If cordis.yml ever RENAMES
|
|
|
+ # the id, the patch degrades to a skip — replay output stays correct
|
|
|
+ # (llm-replay still short-circuits the stream) but the stale patch and a
|
|
|
+ # futile keyless adapter entry linger until review catches them.
|
|
|
+ - id: llm-deepseek
|
|
|
+ name: '@deepseek-ai/dsh-llm-deepseek'
|
|
|
+ disabled: true
|
|
|
+ - insert:
|
|
|
+ - id: llm-replay
|
|
|
+ name: '@deepseek-ai/dsh-llm-replay'
|
Tianyi Cui