mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
refactor(cli)!: one shared base config with per-surface overlays
`dsh` shipped two config trees that were 43 rows the same: apps/cli/cordis.yml composed web as 74 flat rows, while the TUI booted examples/tui-agent/cordis.yml whose single `@deepseek-ai/dsh-tui-demo` row mounted twelve plugins behind a twenty-key pass-through Config. Neither file was what its location claimed — apps/cli hardcoded the "example" as the product default and the "demo" bundle was the application — and every capability change had to be made twice. - apps/cli/base.cordis.yml holds the 43 shared rows; tui.cordis.yml and web.cordis.yml are patch lists stating only what differs per surface - overlays apply as SIBLING patch lists at one include level, because include patches never cross an include boundary. Precedence: base < surface < (--config | personal ~/.dsh/config.yaml) < launcher flag/profile patches - `--config` now applies an overlay INSTEAD OF the personal one, so a demo or test tree never inherits the user's route; new `--config-replace` boots a file as the entire tree (the old `--config` behaviour). Both survive /resume - vendor/include: index each `insert`ed row as it is added so a later patch can configure or disable it. Upstream built the id index once before the patch loop, leaving every surface-only row — the whole TUI front door — silently unpatchable from user config. Logged as local modification 8 - session identity moves to dsh-agent-loop's CONFIGURED_AGENT_IDENTITIES_KEY; dsh-tui's MAIN_SESSION_ID_KEY is deleted (only the bundle read it) - delete examples/tui-agent, examples/cordis-agent, packages/examples/tui-demo; TUI tests → apps/cli/tests, cordis e2e → packages/cordis/tool-cordis/tests, examples/code-mode survives as an overlay leaf - `dsh web` gains --config, threaded into AppCLIEntry as an extra overlay Three latent defects surfaced and are fixed here: the TUI captured the optional sessionQuery service once at construction and could permanently disable /resume when it won the mount race; the session-store root silently reverted to a project-local ./.sessions; --config-replace was dropped by the resume handoff. Verified by booting each tree through the real Loader (TUI 55 entries, web 75, zero unsettled) rather than reading YAML. All eight terminal snapshots replay byte-identically; 14/14 PTY smoke, 112/112 snapshots, 25/25 doc-sync, hygiene and lint clean.
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
llm-adapter.md: 3bf005647d3e7908f1d1553374266c1d6c12c2e6
|
||||
llm-adapter.zh.md: b967d112ed6879b11486ab7aedf64653089d93de
|
||||
# pnpm run verify-translation-pairing --write docs/user/develop/practice/llm-adapter.md
|
||||
llm-adapter.md: 7445688530c1ba61e5c065f9f5e49db6498da5b1
|
||||
llm-adapter.zh.md: c30200314a01f7a61d48e3f47288013c31e5aef4
|
||||
|
||||
@@ -133,10 +133,12 @@ The first argument lists the model names handled by the adapter. If `cordis.yml`
|
||||
- my-model-v1
|
||||
- my-model-v2
|
||||
|
||||
- id: tui-agent
|
||||
name: '@deepseek-ai/dsh-tui-demo'
|
||||
- id: agent-loop
|
||||
name: '@deepseek-ai/dsh-agent-loop'
|
||||
config:
|
||||
provider: my-llm
|
||||
agents:
|
||||
- id: main
|
||||
provider: my-llm
|
||||
model: my-model-v1 # References the model registered above.
|
||||
workspaceContext: false
|
||||
```
|
||||
|
||||
@@ -133,10 +133,12 @@ ctx.llm.registerAdapter(['model-name-1', 'model-name-2'], adapter)
|
||||
- my-model-v1
|
||||
- my-model-v2
|
||||
|
||||
- id: tui-agent
|
||||
name: '@deepseek-ai/dsh-tui-demo'
|
||||
- id: agent-loop
|
||||
name: '@deepseek-ai/dsh-agent-loop'
|
||||
config:
|
||||
provider: my-llm
|
||||
agents:
|
||||
- id: main
|
||||
provider: my-llm
|
||||
model: my-model-v1 # References the model registered above.
|
||||
workspaceContext: false
|
||||
```
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
config.md: a884cb9c2ec31bd4b12a31cce6290df1d134cf9a
|
||||
config.zh.md: 3fb9ce69e5f7cb6b92f055ef18595e5ff07d9bbf
|
||||
# pnpm run verify-translation-pairing --write docs/user/guide/config.md
|
||||
config.md: c9c760cbdb9650e608809fee4498b7f884b339dc
|
||||
config.zh.md: b80e31c6f77f51d013aaebe5c4e9e43f5819e33f
|
||||
|
||||
@@ -8,7 +8,7 @@ Harness uses `cordis.yml` to describe which plugins an agent loads and the confi
|
||||
|
||||
The repository examples are runnable configurations and the most reliable starting points for a new project:
|
||||
|
||||
- [tui-agent](../../../examples/tui-agent/cordis.yml) combines the DeepSeek model, Bash, filesystem, compaction, subagents, workflows, and the interactive TUI.
|
||||
- [the shared `dsh` base](../../../apps/cli/base.cordis.yml) plus the [`tui.cordis.yml`](../../../apps/cli/tui.cordis.yml) overlay combines the DeepSeek model, Bash, filesystem, compaction, subagents, workflows, and the interactive TUI.
|
||||
- [headless-agent](../../../examples/headless-agent/cordis.yml) exposes the coding composition as a one-shot task.
|
||||
- [acp-agent](../../../examples/acp-agent/cordis.yml) exposes fresh sessions to programmatic ACP clients.
|
||||
|
||||
@@ -25,12 +25,13 @@ A minimal configuration is a list of plugin entries:
|
||||
- id: bash
|
||||
name: '@deepseek-ai/dsh-bash-local'
|
||||
|
||||
- id: tui-agent
|
||||
name: '@deepseek-ai/dsh-tui-demo'
|
||||
- id: agent-loop
|
||||
name: '@deepseek-ai/dsh-agent-loop'
|
||||
config:
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
workspaceContext: false
|
||||
agents:
|
||||
- id: main
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
```
|
||||
|
||||
## Plugin entries
|
||||
|
||||
@@ -8,7 +8,7 @@ Harness 使用 `cordis.yml` 描述 Agent 加载哪些插件以及每个插件的
|
||||
|
||||
仓库中的示例就是可以运行的配置,也是新项目最可靠的起点:
|
||||
|
||||
- [tui-agent](../../../examples/tui-agent/cordis.yml) 组合 DeepSeek 模型、Bash、文件系统、压缩、子代理、工作流和交互式 TUI。
|
||||
- [共享的 `dsh` base](../../../apps/cli/base.cordis.yml) 叠加 [`tui.cordis.yml`](../../../apps/cli/tui.cordis.yml) overlay,组合 DeepSeek 模型、Bash、文件系统、压缩、子代理、工作流和交互式 TUI。
|
||||
- [headless-agent](../../../examples/headless-agent/cordis.yml) 以单次任务形式暴露 coding 组装。
|
||||
- [acp-agent](../../../examples/acp-agent/cordis.yml) 向程序化 ACP(Agent Client Protocol)客户端提供全新会话。
|
||||
|
||||
@@ -25,12 +25,13 @@ Harness 使用 `cordis.yml` 描述 Agent 加载哪些插件以及每个插件的
|
||||
- id: bash
|
||||
name: '@deepseek-ai/dsh-bash-local'
|
||||
|
||||
- id: tui-agent
|
||||
name: '@deepseek-ai/dsh-tui-demo'
|
||||
- id: agent-loop
|
||||
name: '@deepseek-ai/dsh-agent-loop'
|
||||
config:
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
workspaceContext: false
|
||||
agents:
|
||||
- id: main
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
```
|
||||
|
||||
## 插件条目
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
index.md: b698b8aeee6cebff374e20ca0f76ddc9e75213c0
|
||||
index.zh.md: 337d246baa12ccf6d7a9656d1ea3b06002554c13
|
||||
# pnpm run verify-translation-pairing --write docs/user/guide/index.md
|
||||
index.md: 72d822f6377089f56abda4383f393eed30a6709a
|
||||
index.zh.md: 442cda48072c3f6bf9579e880c0ab381b799966f
|
||||
|
||||
@@ -14,12 +14,17 @@ Harness implements every capability an AI agent needs—including LLM calls, too
|
||||
config:
|
||||
apiKey: !!js process.env.DEEPSEEK_API_KEY
|
||||
|
||||
# Select the interactive application
|
||||
- name: '@deepseek-ai/dsh-tui-demo'
|
||||
# Select the agent the interactive front door drives
|
||||
- id: agent-loop
|
||||
name: '@deepseek-ai/dsh-agent-loop'
|
||||
config:
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
workspaceContext: false
|
||||
agents:
|
||||
- id: main
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
|
||||
# Select the interactive front door
|
||||
- name: '@deepseek-ai/dsh-tui'
|
||||
```
|
||||
|
||||
## Who it is for
|
||||
|
||||
@@ -14,12 +14,17 @@ Harness 将一个 AI Agent(智能体) 所需要的所有能力——LLM 调
|
||||
config:
|
||||
apiKey: !!js process.env.DEEPSEEK_API_KEY
|
||||
|
||||
# Select the interactive application
|
||||
- name: '@deepseek-ai/dsh-tui-demo'
|
||||
# Select the agent the interactive front door drives
|
||||
- id: agent-loop
|
||||
name: '@deepseek-ai/dsh-agent-loop'
|
||||
config:
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
workspaceContext: false
|
||||
agents:
|
||||
- id: main
|
||||
provider: deepseek
|
||||
model: deepseek-v4-flash
|
||||
|
||||
# Select the interactive front door
|
||||
- name: '@deepseek-ai/dsh-tui'
|
||||
```
|
||||
|
||||
## 适合谁
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write
|
||||
quickstart.md: 25ce51ee3d010d2eb800071b9697fc62857dace1
|
||||
quickstart.zh.md: e2e023670a999566e273d8893c42103dc273e7b1
|
||||
# pnpm run verify-translation-pairing --write docs/user/guide/quickstart.md
|
||||
quickstart.md: 75c0d7096f09092106aca46a5a078673708040e7
|
||||
quickstart.zh.md: 0beadb65f32f21d18bb4550eda967ed2b275b10f
|
||||
|
||||
@@ -52,7 +52,7 @@ The full-screen agent can read and write files, run commands, delegate subtasks,
|
||||
|
||||
## What happened
|
||||
|
||||
headless-agent uses the `@deepseek-ai/dsh-cli-demo` app; tui-agent uses the interactive `@deepseek-ai/dsh-tui-demo` app. Both load the same providerless agent spine, while their `cordis.yml` files select the DeepSeek model and capability plugins appropriate to each surface.
|
||||
headless-agent uses the `@deepseek-ai/dsh-cli-demo` app; the interactive `dsh` surface instead composes [`apps/cli/base.cordis.yml`](../../../apps/cli/base.cordis.yml) with the `tui.cordis.yml` overlay and no app bundle. Both load the same providerless agent spine, while their `cordis.yml` files select the DeepSeek model and capability plugins appropriate to each surface.
|
||||
|
||||
## Next steps
|
||||
|
||||
|
||||
@@ -52,7 +52,7 @@ pnpm run demo:tui
|
||||
|
||||
## 回头看
|
||||
|
||||
headless-agent 使用 `@deepseek-ai/dsh-cli-demo` app,tui-agent 使用交互式 `@deepseek-ai/dsh-tui-demo` app。二者加载同一个 providerless agent spine,并通过各自的 `cordis.yml` 为对应 surface 选择 DeepSeek 模型和能力插件。
|
||||
headless-agent 使用 `@deepseek-ai/dsh-cli-demo` app;交互式 `dsh` surface 则以 [`apps/cli/base.cordis.yml`](../../../apps/cli/base.cordis.yml) 叠加 `tui.cordis.yml` overlay 组合而成,不使用 app 组合包。二者加载同一个 providerless agent spine,并通过各自的 `cordis.yml` 为对应 surface 选择 DeepSeek 模型和能力插件。
|
||||
|
||||
## 下一步
|
||||
|
||||
|
||||
Reference in New Issue
Block a user