dsh-baton-mcp 0.6.1 → 0.6.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +135 -82
- package/README.zh-CN.md +125 -74
- package/host/README.md +4 -4
- package/host/package.json +2 -2
- package/package.json +1 -1
- package/server.json +2 -2
- package/src/codex-hook.mjs +159 -9
- package/src/mcp.mjs +16 -8
- package/src/register.mjs +34 -15
package/README.md
CHANGED
|
@@ -1,29 +1,62 @@
|
|
|
1
1
|
<p align="center">
|
|
2
|
-
<
|
|
2
|
+
English | <a href="README.zh-CN.md">中文</a> · macOS · Windows (<a href="WINDOWS.md">guide</a>) · no Node.js needed · zero dependencies · MIT
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
|
-
|
|
6
|
-
English | <a href="README.zh-CN.md">中文</a>
|
|
7
|
-
</p>
|
|
5
|
+
# dsh-baton
|
|
8
6
|
|
|
9
|
-
|
|
10
|
-
macOS · Windows (<a href="WINDOWS.md">guide</a>) · no Node.js needed · zero dependencies · MIT
|
|
11
|
-
</p>
|
|
7
|
+
Hand coding tasks from Claude Code or Codex to DeepSeek Harness on your machine: the task runs live in the Harness window, the main agent is woken when it ends, and it gets back the files that changed, the project's own test results and a requirement-by-requirement checklist.
|
|
12
8
|
|
|
13
|
-
|
|
9
|
+
- **Cheaper on big jobs:** with Claude Code, the total cost, DeepSeek included, is 51–78% lower.
|
|
10
|
+
- **Less of the 5-hour window:** on a long Codex job, a ChatGPT Plus 5-hour window goes from 86.01% used to 16.01% with GPT-6 Astra, and from 13.71% to 2.67% with GPT-6.1 Sol.
|
|
11
|
+
- **Nothing to watch or poll:** the agent is woken once when the run ends, and the result already holds the changed files, the test output and the requirement checklist.
|
|
14
12
|
|
|
15
|
-
|
|
13
|
+
Needs DeepSeek Harness ≥ 0.2.1-rc.2 (signed in) and Claude Code or Codex; macOS / Windows, zero dependencies. [Quick start →](#quick-start)
|
|
16
14
|
|
|
17
15
|
<p align="center">
|
|
18
|
-
<img src="./assets/readme/
|
|
16
|
+
<img src="./assets/readme/en/hero.gif" width="100%" alt="dsh-baton: pass the baton from Claude Code or Codex to DeepSeek Harness, watch it run live, and get it handed back when it's done">
|
|
19
17
|
</p>
|
|
20
18
|
|
|
19
|
+
## What it is
|
|
20
|
+
|
|
21
|
+
dsh-baton is an MCP server plus a small Harness plugin. Your main agent, Claude Code or Codex, writes the task and hands it over with one tool call. The task runs in a normal Harness session that you can watch, and step into, in the Harness window while it works. When it ends, the main agent is woken once instead of polling. It gets back evidence rather than a summary: which files were created, changed or deleted, the output of your project's own tests, and a point-by-point check against the request. Unlike a plain MCP bridge to another model, the work stays visible in the Harness UI and the proof comes back with the result.
|
|
22
|
+
|
|
23
|
+
## Quick start
|
|
24
|
+
|
|
21
25
|
<p align="center">
|
|
22
|
-
<img src="./assets/readme/
|
|
26
|
+
<img src="./assets/readme/en/install.svg" width="100%" alt="Step 1: in Harness open Plugins, Add plugin, enter dsh-baton-host, Install, Enable now; it registers dsh-baton for Claude Code and Codex. Step 2, Codex only, once: Settings, Hooks, trust dsh-baton: waiting for the Harness run. Step 3: in a new chat, ask for dsh_list_workspaces">
|
|
23
27
|
</p>
|
|
24
28
|
|
|
29
|
+
Nothing else to install: no Node.js, no terminal. The steps are the same on macOS and Windows.
|
|
30
|
+
|
|
31
|
+
**1. Add the plugin in Harness:** **Plugins** (插件) → **Add plugin** (添加插件) → type `dsh-baton-host` → **Install** (安装) → **Enable now** (立即启用).
|
|
32
|
+
|
|
33
|
+
Switched on, the plugin registers dsh-baton for Claude Code and Codex, for every folder, and Harness says so.
|
|
34
|
+
|
|
35
|
+
**2. Codex only, once:** Codex **Settings → Hooks** → **Trust** **dsh-baton: waiting for the Harness run**.
|
|
36
|
+
|
|
37
|
+
If the hook is not in the list yet, or you want to know what trusting it changes:
|
|
38
|
+
|
|
39
|
+
<details>
|
|
40
|
+
<summary>The Codex hook</summary>
|
|
41
|
+
|
|
42
|
+
The hook comes with plugin 0.6.0 and later (0.6.2 and later when you have no Node.js), and shows up in that list only after you restart Harness and then Codex once, after installing or updating the plugin. Node.js is not required: without one it runs on Harness's own runtime, like the server. Codex is then woken when a run ends instead of checking every 270 s. You trust it once: updates and Harness restarts do not ask again. Skip it and Codex waits with `dsh_wait` instead; the first hand-over reminds you.
|
|
43
|
+
|
|
44
|
+
</details>
|
|
45
|
+
|
|
46
|
+
**3. Check:** in a **new** Claude Code or Codex conversation, ask it to call `dsh_list_workspaces`. It lists your Harness workspaces. Codex asks you to approve MCP tool calls: approve the `dsh-baton` tools (for unattended `codex exec` runs, add `--approve-for-me`).
|
|
47
|
+
|
|
48
|
+
That is all. If Harness says it could not register, run `npx -y dsh-baton-mcp setup` in a terminal (this needs Node.js ≥ 22.15); it does the same registration. Updating, removing and Windows details are [further down](#install-details).
|
|
49
|
+
|
|
25
50
|
## See it run
|
|
26
51
|
|
|
52
|
+
*Claude Code and Codex each hand DeepSeek Harness a task, and its subagents build this rainy-night street in 1 h 41 min. 40 s, sound on.*
|
|
53
|
+
|
|
54
|
+
https://github.com/user-attachments/assets/72e2fdff-275e-48bc-8e5a-39ffb025a0a8
|
|
55
|
+
|
|
56
|
+
<p align="center">
|
|
57
|
+
<img src="./assets/readme/en/flow.gif" width="100%" alt="Typical flow: create a workspace, send the task, wait without polling (Claude Code and Codex are woken when the run ends), follow up in the same session">
|
|
58
|
+
</p>
|
|
59
|
+
|
|
27
60
|
One Codex chat starts a task, queues a follow-up, steers the running turn, and waits for all three:
|
|
28
61
|
|
|
29
62
|
<p align="center">
|
|
@@ -38,43 +71,83 @@ Codex and Claude take turns in the same Harness session, and every message is la
|
|
|
38
71
|
|
|
39
72
|
<p align="center"><a href="docs/demos.md">More demos →</a></p>
|
|
40
73
|
|
|
41
|
-
##
|
|
74
|
+
## Token usage
|
|
75
|
+
|
|
76
|
+
**In short: hand over the big, long jobs.** With Claude Code the total cost, DeepSeek included, is 51–78% lower. With Codex on GPT-6 Astra it is 47–81% lower, and the long kanban app takes 16.01% of a ChatGPT Plus 5-hour window instead of 86.01%.
|
|
77
|
+
|
|
78
|
+
**The three test tasks**, asked the way a user would (the requests are in Chinese, linked as written):
|
|
79
|
+
- **Task 1 · CLI tool:** a command-line task manager in Node, no dependencies, split into modules, with tests. [Request](docs/benchmarks/token-usage-2026-10/natural/medium.md)
|
|
80
|
+
- **Task 2 · Web app:** a task manager with a Node server and a page, REST API, stats, tests and a README. [Request](docs/benchmarks/token-usage-2026-10/natural/large.md)
|
|
81
|
+
- **Task 3 · Kanban app (phased):** a kanban board in plain Node and a plain front end, in three phases given one after another in the same conversation: ① the core (REST API, storage, drag and drop); ② labels, due dates, search syntax, archive, undo and redo, activity log, import and export; ③ version conflicts, WIP limits, bulk actions, live sync over SSE, stats. 55 acceptance tests written beforehand, the same for both arms. Requests: [phase 1](docs/benchmarks/token-usage-2026-10/xxl/seed/docs/phase1.md) · [phase 2](docs/benchmarks/token-usage-2026-10/xxl/seed/docs/phase2.md) · [phase 3](docs/benchmarks/token-usage-2026-10/xxl/seed/docs/phase3.md)
|
|
82
|
+
|
|
83
|
+
| Task 3 | Alone | Handed over |
|
|
84
|
+
|---|---|---|
|
|
85
|
+
| Opus 5.5 high | 55/55, 39 min | 55/55, 93 min |
|
|
86
|
+
| GPT-6.1 Sol high | 55/55, 18 min | 55/55, 101 min |
|
|
87
|
+
| GPT-6 Astra high | 55/55, about 31 min | 55/55, about 87 min |
|
|
88
|
+
|
|
89
|
+
Cost per task at list price, DeepSeek V4.1 Flash 1017 at its peak price. Opus 5.5 runs in Claude Code, GPT-6.1 Sol and GPT-6 Astra in Codex, all at high effort:
|
|
90
|
+
|
|
91
|
+
| Task | Model | Alone | Handed over: main agent | Handed over: DeepSeek | Handed over: total | Total | Main agent | 5-hour window, alone → handed over |
|
|
92
|
+
|---|---|---|---|---|---|---|---|---|
|
|
93
|
+
| Task 1 · CLI tool | Opus 5.5 high | $1.07 | $0.42 | $0.10 | $0.52 | −51.2% | −60.8% | — |
|
|
94
|
+
| | GPT-6.1 Sol high | $0.17 | $0.06 | $0.13 | $0.20 | +15.3% | −62.9% | 2.08% → 0.77% |
|
|
95
|
+
| | GPT-6 Astra high | $0.79 | $0.30 | $0.12 | $0.42 | −47.4% | −62.0% | 7.83% → 2.98% |
|
|
96
|
+
| Task 2 · Web app | Opus 5.5 high | $2.13 | $0.47 | $0.13 | $0.60 | −71.7% | −77.7% | — |
|
|
97
|
+
| | GPT-6.1 Sol high | $0.41 | $0.06 | $0.18 | $0.25 | −40.2% | −84.5% | 5.08% → 0.79% |
|
|
98
|
+
| | GPT-6 Astra high | $2.27 | $0.30 | $0.13 | $0.42 | −81.4% | −86.9% | 22.43% → 2.94% |
|
|
99
|
+
| Task 3 · Kanban app (phased) | Opus 5.5 high | $14.18 | $2.32 | $0.84 | $3.16 | −77.7% | −83.6% | — |
|
|
100
|
+
| | GPT-6.1 Sol high | $1.12 | $0.22 | $0.81 | $1.03 | −8.1% | −80.5% | 13.71% → 2.67% |
|
|
101
|
+
| | GPT-6 Astra high | $8.69 | $1.62 | $0.74 | $2.35 | −72.9% | −81.4% | 86.01% → 16.01% |
|
|
42
102
|
|
|
43
103
|
<p align="center">
|
|
44
|
-
<img src="./
|
|
104
|
+
<img src="./docs/benchmarks/token-usage-2026-10/charts/cost.svg" width="100%" alt="Cost per task in USD, working alone vs handed over, grouped by model. Opus 5.5 high: $1.07 vs $0.52, $2.13 vs $0.60, $14.18 vs $3.16. GPT-6.1 Sol high: $0.17 vs $0.20, $0.41 vs $0.25, $1.12 vs $1.03. GPT-6 Astra high: $0.79 vs $0.42, $2.27 vs $0.42, $8.69 vs $2.35">
|
|
45
105
|
</p>
|
|
46
106
|
|
|
47
|
-
|
|
107
|
+
<p align="center">
|
|
108
|
+
<img src="./docs/benchmarks/token-usage-2026-10/charts/quota.svg" width="100%" alt="Share of a ChatGPT Plus 5-hour window in Codex, working alone vs handed over, grouped by model. GPT-6.1 Sol high: 2.08% vs 0.77%, 5.08% vs 0.79%, 13.71% vs 2.67%. GPT-6 Astra high: 7.83% vs 2.98%, 22.43% vs 2.94%, 86.01% vs 16.01%">
|
|
109
|
+
</p>
|
|
48
110
|
|
|
49
|
-
**
|
|
111
|
+
**Hand it over:** big jobs, long jobs, and whenever the 5-hour window is running low. The main agent's own spend drops 61–87% on every task and model.
|
|
50
112
|
|
|
51
|
-
|
|
113
|
+
**Do it yourself:** small tasks on Codex with GPT-6.1 Sol. Sol is cheap enough that DeepSeek's part of a hand-over, two thirds or more, outweighs what Sol saves.
|
|
52
114
|
|
|
53
|
-
|
|
115
|
+
<details>
|
|
116
|
+
<summary>What was tested, and how</summary>
|
|
54
117
|
|
|
55
|
-
**
|
|
118
|
+
- **The only difference** in the hand-over runs is one line added at the end of the request: 交给 DeepSeek Harness 去做。 ("Hand it to DeepSeek Harness.")
|
|
119
|
+
- Same model and effort in both arms, and every run judged by the same acceptance check, which the model never sees.
|
|
120
|
+
- Tasks 1 and 2: the mean of three runs per cell. Task 3: one run per cell. Every run passed its acceptance check, with no rework.
|
|
121
|
+
- Prices are list prices. DeepSeek is counted at its peak price; the real DeepSeek bill came to about 58% of that.
|
|
122
|
+
- The 5-hour window share is worked out from each run's cost: 12.27 points per $1 for GPT-6.1 Sol, 9.90 for GPT-6 Astra.
|
|
123
|
+
- From 0.6.1 Codex is woken by its Stop hook instead of polling with `dsh_wait`, and 0.6.2 cuts the MCP instructions to one sentence, so Codex reads a few thousand to over ten thousand fewer new input tokens per hand-over.
|
|
56
124
|
|
|
57
|
-
|
|
125
|
+
</details>
|
|
58
126
|
|
|
59
127
|
## How it works
|
|
60
128
|
|
|
61
129
|
<p align="center">
|
|
62
|
-
<img src="./assets/readme/architecture.svg" width="100%" alt="MCP clients call dsh-baton-mcp over stdio; it reaches the dsh-baton-host plugin inside Harness through an owner-only local socket; the plugin drives Harness sessions live, with dsh headless as fallback">
|
|
130
|
+
<img src="./assets/readme/en/architecture.svg" width="100%" alt="MCP clients call dsh-baton-mcp over stdio; it reaches the dsh-baton-host plugin inside Harness through an owner-only local socket; the plugin drives Harness sessions live, with dsh headless as fallback">
|
|
63
131
|
</p>
|
|
64
132
|
|
|
65
133
|
<p align="center">
|
|
66
|
-
<img src="./assets/readme/comparison.svg" width="100%" alt="Plugin vs headless: only the plugin shows runs live in the Harness UI, continues desktop sessions and uses desktop agent presets; both reuse the desktop sign-in">
|
|
134
|
+
<img src="./assets/readme/en/comparison.svg" width="100%" alt="Plugin vs headless: only the plugin shows runs live in the Harness UI, continues desktop sessions and uses desktop agent presets; both reuse the desktop sign-in">
|
|
67
135
|
</p>
|
|
68
136
|
|
|
69
|
-
**
|
|
137
|
+
**Pick a model:** just say which one, for example "hand it to DeepSeek, V4 Pro". `dsh_send` passes it as `model` (and `reasoning_effort`), matched against the models Harness lists, so a model Harness adds later works as soon as it shows up. It applies to that session only; Harness's default model stays as it was. `dsh_list_models` shows what is available.
|
|
138
|
+
|
|
139
|
+
Nothing to configure for waiting; if you want to know what each client does while a run is going:
|
|
140
|
+
|
|
141
|
+
<details>
|
|
142
|
+
<summary>How each client waits</summary>
|
|
143
|
+
|
|
70
144
|
- **Claude Code** waits for a run in the background (the `wait_command` that `dsh_send` returns) and is woken once, when the run ends.
|
|
71
145
|
- **Codex** with the dsh-baton Stop hook trusted (from 0.6.1): after `dsh_send` it ends its turn; the hook waits for the run outside the model and, when the run ends or asks something, continues the same conversation with the result. One model request per run instead of one every 270 s.
|
|
72
146
|
- **Codex** without the hook waits inside `dsh_wait`, up to 270 s per call, just under its 300 s tool timeout. An unfinished wait returns only the state, so Codex calls again without summarising. Codex gets no `wait_command`: its terminal cannot wake it, so it would poll.
|
|
73
|
-
- Codex asks you to approve MCP tool calls: approve the `dsh-baton` tools. For unattended `codex exec` runs, add `--approve-for-me`.
|
|
74
147
|
|
|
75
|
-
|
|
148
|
+
</details>
|
|
76
149
|
|
|
77
|
-
|
|
150
|
+
### How a hand-over is checked
|
|
78
151
|
|
|
79
152
|
You don't have to take DeepSeek's word for it. Before the run, dsh-baton notes what is in the folder. When the run ends it shows exactly which files were created, changed or deleted, and runs your project's own tests itself (`npm test`, or whatever the client passes as `checks`). A second, read-only DeepSeek agent then goes through the request point by point and ends with a table: requirement, met or not, and where (file:line). Claude or GPT reads just that, sends anything missing back in one message, and opens code only where a row says "not met". Unless `cwd` names another folder, the new Harness session starts in the folder you're already working in.
|
|
80
153
|
|
|
@@ -82,61 +155,23 @@ You don't have to take DeepSeek's word for it. Before the run, dsh-baton notes w
|
|
|
82
155
|
<img src="./docs/benchmarks/token-usage-2026-10/charts/evidence-chain.svg" width="100%" alt="Evidence chain of one real hand-over: the user asks, Codex writes the spec and checks, dsh-baton snapshots the folder, DeepSeek Harness writes 11 files, dsh-baton lists the changed files and runs npm test itself, Codex sends one fix back on its own, dsh-baton checks again, Codex accepts, and the benchmark's own test passes 13 of 13">
|
|
83
156
|
</p>
|
|
84
157
|
|
|
85
|
-
## Token usage
|
|
86
|
-
|
|
87
|
-
**In short: hand over the big, long jobs.** A feature that spans many files, a large refactor, a whole small app: that is where it saves the most. Claude Code's own bill drops by 65–81%, and Codex gets 2 to 5 times as many tasks out of a ChatGPT Plus 5-hour window (5 times on a medium task with GPT-6 Astra).
|
|
88
|
-
|
|
89
|
-
**The honest part:** for small tasks, Codex on GPT-6.1 Sol is cheap enough that doing it alone costs less in total than handing it over, and at medium size it comes out about even. The hand-over pays off when you want Claude or GPT to plan and review, a cheaper model to do the typing, and you'd rather not keep hitting the 5-hour limit.
|
|
90
|
-
|
|
91
|
-
**Who this is for:** most of us pay for Claude or ChatGPT with a plan (Plus, Pro, Max 5x…), while DeepSeek is pay-as-you-go from a balance you top up, so every hand-over is money spent outside your plan. If your plan's limits already cover how you work, you don't need this: keep it simple and keep the money. If you're like me and keep running long, messy jobs with round after round of changes, and keep hitting the limit, a little DeepSeek spend gets you a lot more out of the plan you already pay for.
|
|
92
|
-
|
|
93
|
-
<p align="center">
|
|
94
|
-
<img src="./docs/benchmarks/token-usage-2026-10/charts/natural-combined.svg" width="100%" alt="Cost per task, working alone vs handed over (0.6.0; the large Astra task with 0.6.1): Claude Code (Opus 5.5) and Codex (GPT-6.1 Sol, GPT-6 Astra), each on its own scale">
|
|
95
|
-
</p>
|
|
96
|
-
|
|
97
|
-
Cost per task at list price, DeepSeek V4.1 Flash 1017 at its peak price:
|
|
98
|
-
|
|
99
|
-
| Client · model | Task | Alone | Handed over, client only | Handed over, with DeepSeek |
|
|
100
|
-
|---|---|---|---|---|
|
|
101
|
-
| Claude Code · Opus 5.5 high | Small | $1.07 | $0.37 (−65%) | $0.55 (−49%) |
|
|
102
|
-
| Claude Code · Opus 5.5 high | Medium | $2.13 | $0.41 (−81%) | $0.70 (−67%) |
|
|
103
|
-
| Codex · GPT-6.1 Sol high | Small | $0.17 | $0.09 (−49%) | $0.29 (+73%) |
|
|
104
|
-
| Codex · GPT-6.1 Sol high | Medium | $0.41 | $0.10 (−75%) | $0.41 (−2%) |
|
|
105
|
-
| Codex · GPT-6 Astra high | Small | $0.79 | $0.56 (−29%) | $0.75 (−6%) |
|
|
106
|
-
| Codex · GPT-6 Astra high | Medium | $2.27 | $0.48 (−79%) | $0.78 (−65%) |
|
|
107
|
-
|
|
108
|
-
<p align="center">
|
|
109
|
-
<img src="./docs/benchmarks/token-usage-2026-10/charts/natural-quota-combined.svg" width="80%" alt="Share of the ChatGPT Plus 5-hour window per task in Codex, working alone vs handed over with 0.6.0: GPT-6.1 Sol and GPT-6 Astra">
|
|
110
|
-
</p>
|
|
111
|
-
|
|
112
|
-
Share of the ChatGPT Plus 5-hour window per task: Sol small 1.9% → 0.8%, Sol medium 4.3% → 1.0%, Astra small 7% → 3.5%, Astra medium 22% → 4%.
|
|
113
|
-
|
|
114
|
-
<details>
|
|
115
|
-
<summary>What was tested, and how</summary>
|
|
116
|
-
|
|
117
|
-
- **Two tasks, asked the way a user would.** The small one takes Claude Code or Codex about 7–8 minutes on its own; the medium one is a small app with a server and a page. Long jobs beyond that were not measured. The requests are in Chinese, linked as written:
|
|
118
|
-
- Small: a command-line task manager in Node, no dependencies, split into modules, with tests. [Request](docs/benchmarks/token-usage-2026-10/natural/medium.md) · [acceptance check](docs/benchmarks/token-usage-2026-10/checks/natural-medium.mjs)
|
|
119
|
-
- Medium: a task manager web app, Node server plus page, REST API, stats, tests and a README. [Request](docs/benchmarks/token-usage-2026-10/natural/large.md) · [acceptance check](docs/benchmarks/token-usage-2026-10/checks/natural-large.mjs)
|
|
120
|
-
- **The only difference** in the hand-over runs is one line added at the end: 交给 DeepSeek Harness 去做。 ("Hand it to DeepSeek Harness.")
|
|
121
|
-
- Same model and effort in both arms, three runs per cell (Astra: one run each, two for the small hand-over), and every run judged by the same acceptance check, which the model never sees. All 12 hand-over runs passed it the first time.
|
|
122
|
-
- Prices are list prices. DeepSeek is counted at its peak price, the most conservative case; the real DeepSeek bill came to about 58% of that.
|
|
123
|
-
- Every run, the raw data and the scripts: [run log](docs/benchmarks/token-usage-2026-10/LOG.md) and [full report](docs/benchmarks/token-usage-2026-10.md).
|
|
124
|
-
|
|
125
|
-
</details>
|
|
126
|
-
|
|
127
158
|
## Tools
|
|
128
159
|
|
|
129
160
|
<p align="center">
|
|
130
|
-
<img src="./assets/readme/tools.svg" width="100%" alt="Ten tools in the tool list: list workspaces, list sessions, read session, list models, send, status, wait, answer, cancel, call. Six less used tools are reached through dsh_call: create and rename workspace, session activity, rename session, update queued, list runs">
|
|
161
|
+
<img src="./assets/readme/en/tools.svg" width="100%" alt="Ten tools in the tool list: list workspaces, list sessions, read session, list models, send, status, wait, answer, cancel, call. Six less used tools are reached through dsh_call: create and rename workspace, session activity, rename session, update queued, list runs">
|
|
131
162
|
</p>
|
|
132
163
|
|
|
133
164
|
<p align="center">
|
|
134
|
-
<img src="./assets/readme/states.svg" width="100%" alt="Run states: queued, running, waiting, completed, failed, cancelled, and interrupted when Harness restarts mid-run. A busy session takes followup (queued) or steer (interjects) messages">
|
|
165
|
+
<img src="./assets/readme/en/states.svg" width="100%" alt="Run states: queued, running, waiting, completed, failed, cancelled, and interrupted when Harness restarts mid-run. A busy session takes followup (queued) or steer (interjects) messages">
|
|
135
166
|
</p>
|
|
136
167
|
|
|
168
|
+
When you want the exact parameters and return fields of each tool:
|
|
169
|
+
|
|
137
170
|
<details>
|
|
138
171
|
<summary>Full tool reference</summary>
|
|
139
172
|
|
|
173
|
+
The server's MCP instructions are a single sentence (from 0.6.2); how to hand over, wait and answer is in each tool's own description. Codex repeats the instructions in front of every tool's description, so the catalogue it shows the model is now about 9.7k characters instead of 24.3k.
|
|
174
|
+
|
|
140
175
|
| Tool | What it does |
|
|
141
176
|
|---|---|
|
|
142
177
|
| `dsh_list_workspaces` | Workspaces in the Harness sidebar |
|
|
@@ -144,7 +179,7 @@ Share of the ChatGPT Plus 5-hour window per task: Sol small 1.9% → 0.8%, Sol m
|
|
|
144
179
|
| `dsh_list_sessions` | Sessions newest first, with title, folder, running state and `model` (what its next request uses); filter by folder or text. Archived sessions are left out |
|
|
145
180
|
| `dsh_list_models` | The models Harness can run (provider, id, name, reasoning efforts) and its default model |
|
|
146
181
|
| `dsh_read_session` | Recent prompts and replies of one session (with tool names); `archived: true` for an archived session |
|
|
147
|
-
| `dsh_send` | Send a message: `session_id` continues that session; otherwise a new one starts in `cwd` or `workspace_id`, or, with neither, in the folder the conversation works in (a `cwd` that is not a workspace yet is registered first; a `cwd` outside the conversation's folder is allowed and noted in `folder_note`). `checks`: test commands dsh-baton runs itself when the run ends (see How a hand-over is checked). Returns a `run_id` at once. In Harness the message is marked "Sent by Claude / ChatGPT from another chat". An archived session is refused: unarchive it in Harness, or start a new session. To a busy session, `mode` `followup` queues the message after the current turn and `steer` adds it to the running turn; left out, it does what Harness's own setting says (Settings → sending while busy: queue or steer), and `followup` when that cannot be read. `mode_source` says which applied. `model` only when the user names one ("DeepSeek-V4 Pro", "v4-pro"; `reasoning_effort` likewise): it is matched against Harness's own model list, ignoring case, spaces, hyphens and a leading DeepSeek, so a model Harness adds later (V4.1 Pro) works as soon as Harness lists it; a name that matches nothing or several fails the send, before anything is created, with the list (`provider/model` picks one). It is set on that session before the message goes in, and Harness's default model is put back as it was (Harness saves a session's pick as the default too). Left out, a continued session keeps its own model and a new one uses Harness's default. The reply says which in `model` and `model_source` |
|
|
182
|
+
| `dsh_send` | Send a message: `session_id` continues that session; otherwise a new one starts in `cwd` or `workspace_id`, or, with neither, in the folder the conversation works in (a `cwd` that is not a workspace yet is registered first; a `cwd` outside the conversation's folder is allowed and noted in `folder_note`). `checks`: test commands dsh-baton runs itself when the run ends (see [How a hand-over is checked](#how-a-hand-over-is-checked)). Returns a `run_id` at once. In Harness the message is marked "Sent by Claude / ChatGPT from another chat". An archived session is refused: unarchive it in Harness, or start a new session. To a busy session, `mode` `followup` queues the message after the current turn and `steer` adds it to the running turn; left out, it does what Harness's own setting says (Settings → sending while busy: queue or steer), and `followup` when that cannot be read. `mode_source` says which applied. `model` only when the user names one ("DeepSeek-V4 Pro", "v4-pro"; `reasoning_effort` likewise): it is matched against Harness's own model list, ignoring case, spaces, hyphens and a leading DeepSeek, so a model Harness adds later (V4.1 Pro) works as soon as Harness lists it; a name that matches nothing or several fails the send, before anything is created, with the list (`provider/model` picks one). It is set on that session before the message goes in, and Harness's default model is put back as it was (Harness saves a session's pick as the default too). Left out, a continued session keeps its own model and a new one uses Harness's default. The reply says which in `model` and `model_source` |
|
|
148
183
|
| `dsh_status` | Run progress: state, recent text and tool calls, final reply; `waiting_on` when the turn is over but sub-agents or jobs still run; `human_interjections` when someone typed in the Harness UI mid-run; state `interrupted` for a run cut short by a Harness restart; `model` the run was sent with |
|
|
149
184
|
| `dsh_wait` | Codex with the Stop hook trusted does not need it. Wait for the run to end; a finished run carries `evidence` (files changed, check results) when the message was sent with `checks` (or until it stops to ask a person, see `dsh_answer`): up to 270 s per call for Codex, 50 s for other clients. Still going: returns `timed_out` with just the state; call it again. Clients that can wait in the background use `dsh_send`'s `wait_command` instead. `dsh_status` is a one-off look, not a way to wait |
|
|
150
185
|
| `dsh_answer` | Answer the questions a run stopped to ask (Harness's ask_user_question): per question, an option number or label, free text, or skip; one at a time or all at once. `dsh_wait` and `wait_command` return as soon as a run asks, with the questions (`needs_input`, `question`; the option Harness's model would pick is in `harness_suggested`, apart from the labels). The assistant answers by its own judgment only when you told it to decide, and then passes `reason` and tells you what it chose and why; otherwise it brings you the questions, starting with its own recommendation and reason. You can also answer in the Harness window: whoever answers first wins |
|
|
@@ -158,7 +193,12 @@ Share of the ChatGPT Plus 5-hour window per task: Sol small 1.9% → 0.8%, Sol m
|
|
|
158
193
|
|
|
159
194
|
</details>
|
|
160
195
|
|
|
161
|
-
##
|
|
196
|
+
## Command line and configuration
|
|
197
|
+
|
|
198
|
+
When you want to drive Harness from a terminal or a script instead of a chat:
|
|
199
|
+
|
|
200
|
+
<details>
|
|
201
|
+
<summary>CLI commands</summary>
|
|
162
202
|
|
|
163
203
|
```bash
|
|
164
204
|
dsh-baton workspaces
|
|
@@ -175,13 +215,20 @@ dsh-baton rename session-xxxx "New title"
|
|
|
175
215
|
dsh-baton rename-workspace ~/code/new-app "New name"
|
|
176
216
|
```
|
|
177
217
|
|
|
178
|
-
|
|
218
|
+
(From source, use `node src/cli.mjs …`.)
|
|
219
|
+
|
|
220
|
+
</details>
|
|
221
|
+
|
|
222
|
+
When the defaults don't fit, for example a different socket path or forcing headless mode:
|
|
223
|
+
|
|
224
|
+
<details>
|
|
225
|
+
<summary>Environment variables</summary>
|
|
179
226
|
|
|
180
227
|
| Variable | Default | Meaning |
|
|
181
228
|
|---|---|---|
|
|
182
229
|
| `DSH_BATON_BACKEND` | `auto` | `auto`, `host` or `headless` |
|
|
183
230
|
| `DSH_BATON_HOME` | `~/.dsh-baton` | Socket and headless run records |
|
|
184
|
-
| `DSH_BATON_SOCKET` | `$DSH_BATON_HOME/host.sock` | Plugin socket path (must match on both sides); on Windows mapped to a per-user named pipe |
|
|
231
|
+
| `DSH_BATON_SOCKET` | `$DSH_BATON_HOME/host.sock` | Plugin socket path (must match on both sides); on Windows mapped to a per-user named pipe, see [WINDOWS.md](WINDOWS.md) |
|
|
185
232
|
| `DSH_BATON_WAIT_S` | `270` for Codex, else `50` | How long one `dsh_wait` call waits; set it only if you raised the client's tool timeout, and keep it below that |
|
|
186
233
|
| `DSH_BATON_CODEX_HOOK` | `1` | `0` (set for Harness) stops the plugin adding the Codex Stop hook |
|
|
187
234
|
| `DSH_BIN` | the `dsh` inside the macOS app, else `PATH` | Harness CLI for headless mode |
|
|
@@ -189,6 +236,10 @@ dsh-baton rename-workspace ~/code/new-app "New name"
|
|
|
189
236
|
| `DSH_BATON_ACCOUNT` | `1` | `0` uses the API-key route in headless mode |
|
|
190
237
|
| `DSH_BATON_PATCHES` | empty | Extra headless `--patch` overlays, `:`-separated |
|
|
191
238
|
|
|
239
|
+
</details>
|
|
240
|
+
|
|
241
|
+
When the Harness plugin is not reachable:
|
|
242
|
+
|
|
192
243
|
<details>
|
|
193
244
|
<summary>Headless fallback details</summary>
|
|
194
245
|
|
|
@@ -198,18 +249,20 @@ When the plugin is unreachable, the MCP server falls back to Harness's `dsh head
|
|
|
198
249
|
|
|
199
250
|
## Install details
|
|
200
251
|
|
|
252
|
+
When you update or remove the plugin, come from dsh-bridge, run from source, or the plugin could not register:
|
|
253
|
+
|
|
201
254
|
<details>
|
|
202
255
|
<summary>What the plugin does, updating, removing, upgrading from dsh-bridge, installing from source, Windows</summary>
|
|
203
256
|
|
|
204
257
|
**What the plugin does when switched on.** It copies the MCP server to `~/.dsh-baton/app`, a folder that stays put, and writes the MCP entry into `~/.claude.json` and `~/.codex/config.toml` directly, keeping a `*.bak-dsh-baton` backup of each. It starts the server with your own Node.js ≥ 22.15 when it finds one on `PATH`; without one, with Harness's own runtime (the Harness app in Node mode, `ELECTRON_RUN_AS_NODE=1`), so nothing else has to be installed. Either way it works with only the desktop apps installed, when `claude` / `codex` are not on your `PATH`. It runs again on each Harness start: an entry that is already right, or a working one that starts another copy of dsh-baton, is left alone. In Harness, the source switches to the npm registry ("Official npm registry", 「npm 官方源」) by itself once you type the package name, and no restart is needed. To turn the registration off, set `DSH_BATON_AUTO_REGISTER=0` for Harness.
|
|
205
258
|
|
|
206
|
-
**The Codex Stop hook.** The plugin adds one `[[hooks.Stop]]` block, marked `# dsh-baton`, to `~/.codex/config.toml`; Codex shows it as **dsh-baton: waiting for the Harness run** and runs it only once you trust it (dsh-baton never trusts it for you). The block only names a small script, `~/.dsh-baton/bin/codex-stop-hook` (`codex-stop-hook.cmd` on Windows), and everything that can move, Node.js and the server, lives in that script. So the block itself never changes: updates, same-version refreshes and Harness restarts leave it as it is, and your trust stays. If the block is ever rewritten, dsh-baton drops the old trust record, and Codex asks you to trust it again. Windows uses a `.cmd` because Codex runs hooks through `PowerShell -Command`, which cannot start a quoted program path.
|
|
259
|
+
**The Codex Stop hook.** The plugin adds one `[[hooks.Stop]]` block, marked `# dsh-baton`, to `~/.codex/config.toml`; Codex shows it as **dsh-baton: waiting for the Harness run** and runs it only once you trust it (dsh-baton never trusts it for you). The block only names a small script, `~/.dsh-baton/bin/codex-stop-hook` (`codex-stop-hook.cmd` on Windows), and everything that can move, Node.js and the server, lives in that script. So the block itself never changes: updates, same-version refreshes and Harness restarts leave it as it is, and your trust stays. If the block is ever rewritten, dsh-baton drops the old trust record, and Codex asks you to trust it again. Windows uses a `.cmd` because Codex runs hooks through `PowerShell -Command`, which cannot start a quoted program path. Without a Node.js of your own, the script runs Harness's own app in Node mode (`ELECTRON_RUN_AS_NODE=1`), as the server does; the plugin rewrites it on each start, so it follows Harness updates. Not added without Codex, with `DSH_BATON_CODEX_HOOK=0`, or when Codex's dsh-baton entry names no server folder (a bare `npx` command); the first hand-over in a Codex conversation then says why. `dsh-baton setup --codex-hook` adds it by hand, `setup --remove` takes it out, `DSH_BATON_CODEX_HOOK=0` for Harness stops the plugin adding it.
|
|
207
260
|
|
|
208
|
-
**Updates need no restart.** When a newer version lands in `~/.dsh-baton/app` (a plugin update, `setup`, or a copy by hand), or the same version with changed files, conversations already open in Claude Code and Codex use it from their next `dsh_*` call: the server checks the folder before each call, starts the new version, and says once in that call's result that it was updated. A `dsh_wait` that is already running finishes on the old version first. If the new version cannot start, the old one keeps working and the result says why. A tool added in the new version shows up in Claude Code at once (the server tells the client its tool list changed); Codex keeps the tool list a conversation started with, so it does not show a new tool until the next conversation;
|
|
261
|
+
**Updates need no restart.** When a newer version lands in `~/.dsh-baton/app` (a plugin update, `setup`, or a copy by hand), or the same version with changed files, conversations already open in Claude Code and Codex use it from their next `dsh_*` call: the server checks the folder before each call, starts the new version, and says once in that call's result that it was updated. A `dsh_wait` that is already running finishes on the old version first. If the new version cannot start, the old one keeps working and the result says why. A tool added in the new version shows up in Claude Code at once (the server tells the client its tool list changed); Codex keeps the tool list a conversation started with, so it does not show a new tool until the next conversation; it can still use one at once through `dsh_call`, which the update note points to, and the tools it already has run the new code right away.
|
|
209
262
|
|
|
210
263
|
**`npx -y dsh-baton-mcp setup`** does the same registration from a terminal: for a plugin that could not register, or when you come from an MCP directory. With the plugin already registered it changes nothing, then points you to the plugin if it is missing.
|
|
211
264
|
|
|
212
|
-
**Updating.** Harness has an update button only for its official plugins, so: Plugins → dsh-baton-host → **Uninstall**, then **Add plugin** → `dsh-baton-host`. For a while after a release, Harness installs the previous version instead (pnpm's `minimumReleaseAge` holds back versions published very recently, and the install dialog says so); to get the new one at once, type the version: `dsh-baton-host@0.6.
|
|
265
|
+
**Updating.** Harness has an update button only for its official plugins, so: Plugins → dsh-baton-host → **Uninstall**, then **Add plugin** → `dsh-baton-host`. For a while after a release, Harness installs the previous version instead (pnpm's `minimumReleaseAge` holds back versions published very recently, and the install dialog says so); to get the new one at once, type the version: `dsh-baton-host@0.6.2`. A pre-release must always be added by its exact version, such as `dsh-baton-host@0.6.0-next.0`: Harness resolves `@next` to a broken placeholder. Plain `dsh-baton-host` gets the latest release. Switched on again, the plugin brings the MCP server to the same version; new conversations use it. If the two are ever out of step, the first tool call that notices it says so, naming the older side and the newer side's exact version to install.
|
|
213
266
|
|
|
214
267
|
**Removing.** Harness → Plugins → dsh-baton-host → **Uninstall**, then `npx -y dsh-baton-mcp setup --remove`. The plugin cannot tell an uninstall from Harness quitting, so it leaves the MCP entries to that command, which also deletes `~/.dsh-baton/app`; run records stay in `~/.dsh-baton` until you delete it.
|
|
215
268
|
|
|
@@ -219,6 +272,10 @@ When the plugin is unreachable, the MCP server falls back to Harness's `dsh head
|
|
|
219
272
|
|
|
220
273
|
**Windows.** Same steps; [WINDOWS.md](WINDOWS.md) covers what differs (a named pipe instead of a socket file) and fixes for a Plugins page that cannot install or uninstall.
|
|
221
274
|
|
|
275
|
+
</details>
|
|
276
|
+
|
|
277
|
+
When you register by hand, or want dsh-baton in the Claude desktop chat app (not Claude Code):
|
|
278
|
+
|
|
222
279
|
<details>
|
|
223
280
|
<summary>Manual registration and the Claude desktop app</summary>
|
|
224
281
|
|
|
@@ -239,22 +296,18 @@ codex mcp add dsh-baton -- "$(command -v node)" "$PWD/dsh-baton/src/server.mjs"
|
|
|
239
296
|
|
|
240
297
|
</details>
|
|
241
298
|
|
|
242
|
-
</details>
|
|
243
|
-
|
|
244
299
|
## Security and limits
|
|
245
300
|
|
|
246
301
|
<p align="center">
|
|
247
|
-
<img src="./assets/readme/security.svg" width="100%" alt="Owner-only channel (socket 0600 on macOS and Linux, per-user named pipe on Windows), no network port, Harness sandbox and approvals apply">
|
|
302
|
+
<img src="./assets/readme/en/security.svg" width="100%" alt="Owner-only channel (socket 0600 on macOS and Linux, per-user named pipe on Windows), no network port, Harness sandbox and approvals apply">
|
|
248
303
|
</p>
|
|
249
304
|
|
|
250
305
|
<p align="center">
|
|
251
|
-
<img src="./assets/readme/limits.svg" width="100%" alt="Good to know: a message typed in the UI mid-run is flagged on the run as a human interjection, run records survive a Harness restart (cut-short runs show interrupted), Claude Code and Codex are woken once when a run ends">
|
|
306
|
+
<img src="./assets/readme/en/limits.svg" width="100%" alt="Good to know: a message typed in the UI mid-run is flagged on the run as a human interjection, run records survive a Harness restart (cut-short runs show interrupted), Claude Code and Codex are woken once when a run ends">
|
|
252
307
|
</p>
|
|
253
308
|
|
|
254
309
|
Any process running as your OS user can drive Harness through the socket, the same as running `dsh` directly. dsh-baton relies on Harness 0.2.1-series internal service APIs, so a major Harness update may need a follow-up release.
|
|
255
310
|
|
|
256
|
-
<p align="center"><a href="docs/demos.md">More demos →</a></p>
|
|
257
|
-
|
|
258
311
|
## License
|
|
259
312
|
|
|
260
313
|
MIT
|
package/README.zh-CN.md
CHANGED
|
@@ -1,29 +1,62 @@
|
|
|
1
1
|
<p align="center">
|
|
2
|
-
<
|
|
2
|
+
<a href="README.md">English</a> | 中文 · macOS · Windows（<a href="WINDOWS.md">说明</a>）· 不用装 Node.js · 零依赖 · MIT
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
5
|
+
# dsh-baton
|
|
6
|
+
|
|
7
|
+
把 Claude Code 或 Codex 的编码任务交给本机的 DeepSeek Harness：任务在 Harness 界面里实时跑，跑完自动唤醒主 Agent，并带回改了哪些文件、项目自己的测试结果，以及逐条需求对照表。
|
|
8
|
+
|
|
9
|
+
- **大任务更省**：Claude Code 连 DeepSeek 一起算，总花费少 51–78%。
|
|
10
|
+
- **少用 5 小时额度**：Codex 长任务，ChatGPT Plus 5 小时额度用 GPT-6 Astra 从 86.01% 降到 16.01%，用 GPT-6.1 Sol 从 13.71% 降到 2.67%。
|
|
11
|
+
- **不用盯、不用轮询**：跑完只唤醒一次，结果自带改动文件、测试输出和需求对照。
|
|
12
|
+
|
|
13
|
+
需要 DeepSeek Harness ≥ 0.2.1-rc.2（已登录）和 Claude Code 或 Codex；macOS / Windows，零依赖。[快速上手 →](#快速上手)
|
|
8
14
|
|
|
9
15
|
<p align="center">
|
|
10
|
-
|
|
16
|
+
<img src="./assets/readme/zh/hero.gif" width="100%" alt="dsh-baton：让 Claude Code 或 Codex 把接力棒交给 DeepSeek Harness，界面实时可见，跑完那一刻就交回给你">
|
|
11
17
|
</p>
|
|
12
18
|
|
|
13
|
-
|
|
19
|
+
## 这是什么
|
|
14
20
|
|
|
15
|
-
|
|
21
|
+
dsh-baton 是一个 MCP 服务器加一个 Harness 小插件。主 Agent（Claude Code 或 Codex）写好任务，用一次工具调用交出去。任务在一个普通的 Harness 对话里跑，你可以在 Harness 界面里实时看着，也可以随时插话。跑完时主 Agent 只被唤醒一次，不用轮询。它拿回的是证据而不是一段总结：新建、修改、删除了哪些文件，项目自己的测试输出，以及对照需求的逐条检查。和普通的 MCP 桥接另一个模型相比，区别在于整个过程在 Harness 界面里看得见，证据随结果一起带回来。
|
|
22
|
+
|
|
23
|
+
## 快速上手
|
|
16
24
|
|
|
17
25
|
<p align="center">
|
|
18
|
-
<img src="./assets/readme/zh/
|
|
26
|
+
<img src="./assets/readme/zh/install.svg" width="100%" alt="第一步：Harness → 插件 → 添加插件 → 输入 dsh-baton-host → 安装 → 立即启用，它会为 Claude Code 和 Codex 注册 dsh-baton。第二步（仅 Codex，一次）：设置 → 钩子 → 信任 dsh-baton: waiting for the Harness run。第三步：新开对话，让它调用 dsh_list_workspaces">
|
|
19
27
|
</p>
|
|
20
28
|
|
|
29
|
+
别的都不用装：不用 Node.js，也不用开终端。macOS 和 Windows 步骤完全相同。
|
|
30
|
+
|
|
31
|
+
**1. 在 Harness 里添加插件：** 插件 → 添加插件 → 输入 `dsh-baton-host` → 安装 → 立即启用。
|
|
32
|
+
|
|
33
|
+
插件启用后会为 Claude Code 和 Codex 注册 dsh-baton（对所有文件夹生效），Harness 里会弹出提示。
|
|
34
|
+
|
|
35
|
+
**2. 仅 Codex，只需一次**：Codex **设置 → 钩子（Hooks）** → **信任** **dsh-baton: waiting for the Harness run**。
|
|
36
|
+
|
|
37
|
+
列表里还没有这个钩子，或者想知道信任它会改变什么时，展开看：
|
|
38
|
+
|
|
39
|
+
<details>
|
|
40
|
+
<summary>Codex 钩子</summary>
|
|
41
|
+
|
|
42
|
+
钩子要插件 0.6.0 以上才有（没有 Node.js 时要 0.6.2 以上）；装好或更新插件后，先重启一次 Harness，再重启一次 Codex，它才会出现在这个列表里。不需要 Node.js：没有的话它和服务器一样用 Harness 自带运行环境。之后 Codex 在任务跑完时会被自动唤醒，不用再每 270 秒查一次。只需信任一次：以后升级、热更新、重启 Harness 都不用再信任。不信任也能用，Codex 会改用 `dsh_wait` 等，第一次交接时会提醒你。
|
|
43
|
+
|
|
44
|
+
</details>
|
|
45
|
+
|
|
46
|
+
**3. 检查**：在 Claude Code 或 Codex 里**新开**一个对话，让它调用 `dsh_list_workspaces`，会列出你的 Harness 工作区。Codex 调用 MCP 工具时会请你批准，批准 `dsh-baton` 的工具即可（无人值守的 `codex exec` 加上 `--approve-for-me`）。
|
|
47
|
+
|
|
48
|
+
就这些。如果 Harness 提示没能注册，在终端运行 `npx -y dsh-baton-mcp setup`（这需要 Node.js ≥ 22.15），它做的是同样的注册。更新、卸载和 Windows 说明在[后面](#安装细节)。
|
|
49
|
+
|
|
50
|
+
## 看它跑
|
|
51
|
+
|
|
52
|
+
*Claude Code 和 Codex 各派一个任务给 DeepSeek Harness，它的子代理用 1 小时 41 分搭出了这条雨夜街道。40 秒，建议开声音。*
|
|
53
|
+
|
|
54
|
+
https://github.com/user-attachments/assets/ed931637-acb3-4c16-8c52-72298ea90485
|
|
55
|
+
|
|
21
56
|
<p align="center">
|
|
22
57
|
<img src="./assets/readme/zh/flow.gif" width="100%" alt="典型流程：新建工作区、派发任务、不轮询地等待（Claude Code 和 Codex 在运行结束时被唤醒）、在同一个对话里续接追问">
|
|
23
58
|
</p>
|
|
24
59
|
|
|
25
|
-
## 实际演示
|
|
26
|
-
|
|
27
60
|
一个 Codex 对话里完成新建、排队、插队和等待：
|
|
28
61
|
|
|
29
62
|
<p align="center">
|
|
@@ -38,23 +71,58 @@ Codex 和 Claude 轮流往同一个 Harness 对话发消息，每条都标明是
|
|
|
38
71
|
|
|
39
72
|
<p align="center"><a href="docs/demos.zh-CN.md">更多演示 →</a></p>
|
|
40
73
|
|
|
41
|
-
##
|
|
74
|
+
## Token 用量实测
|
|
75
|
+
|
|
76
|
+
**一句话：大活、长活交给它**。Claude Code 连 DeepSeek 一起算，总花费少 51–78%；Codex 用 GPT-6 Astra 少 47–81%，分阶段的看板应用占 ChatGPT Plus 5 小时额度从 86.01% 降到 16.01%。
|
|
77
|
+
|
|
78
|
+
**三个测试案例**，都按普通用户的口吻提需求（原文可以直接点开看）：
|
|
79
|
+
- **案例 1 · 命令行工具**：用 Node 写一个命令行任务管理工具，零依赖，分模块，带测试。[需求原文](docs/benchmarks/token-usage-2026-10/natural/medium.md)
|
|
80
|
+
- **案例 2 · 任务管理网页**：Node 服务器加前端页面，REST 接口、统计、测试和 README。[需求原文](docs/benchmarks/token-usage-2026-10/natural/large.md)
|
|
81
|
+
- **案例 3 · 看板应用（分阶段）**：只用 Node 内置模块和原生前端的看板应用，三个阶段在同一个对话里依次给：① 主体（REST 接口、持久化、前端拖拽）；② 标签、截止日期、搜索语法、归档、撤销重做、活动日志、导入导出；③ 版本冲突检测、WIP 上限、批量操作、SSE 实时同步、统计。事先写好 55 项验收测试，两组用同一套。需求原文：[阶段 1](docs/benchmarks/token-usage-2026-10/xxl/seed/docs/phase1.md) · [阶段 2](docs/benchmarks/token-usage-2026-10/xxl/seed/docs/phase2.md) · [阶段 3](docs/benchmarks/token-usage-2026-10/xxl/seed/docs/phase3.md)
|
|
82
|
+
|
|
83
|
+
| 案例 3 | 自己做 | 转交 |
|
|
84
|
+
|---|---|---|
|
|
85
|
+
| Opus 5.5 high | 55/55，39 分钟 | 55/55，93 分钟 |
|
|
86
|
+
| GPT-6.1 Sol high | 55/55，18 分钟 | 55/55，101 分钟 |
|
|
87
|
+
| GPT-6 Astra high | 55/55，约 31 分钟 | 55/55，约 87 分钟 |
|
|
88
|
+
|
|
89
|
+
每个任务的花费，按标价计，DeepSeek V4.1 Flash 1017 按高峰价。Opus 5.5 跑在 Claude Code 里，GPT-6.1 Sol 和 GPT-6 Astra 跑在 Codex 里，推理强度都是 high：
|
|
90
|
+
|
|
91
|
+
| 案例 | 模型 | 自己做 | 转交：主 Agent | 转交：DeepSeek | 转交合计 | 合计变化 | 主 Agent 变化 | 5 小时额度，自己做 → 转交 |
|
|
92
|
+
|---|---|---|---|---|---|---|---|---|
|
|
93
|
+
| 案例 1 · 命令行工具 | Opus 5.5 high | $1.07 | $0.42 | $0.10 | $0.52 | −51.2% | −60.8% | — |
|
|
94
|
+
| | GPT-6.1 Sol high | $0.17 | $0.06 | $0.13 | $0.20 | +15.3% | −62.9% | 2.08% → 0.77% |
|
|
95
|
+
| | GPT-6 Astra high | $0.79 | $0.30 | $0.12 | $0.42 | −47.4% | −62.0% | 7.83% → 2.98% |
|
|
96
|
+
| 案例 2 · 任务管理网页 | Opus 5.5 high | $2.13 | $0.47 | $0.13 | $0.60 | −71.7% | −77.7% | — |
|
|
97
|
+
| | GPT-6.1 Sol high | $0.41 | $0.06 | $0.18 | $0.25 | −40.2% | −84.5% | 5.08% → 0.79% |
|
|
98
|
+
| | GPT-6 Astra high | $2.27 | $0.30 | $0.13 | $0.42 | −81.4% | −86.9% | 22.43% → 2.94% |
|
|
99
|
+
| 案例 3 · 看板应用（分阶段） | Opus 5.5 high | $14.18 | $2.32 | $0.84 | $3.16 | −77.7% | −83.6% | — |
|
|
100
|
+
| | GPT-6.1 Sol high | $1.12 | $0.22 | $0.81 | $1.03 | −8.1% | −80.5% | 13.71% → 2.67% |
|
|
101
|
+
| | GPT-6 Astra high | $8.69 | $1.62 | $0.74 | $2.35 | −72.9% | −81.4% | 86.01% → 16.01% |
|
|
42
102
|
|
|
43
103
|
<p align="center">
|
|
44
|
-
<img src="./
|
|
104
|
+
<img src="./docs/benchmarks/token-usage-2026-10/charts/cost.zh.svg" width="100%" alt="每个任务花了多少钱（美元），自己做对转交，按模型分组。Opus 5.5 high：$1.07 对 $0.52，$2.13 对 $0.60，$14.18 对 $3.16。GPT-6.1 Sol high：$0.17 对 $0.20，$0.41 对 $0.25，$1.12 对 $1.03。GPT-6 Astra high：$0.79 对 $0.42，$2.27 对 $0.42，$8.69 对 $2.35">
|
|
45
105
|
</p>
|
|
46
106
|
|
|
47
|
-
|
|
107
|
+
<p align="center">
|
|
108
|
+
<img src="./docs/benchmarks/token-usage-2026-10/charts/quota.zh.svg" width="100%" alt="Codex 占 ChatGPT Plus 5 小时额度，自己做对转交，按模型分组。GPT-6.1 Sol high：2.08% 对 0.77%，5.08% 对 0.79%，13.71% 对 2.67%。GPT-6 Astra high：7.83% 对 2.98%，22.43% 对 2.94%，86.01% 对 16.01%">
|
|
109
|
+
</p>
|
|
48
110
|
|
|
49
|
-
|
|
111
|
+
**适合转交**：大任务、长任务，以及 5 小时额度快用完的时候。每个案例、每个模型，主 Agent 自己的花费都少了 61–87%。
|
|
50
112
|
|
|
51
|
-
|
|
113
|
+
**适合自己做**：Codex 用 GPT-6.1 Sol 的小任务。Sol 本身够便宜，转交时 DeepSeek 那部分要占到三分之二以上，抵掉了 Sol 省下的钱。
|
|
52
114
|
|
|
53
|
-
|
|
115
|
+
<details>
|
|
116
|
+
<summary>测了什么、怎么测的</summary>
|
|
54
117
|
|
|
55
|
-
|
|
118
|
+
- **转交组唯一的区别**，是在需求末尾多一句：交给 DeepSeek Harness 去做。
|
|
119
|
+
- 两组用同一个模型、同样的推理强度；每次都用同一套验收脚本检查，模型看不到这个脚本。
|
|
120
|
+
- 案例 1、2：每格 3 次取平均。案例 3：每格 1 次。全部通过验收，没有返工。
|
|
121
|
+
- 价格按标价算。DeepSeek 按高峰价；实际 DeepSeek 账单大约是这个数的 58%。
|
|
122
|
+
- 5 小时额度按每次运行的花费换算：GPT-6.1 Sol 每 $1 合 12.27 个百分点，GPT-6 Astra 合 9.90 个。
|
|
123
|
+
- 0.6.1 起 Codex 由 Stop 钩子唤醒，不再用 `dsh_wait` 轮询；0.6.2 把 MCP 说明缩成一句话，Codex 每次转交少读几千到一万多个新输入 token。
|
|
56
124
|
|
|
57
|
-
|
|
125
|
+
</details>
|
|
58
126
|
|
|
59
127
|
## 工作原理
|
|
60
128
|
|
|
@@ -66,15 +134,20 @@ Codex 和 Claude 轮流往同一个 Harness 对话发消息，每条都标明是
|
|
|
66
134
|
<img src="./assets/readme/zh/comparison.svg" width="100%" alt="插件和 headless 对比：只有插件能在 Harness 界面实时可见、续接桌面版的对话、使用桌面版智能体预设；两者都沿用桌面版登录">
|
|
67
135
|
</p>
|
|
68
136
|
|
|
69
|
-
|
|
137
|
+
**指定模型**：直接说用哪个就行，比如「交给 DeepSeek，用 V4 Pro」。`dsh_send` 会把它作为 `model`（以及 `reasoning_effort`）传过去，按 Harness 自己的模型列表匹配，所以 Harness 以后新加的模型一出现就能用。只对这个对话生效，Harness 的默认模型保持不变。`dsh_list_models` 可以看有哪些模型。
|
|
138
|
+
|
|
139
|
+
等待不需要任何配置；想知道任务跑着时各客户端在做什么，展开看：
|
|
140
|
+
|
|
141
|
+
<details>
|
|
142
|
+
<summary>各客户端怎么等待</summary>
|
|
143
|
+
|
|
70
144
|
- **Claude Code** 在后台等待任务（`dsh_send` 返回的 `wait_command`），任务结束时只被唤醒一次。
|
|
71
145
|
- **Codex**（0.6.1 起）信任了 dsh-baton 的 Stop 钩子后：`dsh_send` 之后直接结束这一轮；钩子在模型之外等任务，任务结束或停下来提问时，带着结果继续同一个对话。每个任务只唤醒模型一次，而不是每 270 秒一次。
|
|
72
146
|
- **Codex** 没有钩子时在 `dsh_wait` 里等待，每次最多 270 秒，刚好低于它 300 秒的工具超时。没做完时只返回状态，Codex 会直接再调用，不会去总结进度。Codex 不会收到 `wait_command`：它的终端无法在命令结束时唤醒它，只能轮询。
|
|
73
|
-
- Codex 调用 MCP 工具时会请你批准，批准 `dsh-baton` 的工具即可；无人值守的 `codex exec` 加上 `--approve-for-me`。
|
|
74
147
|
|
|
75
|
-
|
|
148
|
+
</details>
|
|
76
149
|
|
|
77
|
-
|
|
150
|
+
### 转交之后怎么验收
|
|
78
151
|
|
|
79
152
|
不用光听 DeepSeek 自己说做完了。运行前，dsh-baton 先记下文件夹里有什么；运行结束后，它会列出到底新建、修改、删除了哪些文件，并亲自跑一遍项目自己的测试（`npm test`，或者客户端在 `checks` 里给的命令）。接着，另一个只读的 DeepSeek 子智能体会对照需求逐条检查，最后给一张表：哪条需求、做到没有、依据在哪个文件第几行。Claude 或 GPT 只看这些，没做到的一次性发回去改，只有表里写着「没做到」的地方才去翻代码。不用 `cwd` 指定的话，新对话就开在你当前工作的文件夹里。
|
|
80
153
|
|
|
@@ -82,48 +155,6 @@ Codex 和 Claude 轮流往同一个 Harness 对话发消息，每条都标明是
|
|
|
82
155
|
<img src="./docs/benchmarks/token-usage-2026-10/charts/evidence-chain.zh.svg" width="100%" alt="一次真实转交的证据链：用户提需求，Codex 写规格和验收命令，dsh-baton 给文件夹拍快照，DeepSeek Harness 写出 11 个文件，dsh-baton 自己列出改动并跑 npm test，Codex 主动打回一处，dsh-baton 再次验收，Codex 通过，基准测试自己的验收 13/13 通过">
|
|
83
156
|
</p>
|
|
84
157
|
|
|
85
|
-
## Token 用量实测
|
|
86
|
-
|
|
87
|
-
**一句话：大活、长活交给它**。一次性做一个跨很多文件的功能、一次大重构、一整个小应用，这种时候最省：Claude Code 自己的花费少 65–81%，Codex 在 ChatGPT Plus 一个 5 小时额度里能多做 2 到 5 倍的任务（GPT-6 Astra 做中号任务时是 5 倍）。
|
|
88
|
-
|
|
89
|
-
**说实话**：小任务，Codex 用 GPT-6.1 Sol 自己做，总价反而比转交更便宜；中号任务两者基本持平。转交值得的场景是：你想让 Claude 或 GPT 负责规划和把关，让更便宜的模型去动手写，又不想老是撞上 5 小时额度上限。
|
|
90
|
-
|
|
91
|
-
**适合谁**：大多数人用 Claude 或 ChatGPT 走的是订阅套餐（Plus、Pro、Max 5x 之类），而 DeepSeek 是充值后按用量扣费，所以每次转交都是套餐之外多花的钱。如果你的套餐额度本来就够用，就不用折腾这套流程，省一点是一点。如果你像我一样，经常跑又长又杂、要反复修改的大任务，老是撞上额度上限，那花一点 DeepSeek 的钱，就能让你已经付费的套餐多干很多活。
|
|
92
|
-
|
|
93
|
-
<p align="center">
|
|
94
|
-
<img src="./docs/benchmarks/token-usage-2026-10/charts/natural-combined.zh.svg" width="100%" alt="每个任务的花费，自己做与转交（0.6.0；Astra 大号任务为 0.6.1）：Claude Code（Opus 5.5）和 Codex（GPT-6.1 Sol、GPT-6 Astra），各用自己的刻度">
|
|
95
|
-
</p>
|
|
96
|
-
|
|
97
|
-
每个任务的花费，按标价计，DeepSeek V4.1 Flash 1017 按高峰价：
|
|
98
|
-
|
|
99
|
-
| 客户端 · 模型 | 任务 | 自己做 | 转交，只算客户端 | 转交，含 DeepSeek |
|
|
100
|
-
|---|---|---|---|---|
|
|
101
|
-
| Claude Code · Opus 5.5 high | 小号 | $1.07 | $0.37（−65%） | $0.55（−49%） |
|
|
102
|
-
| Claude Code · Opus 5.5 high | 中号 | $2.13 | $0.41（−81%） | $0.70（−67%） |
|
|
103
|
-
| Codex · GPT-6.1 Sol high | 小号 | $0.17 | $0.09（−49%） | $0.29（+73%） |
|
|
104
|
-
| Codex · GPT-6.1 Sol high | 中号 | $0.41 | $0.10（−75%） | $0.41（−2%） |
|
|
105
|
-
| Codex · GPT-6 Astra high | 小号 | $0.79 | $0.56（−29%） | $0.75（−6%） |
|
|
106
|
-
| Codex · GPT-6 Astra high | 中号 | $2.27 | $0.48（−79%） | $0.78（−65%） |
|
|
107
|
-
|
|
108
|
-
<p align="center">
|
|
109
|
-
<img src="./docs/benchmarks/token-usage-2026-10/charts/natural-quota-combined.zh.svg" width="80%" alt="Codex 每个任务占 ChatGPT Plus 5 小时额度，自己做与用 0.6.0 转交：GPT-6.1 Sol 和 GPT-6 Astra">
|
|
110
|
-
</p>
|
|
111
|
-
|
|
112
|
-
每个任务占 ChatGPT Plus 5 小时额度：Sol 小号 1.9% → 0.8%，Sol 中号 4.3% → 1.0%，Astra 小号 7% → 3.5%，Astra 中号 22% → 4%。
|
|
113
|
-
|
|
114
|
-
<details>
|
|
115
|
-
<summary>测了什么、怎么测的</summary>
|
|
116
|
-
|
|
117
|
-
- **两个任务，用普通用户的口吻提**。小号任务 Claude Code 或 Codex 自己做大约 7–8 分钟；中号任务是一个带服务器和页面的小应用。比这更长的大活没有测。原文如下，可以直接点开看：
|
|
118
|
-
- 小号：用 Node 写一个命令行任务管理工具，零依赖，分模块，带测试。[需求原文](docs/benchmarks/token-usage-2026-10/natural/medium.md) · [验收脚本](docs/benchmarks/token-usage-2026-10/checks/natural-medium.mjs)
|
|
119
|
-
- 中号：一个任务管理网页应用，Node 服务器加前端页面，REST 接口、统计、测试和 README。[需求原文](docs/benchmarks/token-usage-2026-10/natural/large.md) · [验收脚本](docs/benchmarks/token-usage-2026-10/checks/natural-large.mjs)
|
|
120
|
-
- **转交组唯一的区别**，是在需求末尾多一句：交给 DeepSeek Harness 去做。
|
|
121
|
-
- 两组用同一个模型、同样的推理强度，每格跑 3 次（Astra 各 1 次，小号转交跑了 2 次）；每次都用同一套验收脚本检查，模型看不到这个脚本。转交组 12 次全部一次通过。
|
|
122
|
-
- 价格按标价算。DeepSeek 按高峰价，是最保守的算法；实际 DeepSeek 账单大约是这个数的 58%。
|
|
123
|
-
- 每一次运行、原始数据和脚本：[运行日志](docs/benchmarks/token-usage-2026-10/LOG.md)、[完整报告](docs/benchmarks/token-usage-2026-10.md)。
|
|
124
|
-
|
|
125
|
-
</details>
|
|
126
|
-
|
|
127
158
|
## 工具
|
|
128
159
|
|
|
129
160
|
<p align="center">
|
|
@@ -134,9 +165,13 @@ Codex 和 Claude 轮流往同一个 Harness 对话发消息，每条都标明是
|
|
|
134
165
|
<img src="./assets/readme/zh/states.svg" width="100%" alt="运行状态：queued、running、waiting、completed、failed、cancelled，Harness 中途重启则为 interrupted。对话正忙时，followup 进排队栏，steer 在下一步插话">
|
|
135
166
|
</p>
|
|
136
167
|
|
|
168
|
+
需要查每个工具的具体参数和返回字段时：
|
|
169
|
+
|
|
137
170
|
<details>
|
|
138
171
|
<summary>完整工具说明</summary>
|
|
139
172
|
|
|
173
|
+
服务器的 MCP instructions 只有一句话（0.6.2 起）；怎么转交、怎么等、怎么回答问题，都写在各个工具自己的说明里。Codex 会在每个工具的说明前面重复一遍 instructions，所以它给模型看的工具目录从约 2.43 万字符降到约 0.97 万字符。
|
|
174
|
+
|
|
140
175
|
| 工具 | 作用 |
|
|
141
176
|
|---|---|
|
|
142
177
|
| `dsh_list_workspaces` | 列出 Harness 侧边栏里的工作区 |
|
|
@@ -144,7 +179,7 @@ Codex 和 Claude 轮流往同一个 Harness 对话发消息，每条都标明是
|
|
|
144
179
|
| `dsh_list_sessions` | 列出对话（最新在前），带标题、目录、是否在跑和 `model`（下一次请求用的模型）；可按目录或关键字过滤。已归档的对话不会列出 |
|
|
145
180
|
| `dsh_list_models` | 列出 Harness 能用的模型（provider、id、名称、推理强度）和它的默认模型 |
|
|
146
181
|
| `dsh_read_session` | 读某个对话最近的消息和回复（含用到的工具名）；已归档的对话会带 `archived: true` |
|
|
147
|
-
| `dsh_send` | 发消息。带 `session_id` 续接那个对话；否则新开对话，建在 `cwd` 或 `workspace_id` 指定的位置，都不带时建在当前对话所在的文件夹（`cwd` 还不是工作区时会先登记；指定的 `cwd` 在当前对话文件夹之外也可以，结果里的 `folder_note` 会提醒）。`checks`：运行结束后 dsh-baton
|
|
182
|
+
| `dsh_send` | 发消息。带 `session_id` 续接那个对话；否则新开对话，建在 `cwd` 或 `workspace_id` 指定的位置，都不带时建在当前对话所在的文件夹（`cwd` 还不是工作区时会先登记；指定的 `cwd` 在当前对话文件夹之外也可以，结果里的 `folder_note` 会提醒）。`checks`：运行结束后 dsh-baton 自己跑的测试命令（见[转交之后怎么验收](#转交之后怎么验收)）。立即返回 `run_id`。Harness 里这条消息会标注「由 Claude / ChatGPT 从另一个聊天发送」。已归档的对话会被拒绝：先在 Harness 里取消归档，或新开对话。对话正忙时，`mode` 为 `followup` 会排在当前回合之后，`steer` 会插进正在跑的回合；不传时跟随 Harness 自己的设置（设置 → 繁忙时的发送行为：排队发送或插话发送），读不到设置时按 `followup`。返回里的 `mode_source` 说明用的是哪种。`model` 只在用户点名模型时传（如“DeepSeek-V4 Pro”“v4-pro”；`reasoning_effort` 同理）：按 Harness 自己的模型列表匹配，不分大小写，忽略空格、连字符和开头的 DeepSeek，所以 Harness 以后上线的模型（如 V4.1 Pro）一出现在列表里就能用；匹配不到或匹配到多个时，发送直接失败、什么都不创建，并列出可用模型（用 `provider/model` 指定其一）。模型在消息发出前设到该对话上，Harness 的默认模型会恢复原样（Harness 会把对话里选的模型同时存成默认）。不传时，续接的对话沿用它自己的模型，新对话用 Harness 默认模型。返回值的 `model` 和 `model_source` 写明用的是哪个 |
|
|
148
183
|
| `dsh_status` | 查看运行进度：状态、最近的文字和工具调用、最终回复；回合结束但子智能体/后台任务还在跑时给出 `waiting_on`；中途有人在 Harness 界面里发消息时给出 `human_interjections`；被 Harness 重启打断的任务状态为 `interrupted`；以及这次运行发送时用的 `model` |
|
|
149
184
|
| `dsh_wait` | 信任了 Stop 钩子的 Codex 用不到它。等运行结束；发消息时带了 `checks` 的，结束后会附上 `evidence`（改了哪些文件、测试结果）（或者等到它停下来问人，见 `dsh_answer`）：Codex 每次最多等 270 秒，其他客户端 50 秒。没做完会带 `timed_out`，只返回状态，再调用一次即可。能在后台等待的客户端改用 `dsh_send` 返回的 `wait_command`。`dsh_status` 只用来看一眼，不用来等待 |
|
|
150
185
|
| `dsh_answer` | 回答运行中途提出的问题（Harness 的 ask_user_question）：每道题可以填选项编号或选项文字、自由填写，或者跳过；可以逐题回答，也可以一次答完。运行一提问，`dsh_wait` 和 `wait_command` 就会立刻返回，并带上题目（`needs_input`、`question`；Harness 那边模型推荐的选项单独放在 `harness_suggested` 里，不再写在选项文字中）。只有你说过让它自己决定时，助手才会按自己的判断回答，这时它会带上 `reason`，并告诉你选了什么、为什么；否则它会把题目转给你，开头先写它自己的建议和理由。你也可以直接在 Harness 窗口里回答，谁先答就算谁的 |
|
|
@@ -158,7 +193,12 @@ Codex 和 Claude 轮流往同一个 Harness 对话发消息，每条都标明是
|
|
|
158
193
|
|
|
159
194
|
</details>
|
|
160
195
|
|
|
161
|
-
##
|
|
196
|
+
## 命令行和配置
|
|
197
|
+
|
|
198
|
+
想在终端或脚本里直接驱动 Harness，而不是通过对话时：
|
|
199
|
+
|
|
200
|
+
<details>
|
|
201
|
+
<summary>命令行</summary>
|
|
162
202
|
|
|
163
203
|
```bash
|
|
164
204
|
dsh-baton workspaces
|
|
@@ -177,7 +217,12 @@ dsh-baton rename-workspace ~/code/new-app 新名字
|
|
|
177
217
|
|
|
178
218
|
（从源码运行时用 `node src/cli.mjs …`。）
|
|
179
219
|
|
|
180
|
-
|
|
220
|
+
</details>
|
|
221
|
+
|
|
222
|
+
默认值不合适时，比如要换套接字路径或强制用 headless 模式：
|
|
223
|
+
|
|
224
|
+
<details>
|
|
225
|
+
<summary>环境变量</summary>
|
|
181
226
|
|
|
182
227
|
| 变量 | 默认值 | 作用 |
|
|
183
228
|
|---|---|---|
|
|
@@ -191,6 +236,10 @@ dsh-baton rename-workspace ~/code/new-app 新名字
|
|
|
191
236
|
| `DSH_BATON_ACCOUNT` | `1` | headless 模式下设为 `0` 则改用 API key 路线 |
|
|
192
237
|
| `DSH_BATON_PATCHES` | 空 | headless 模式额外的 `--patch` 覆盖文件，用 `:` 分隔 |
|
|
193
238
|
|
|
239
|
+
</details>
|
|
240
|
+
|
|
241
|
+
Harness 插件连不上时：
|
|
242
|
+
|
|
194
243
|
<details>
|
|
195
244
|
<summary>headless 后备模式说明</summary>
|
|
196
245
|
|
|
@@ -200,18 +249,20 @@ dsh-baton rename-workspace ~/code/new-app 新名字
|
|
|
200
249
|
|
|
201
250
|
## 安装细节
|
|
202
251
|
|
|
252
|
+
更新或卸载插件、从 dsh-bridge 升级、从源码运行，或者插件没能注册时：
|
|
253
|
+
|
|
203
254
|
<details>
|
|
204
255
|
<summary>插件做了什么、更新、卸载、从 dsh-bridge 升级、从源码安装、Windows</summary>
|
|
205
256
|
|
|
206
257
|
**插件启用时做了什么**。它把 MCP 服务器复制到 `~/.dsh-baton/app` 这个固定的文件夹，再直接把 MCP 注册写进 `~/.claude.json` 和 `~/.codex/config.toml`，各留一份 `*.bak-dsh-baton` 备份。电脑上有 Node.js ≥ 22.15（在 `PATH` 里能找到）就用它启动服务器；没有的话，就用 Harness 自带的运行环境（Harness 应用本身以 Node 模式运行，`ELECTRON_RUN_AS_NODE=1`），不用另外安装任何东西。两种情况下，只装了桌面应用、`claude` / `codex` 不在 `PATH` 里也能用。每次 Harness 启动都会再检查一遍：已经正确的注册、或者指向另一份可用 dsh-baton 的注册，都不会改动。在 Harness 里输入包名后，安装源会自动切到「npm 官方源」（英文界面是 "Official npm registry"），不用另外选择，也不用重启。不想让插件自动注册，给 Harness 设置 `DSH_BATON_AUTO_REGISTER=0`。
|
|
207
258
|
|
|
208
|
-
**Codex 的 Stop 钩子**。插件会在 `~/.codex/config.toml` 里加一段带 `# dsh-baton` 标记的 `[[hooks.Stop]]`，Codex 里显示为 **dsh-baton: waiting for the Harness run**，你信任之后才会运行（dsh-baton 不会替你信任）。这一段只写了一个小脚本的路径 `~/.dsh-baton/bin/codex-stop-hook`（Windows 上是 `codex-stop-hook.cmd`），Node.js 和服务器这些会变的路径都放在脚本里。所以这一段本身永远不变：升级、同版本刷新、重启 Harness 都不会动它，信任一直有效。万一这一段被改写，dsh-baton 会清掉旧的信任记录，Codex 会请你重新信任。Windows 上用 `.cmd`，是因为 Codex 通过 `PowerShell -Command`
|
|
259
|
+
**Codex 的 Stop 钩子**。插件会在 `~/.codex/config.toml` 里加一段带 `# dsh-baton` 标记的 `[[hooks.Stop]]`，Codex 里显示为 **dsh-baton: waiting for the Harness run**，你信任之后才会运行（dsh-baton 不会替你信任）。这一段只写了一个小脚本的路径 `~/.dsh-baton/bin/codex-stop-hook`（Windows 上是 `codex-stop-hook.cmd`），Node.js 和服务器这些会变的路径都放在脚本里。所以这一段本身永远不变：升级、同版本刷新、重启 Harness 都不会动它，信任一直有效。万一这一段被改写，dsh-baton 会清掉旧的信任记录，Codex 会请你重新信任。Windows 上用 `.cmd`，是因为 Codex 通过 `PowerShell -Command` 运行钩子，启动不了带引号的程序路径。没有自己的 Node.js 时，脚本和服务器一样以 Node 模式（`ELECTRON_RUN_AS_NODE=1`）运行 Harness 程序本身；插件每次启动都会重写它，所以 Harness 更新后路径也会跟上。只有没装 Codex、设了 `DSH_BATON_CODEX_HOOK=0`、或 Codex 里的 dsh-baton 条目没指向服务器目录（比如裸的 `npx` 命令）时才不加；这时 Codex 对话里第一次交接会说明原因。手动添加用 `dsh-baton setup --codex-hook`，`setup --remove` 会删掉它，给 Harness 设置 `DSH_BATON_CODEX_HOOK=0` 则插件不再添加。
|
|
209
260
|
|
|
210
|
-
**更新不用重启**。新版本装进 `~/.dsh-baton/app` 后（插件更新、`setup` 或手动复制），或者同一版本但文件有改动时，Claude Code 和 Codex 里已经开着的对话，下一次调用 `dsh_*` 工具时就会用上：服务器每次调用前检查这个文件夹，启动新版本，并在这次调用的结果里提示一次已经更新。正在进行的 `dsh_wait` 会先在旧版本里跑完。新版本启动失败时，旧版本继续工作，结果里会说明原因。新版本新增的工具，Claude Code 里马上就能用（服务器会通知客户端工具列表变了）；Codex
|
|
261
|
+
**更新不用重启**。新版本装进 `~/.dsh-baton/app` 后（插件更新、`setup` 或手动复制），或者同一版本但文件有改动时，Claude Code 和 Codex 里已经开着的对话，下一次调用 `dsh_*` 工具时就会用上：服务器每次调用前检查这个文件夹，启动新版本，并在这次调用的结果里提示一次已经更新。正在进行的 `dsh_wait` 会先在旧版本里跑完。新版本启动失败时，旧版本继续工作，结果里会说明原因。新版本新增的工具，Claude Code 里马上就能用（服务器会通知客户端工具列表变了）；Codex 一直用对话开始时的工具列表，新工具要到下一个新对话才会显示；不过旧对话里也能通过 `dsh_call` 马上用上新功能（更新提示里会写明），已有的工具也会立刻用上新代码。
|
|
211
262
|
|
|
212
263
|
**`npx -y dsh-baton-mcp setup`** 在终端里做同样的注册：用于插件没能注册的情况，或者从 MCP 目录过来的用户。插件已经注册过时它什么都不改；插件没装的话，它会提示去添加。
|
|
213
264
|
|
|
214
|
-
**更新**。Harness 只给官方插件提供"更新"按钮，所以要：插件 → dsh-baton-host → **卸载**，再**添加插件** → `dsh-baton-host`。新版本刚发布的一段时间里，Harness 会装上一个版本（pnpm 的 `minimumReleaseAge` 会暂缓刚发布的版本，安装弹窗里会说明）；想马上用新版，输入带版本号的名字：`dsh-baton-host@0.6.
|
|
265
|
+
**更新**。Harness 只给官方插件提供"更新"按钮，所以要：插件 → dsh-baton-host → **卸载**，再**添加插件** → `dsh-baton-host`。新版本刚发布的一段时间里，Harness 会装上一个版本（pnpm 的 `minimumReleaseAge` 会暂缓刚发布的版本，安装弹窗里会说明）；想马上用新版，输入带版本号的名字：`dsh-baton-host@0.6.2`。预发布版必须写确切版本号添加，比如 `dsh-baton-host@0.6.0-next.0`：Harness 会把 `@next` 解析成一个坏掉的占位包。只输入 `dsh-baton-host` 装的是最新正式版。重新启用后，插件会把 MCP 服务器也更新到同一版本，新开的对话就会用上。万一两边版本对不上，第一次发现不一致的工具调用会提示，并写明哪一边旧、另一边的确切版本号。
|
|
215
266
|
|
|
216
267
|
**卸载**。Harness → 插件 → dsh-baton-host → **卸载**，再运行 `npx -y dsh-baton-mcp setup --remove`。插件分不清"被卸载"和"Harness 退出"，所以 MCP 注册交给这条命令删，它也会删掉 `~/.dsh-baton/app`；运行记录留在 `~/.dsh-baton`，不需要的话自己删掉。
|
|
217
268
|
|
|
@@ -221,6 +272,10 @@ dsh-baton rename-workspace ~/code/new-app 新名字
|
|
|
221
272
|
|
|
222
273
|
**Windows**。步骤相同；[WINDOWS.md](WINDOWS.md) 说明了不同之处（用命名管道代替套接字文件），以及插件页装不上或卸不掉时的修法。
|
|
223
274
|
|
|
275
|
+
</details>
|
|
276
|
+
|
|
277
|
+
手动注册，或者想在 Claude 桌面聊天应用（不是 Claude Code）里用 dsh-baton 时：
|
|
278
|
+
|
|
224
279
|
<details>
|
|
225
280
|
<summary>手动注册与 Claude 桌面应用</summary>
|
|
226
281
|
|
|
@@ -241,8 +296,6 @@ codex mcp add dsh-baton -- "$(command -v node)" "$PWD/dsh-baton/src/server.mjs"
|
|
|
241
296
|
|
|
242
297
|
</details>
|
|
243
298
|
|
|
244
|
-
</details>
|
|
245
|
-
|
|
246
299
|
## 安全与限制
|
|
247
300
|
|
|
248
301
|
<p align="center">
|
|
@@ -255,8 +308,6 @@ codex mcp add dsh-baton -- "$(command -v node)" "$PWD/dsh-baton/src/server.mjs"
|
|
|
255
308
|
|
|
256
309
|
任何能以你的身份运行程序的进程都能通过这个套接字驱动 Harness，这和直接运行 `dsh` 的权限一样。本项目依赖 Harness 0.2.1 系列的内部服务接口，Harness 大版本更新后可能需要跟进。
|
|
257
310
|
|
|
258
|
-
<p align="center"><a href="docs/demos.zh-CN.md">更多演示 →</a></p>
|
|
259
|
-
|
|
260
311
|
## 许可证
|
|
261
312
|
|
|
262
313
|
MIT
|
package/host/README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
<p align="center">
|
|
2
|
-
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/hero.gif" width="100%" alt="dsh-baton: pass the baton from Claude Code or Codex to DeepSeek Harness, watch it run live, and get it handed back when it's done">
|
|
2
|
+
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/en/hero.gif" width="100%" alt="dsh-baton: pass the baton from Claude Code or Codex to DeepSeek Harness, watch it run live, and get it handed back when it's done">
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
5
|
<p align="center">
|
|
@@ -17,13 +17,13 @@ The DeepSeek Harness plugin for [dsh-baton](https://github.com/JialaoLiu/dsh-bat
|
|
|
17
17
|
DeepSeek Harness 插件，配合 [dsh-baton](https://github.com/JialaoLiu/dsh-baton/blob/main/README.zh-CN.md) 使用。它运行在 Harness 内部，只开一个当前用户才能访问的本地套接字，让 MCP 客户端能新建工作区和对话、续接指定对话、等待任务完成。所有操作都走 Harness 官方会话服务，界面实时可见。
|
|
18
18
|
|
|
19
19
|
<p align="center">
|
|
20
|
-
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/features.svg" width="100%" alt="Create workspaces and sessions, continue a session, run live in the Harness UI labelled with the sender, get woken when it is done, no extra API key, macOS and Windows with zero dependencies">
|
|
20
|
+
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/en/features.svg" width="100%" alt="Create workspaces and sessions, continue a session, run live in the Harness UI labelled with the sender, get woken when it is done, no extra API key, macOS and Windows with zero dependencies">
|
|
21
21
|
</p>
|
|
22
22
|
|
|
23
23
|
## Install / 安装
|
|
24
24
|
|
|
25
25
|
<p align="center">
|
|
26
|
-
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/install.svg" width="100%" alt="Step 1: in Harness open Plugins, Add plugin, enter dsh-baton-host, Install, Enable now; it registers dsh-baton for Claude Code and Codex. Step 2: in a new chat, ask for dsh_list_workspaces">
|
|
26
|
+
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/en/install.svg" width="100%" alt="Step 1: in Harness open Plugins, Add plugin, enter dsh-baton-host, Install, Enable now; it registers dsh-baton for Claude Code and Codex. Step 2: in a new chat, ask for dsh_list_workspaces">
|
|
27
27
|
</p>
|
|
28
28
|
|
|
29
29
|
Harness → Plugins / 插件 → Add plugin / 添加插件 → `dsh-baton-host` → Install / 安装 → Enable now / 立即启用
|
|
@@ -39,7 +39,7 @@ Remove / 卸载: uninstall, then `npx -y dsh-baton-mcp setup --remove` / 卸载
|
|
|
39
39
|
## How it works / 工作原理
|
|
40
40
|
|
|
41
41
|
<p align="center">
|
|
42
|
-
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/architecture.svg" width="100%" alt="MCP clients call dsh-baton-mcp over stdio; it reaches the dsh-baton-host plugin inside Harness through an owner-only local socket; the plugin drives Harness sessions live, with dsh headless as fallback">
|
|
42
|
+
<img src="https://raw.githubusercontent.com/JialaoLiu/dsh-baton/main/assets/readme/en/architecture.svg" width="100%" alt="MCP clients call dsh-baton-mcp over stdio; it reaches the dsh-baton-host plugin inside Harness through an owner-only local socket; the plugin drives Harness sessions live, with dsh headless as fallback">
|
|
43
43
|
</p>
|
|
44
44
|
|
|
45
45
|
## Socket protocol / 套接字协议
|
package/host/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-baton-host",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.3",
|
|
4
4
|
"description": "DeepSeek Harness plugin for dsh-baton: adding it is the whole install. Switched on, it registers the dsh-baton MCP server for Claude Code and Codex, then takes the baton over a local, owner-only control socket, runs it in a specific session through the host's own session controller, and hands the result back when the turn is done.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "lib/index.js",
|
|
@@ -20,7 +20,7 @@
|
|
|
20
20
|
"LICENSE"
|
|
21
21
|
],
|
|
22
22
|
"dependencies": {
|
|
23
|
-
"dsh-baton-mcp": "0.6.
|
|
23
|
+
"dsh-baton-mcp": "0.6.3"
|
|
24
24
|
},
|
|
25
25
|
"license": "MIT",
|
|
26
26
|
"dsh": {
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-baton-mcp",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.3",
|
|
4
4
|
"mcpName": "io.github.JialaoLiu/dsh-baton",
|
|
5
5
|
"description": "Pass the baton from Claude Code, Codex or any MCP client to a local DeepSeek Harness: an MCP server that hands off tasks, continues a specific session, shows the run live in Harness and hands the result back when it is done.",
|
|
6
6
|
"type": "module",
|
package/server.json
CHANGED
|
@@ -7,12 +7,12 @@
|
|
|
7
7
|
"url": "https://github.com/JialaoLiu/dsh-baton",
|
|
8
8
|
"source": "github"
|
|
9
9
|
},
|
|
10
|
-
"version": "0.6.
|
|
10
|
+
"version": "0.6.3",
|
|
11
11
|
"packages": [
|
|
12
12
|
{
|
|
13
13
|
"registryType": "npm",
|
|
14
14
|
"identifier": "dsh-baton-mcp",
|
|
15
|
-
"version": "0.6.
|
|
15
|
+
"version": "0.6.3",
|
|
16
16
|
"transport": {
|
|
17
17
|
"type": "stdio"
|
|
18
18
|
}
|
package/src/codex-hook.mjs
CHANGED
|
@@ -3,11 +3,12 @@
|
|
|
3
3
|
// Codex feed reason back to the model in the same turn. `dsh-baton codex-stop-hook` is such
|
|
4
4
|
// a hook: after dsh_send the model ends its turn, the hook waits for the run without any
|
|
5
5
|
// model requests, and returns the result as dsh_wait would. One wake instead of a dsh_wait
|
|
6
|
-
// call every few minutes.
|
|
6
|
+
// call every few minutes.
|
|
7
7
|
import fs from 'node:fs'
|
|
8
|
+
import { execFileSync } from 'node:child_process'
|
|
8
9
|
import path from 'node:path'
|
|
9
10
|
import * as core from './core.mjs'
|
|
10
|
-
import { codexConfigPath, stableNodePath, codexHookEntry, codexHookStatus, HOOK_TIMEOUT_S } from './register.mjs'
|
|
11
|
+
import { codexConfigPath, stableNodePath, codexHookEntry, codexHookStatus, hookResultFile, HOOK_TIMEOUT_S } from './register.mjs'
|
|
11
12
|
|
|
12
13
|
export { editCodexHook, HOOK_TIMEOUT_S } from './register.mjs'
|
|
13
14
|
|
|
@@ -68,6 +69,20 @@ export function hookUntrusted() {
|
|
|
68
69
|
}
|
|
69
70
|
}
|
|
70
71
|
|
|
72
|
+
// Why the plugin did not add the hook (see addCodexHook), in one sentence, or null: when
|
|
73
|
+
// it was added, when Codex is not installed, or when no plugin from 0.6.2 on has run yet.
|
|
74
|
+
const SKIP_REASONS = {
|
|
75
|
+
disabled: 'it is turned off with DSH_BATON_CODEX_HOOK=0 in the environment Harness runs with',
|
|
76
|
+
'no-cli': "Codex's dsh-baton entry does not name a server folder with cli.mjs in it (a bare command such as npx, or a folder that is gone)",
|
|
77
|
+
}
|
|
78
|
+
export function hookSkipReason(env = process.env) {
|
|
79
|
+
let r = null
|
|
80
|
+
try { r = JSON.parse(fs.readFileSync(hookResultFile(env), 'utf8')) } catch { return null }
|
|
81
|
+
if (!['off', 'skipped', 'failed'].includes(r?.state) || !r.reason) return null
|
|
82
|
+
const why = SKIP_REASONS[r.reason] ?? `adding it failed (${String(r.reason).slice(0, 200)})`
|
|
83
|
+
return `dsh-baton's Codex Stop hook is not set up because ${why}, so Codex waits with dsh_wait.`
|
|
84
|
+
}
|
|
85
|
+
|
|
71
86
|
// Each Codex conversation is told about trusting the hook once.
|
|
72
87
|
const notedFile = () => path.join(dir(), 'trust-noted.json')
|
|
73
88
|
export function noteOnce(thread) {
|
|
@@ -80,9 +95,123 @@ export function noteOnce(thread) {
|
|
|
80
95
|
return true
|
|
81
96
|
}
|
|
82
97
|
|
|
83
|
-
//
|
|
84
|
-
//
|
|
85
|
-
|
|
98
|
+
// The language of Codex's own interface. A language picked in Codex's settings is written as
|
|
99
|
+
// localeOverride in its config ([desktop]) and wins, English included. Without one, Codex
|
|
100
|
+
// (Electron) follows the system's preferred language, not its region format:
|
|
101
|
+
// AppleLanguages (then AppleLocale) on macOS, the user interface language that Node's ICU
|
|
102
|
+
// reports on Windows, LC_ALL / LC_MESSAGES / LANG elsewhere (C and POSIX say nothing).
|
|
103
|
+
// 'zh' when that starts with zh, else 'en' (also when nothing can be read). The hook runs
|
|
104
|
+
// at every Codex Stop, so the system is asked only without an override, once per process.
|
|
105
|
+
const defaults = (key) => execFileSync('defaults', ['read', '-g', key], { encoding: 'utf8', timeout: 1500, stdio: ['ignore', 'pipe', 'ignore'] })
|
|
106
|
+
const SYSTEM = {
|
|
107
|
+
platform: process.platform,
|
|
108
|
+
readAppleLanguages: () => /^\(\s*"?([^",\s)]+)/.exec(defaults('AppleLanguages'))?.[1],
|
|
109
|
+
readAppleLocale: () => defaults('AppleLocale').trim(),
|
|
110
|
+
intlLocale: () => Intl.DateTimeFormat().resolvedOptions().locale,
|
|
111
|
+
}
|
|
112
|
+
const attempt = (read) => { try { return read() || '' } catch { return '' } }
|
|
113
|
+
export function systemLocale(env = process.env, sys = SYSTEM) {
|
|
114
|
+
const { platform, readAppleLanguages, readAppleLocale, intlLocale } = { ...SYSTEM, ...sys }
|
|
115
|
+
if (platform === 'darwin') return attempt(readAppleLanguages) || attempt(readAppleLocale)
|
|
116
|
+
if (platform === 'win32') return attempt(intlLocale)
|
|
117
|
+
return [env.LC_ALL, env.LC_MESSAGES, env.LANG].find((v) => v && !/^(C|POSIX)([._@]|$)/.test(v)) ?? ''
|
|
118
|
+
}
|
|
119
|
+
let systemCached
|
|
120
|
+
export function codexLang(env = process.env, sys) {
|
|
121
|
+
let picked
|
|
122
|
+
try {
|
|
123
|
+
picked = fs.readFileSync(codexConfigPath(env), 'utf8').match(/^\s*localeOverride\s*=\s*["']([^"']*)["']/m)?.[1]
|
|
124
|
+
} catch { /* no config: Codex follows the system */ }
|
|
125
|
+
const locale = picked || (sys ? systemLocale(env, sys) : (systemCached ??= systemLocale(env)))
|
|
126
|
+
return /^zh/i.test(locale) ? 'zh' : 'en'
|
|
127
|
+
}
|
|
128
|
+
|
|
129
|
+
// Codex desktop shows reason as is and folds the rest of a long message away, so it opens
|
|
130
|
+
// with a few lines a person reads at a glance: per run, its state, how long it took, and
|
|
131
|
+
// the files and checks dsh-baton saw (only what the result already holds).
|
|
132
|
+
const WORDS = {
|
|
133
|
+
en: {
|
|
134
|
+
state: { completed: 'completed', failed: 'failed', cancelled: 'cancelled', interrupted: 'interrupted' },
|
|
135
|
+
asks: (q, n) => `waiting for an answer${n > 1 ? ` (${n} questions)` : ''}${q ? `: "${q}"` : ''}`,
|
|
136
|
+
approval: 'waiting for an approval in Harness',
|
|
137
|
+
took: (t) => ` in ${t}`, units: ['h', 'm', 's'], join: ' ',
|
|
138
|
+
files: (n, more) => `${n}${more ? '+' : ''} file${n === 1 && !more ? '' : 's'} changed`,
|
|
139
|
+
checks: (ok, bad, skipped, all) => (skipped
|
|
140
|
+
? `checks ${ok}/${all} passed${bad ? `, ${bad} failed` : ''}, ${skipped} skipped`
|
|
141
|
+
: `checks ${bad ? 'failed' : 'passed'} (${ok}/${all})`),
|
|
142
|
+
many: (n) => `dsh-baton: ${n} Harness runs are back`,
|
|
143
|
+
running: (ids) => `Still running: ${ids.join(', ')}`,
|
|
144
|
+
sep: ': ', dot: ' · ',
|
|
145
|
+
},
|
|
146
|
+
zh: {
|
|
147
|
+
state: { completed: '已完成', failed: '失败', cancelled: '已取消', interrupted: '被中断' },
|
|
148
|
+
asks: (q, n) => `在等回答${n > 1 ? `（共 ${n} 个问题）` : ''}${q ? `：「${q}」` : ''}`,
|
|
149
|
+
approval: '在等你在 Harness 里批准',
|
|
150
|
+
took: (t) => `，用时 ${t}`, units: [' 小时', ' 分', ' 秒'], join: ' ',
|
|
151
|
+
files: (n, more) => `改动 ${n}${more ? '+' : ''} 个文件`,
|
|
152
|
+
checks: (ok, bad, skipped, all) => (skipped
|
|
153
|
+
? `项目测试 ${ok}/${all} 通过${bad ? `，${bad} 个未通过` : ''}，${skipped} 个超时未跑`
|
|
154
|
+
: `项目测试${bad ? '未通过' : '通过'}（${ok}/${all}）`),
|
|
155
|
+
many: (n) => `dsh-baton：${n} 个 Harness 任务回来了`,
|
|
156
|
+
running: (ids) => `还在运行：${ids.join('、')}`,
|
|
157
|
+
sep: '：', dot: ' · ',
|
|
158
|
+
},
|
|
159
|
+
}
|
|
160
|
+
|
|
161
|
+
function took(r, w) {
|
|
162
|
+
const ms = Date.parse(r.ended_at) - Date.parse(r.started_at)
|
|
163
|
+
if (!(ms >= 0)) return null
|
|
164
|
+
const s = Math.round(ms / 1000)
|
|
165
|
+
const [h, m, sec] = [Math.floor(s / 3600), Math.floor((s % 3600) / 60), s % 60]
|
|
166
|
+
const parts = h ? [[h, 0], [m, 1]] : m ? [[m, 1], [sec, 2]] : [[sec, 2]]
|
|
167
|
+
return parts.filter(([v], i) => v || i === 0).map(([v, u]) => `${v}${w.units[u]}`).join(w.join)
|
|
168
|
+
}
|
|
169
|
+
|
|
170
|
+
// By characters, not UTF-16 units, so an emoji is never cut in half.
|
|
171
|
+
const clip = (text, n = 100) => {
|
|
172
|
+
const t = Array.from(String(text ?? '').replace(/\s+/g, ' ').trim())
|
|
173
|
+
return t.length > n ? `${t.slice(0, n).join('')}…` : t.join('')
|
|
174
|
+
}
|
|
175
|
+
|
|
176
|
+
function runLine(r, w) {
|
|
177
|
+
if (r.needs_input) {
|
|
178
|
+
const qs = r.question?.questions ?? []
|
|
179
|
+
return r.needs_input === 'harness-ui' && !qs.length ? w.approval : w.asks(clip(qs[0]?.question), qs.length)
|
|
180
|
+
}
|
|
181
|
+
const t = took(r, w)
|
|
182
|
+
const bits = [`${w.state[r.state] ?? r.state}${t ? w.took(t) : ''}`]
|
|
183
|
+
const ch = r.evidence?.changes
|
|
184
|
+
if (ch) bits.push(w.files((ch.created?.length ?? 0) + (ch.modified?.length ?? 0) + (ch.deleted?.length ?? 0), ch.truncated))
|
|
185
|
+
// A check skipped for lack of time did not fail: it is counted apart.
|
|
186
|
+
const checks = r.evidence?.checks
|
|
187
|
+
if (checks?.length) {
|
|
188
|
+
const ok = checks.filter((c) => c.passed).length
|
|
189
|
+
const skipped = checks.filter((c) => c.skipped).length
|
|
190
|
+
bits.push(w.checks(ok, checks.length - ok - skipped, skipped, checks.length))
|
|
191
|
+
}
|
|
192
|
+
return bits.join(w.dot)
|
|
193
|
+
}
|
|
194
|
+
|
|
195
|
+
export function glanceFor(results, running = [], lang = 'en') {
|
|
196
|
+
const w = WORDS[lang] ?? WORDS.en
|
|
197
|
+
const lines = results.length === 1
|
|
198
|
+
? [`dsh-baton${w.dot}${results[0].run_id}${w.sep}${runLine(results[0], w)}`]
|
|
199
|
+
: [w.many(results.length), ...results.map((r) => `- ${r.run_id}${w.sep}${runLine(r, w)}`)]
|
|
200
|
+
if (running.length) lines.push(w.running(running))
|
|
201
|
+
return lines.join('\n')
|
|
202
|
+
}
|
|
203
|
+
|
|
204
|
+
// What the model is told: a glance for the person first, then each run's result as
|
|
205
|
+
// dsh_wait returns it, and which runs of the same batch are still going (when one came
|
|
206
|
+
// back early to ask something or failed).
|
|
207
|
+
// Should the glance fail on an odd result, the model still gets everything.
|
|
208
|
+
function reasonFor(results, running, lang) {
|
|
209
|
+
let glance = ''
|
|
210
|
+
try { glance = `${glanceFor(results, running, lang)}\n\n` } catch { /* results only */ }
|
|
211
|
+
return `${glance}${modelPart(results, running)}`
|
|
212
|
+
}
|
|
213
|
+
|
|
214
|
+
function modelPart(results, running) {
|
|
86
215
|
const one = results.length === 1 ? results[0] : null
|
|
87
216
|
const what = one
|
|
88
217
|
? `the Harness run ${one.run_id} you handed over with dsh_send has ${one.needs_input ? 'stopped to ask a question' : `ended (${one.state})`}`
|
|
@@ -94,6 +223,23 @@ function reasonFor(results, running) {
|
|
|
94
223
|
return `dsh-baton: ${what}.${still} ${one ? 'This is its result' : 'These are their results'}, as dsh_wait would return ${one ? 'it' : 'them'}; act on ${one ? 'it' : 'them'} now (follow the hints):\n${body}`
|
|
95
224
|
}
|
|
96
225
|
|
|
226
|
+
// What Codex shows the user for the wake (systemMessage), instead of the JSON in reason:
|
|
227
|
+
// a short line per run with its id and state, in Codex's language. The model reads reason only.
|
|
228
|
+
export function summaryFor(results, running = [], lang = 'en') {
|
|
229
|
+
if (lang === 'zh') {
|
|
230
|
+
const one = (r) => r.needs_input ? `${r.run_id} 在等回答` : `${r.run_id}（${r.state}）`
|
|
231
|
+
const head = results.length === 1
|
|
232
|
+
? (results[0].needs_input ? `dsh-baton：Harness 任务 ${one(results[0])}，问题已交给 Codex` : `dsh-baton：Harness 任务 ${one(results[0])}已结束，结果已交回 Codex`)
|
|
233
|
+
: `dsh-baton：${results.length} 个 Harness 任务已交回 Codex：${results.map(one).join('，')}`
|
|
234
|
+
return running.length ? `${head}；还在运行 ${running.length} 个` : head
|
|
235
|
+
}
|
|
236
|
+
const one = (r) => r.needs_input ? `${r.run_id} waiting for an answer` : `${r.run_id} (${r.state})`
|
|
237
|
+
const head = results.length === 1
|
|
238
|
+
? (results[0].needs_input ? `dsh-baton: Harness run ${one(results[0])}, question passed to Codex` : `dsh-baton: Harness run ${one(results[0])} ended, result passed to Codex`)
|
|
239
|
+
: `dsh-baton: ${results.length} Harness runs passed to Codex: ${results.map(one).join(', ')}`
|
|
240
|
+
return running.length ? `${head}; ${running.length} still running` : head
|
|
241
|
+
}
|
|
242
|
+
|
|
97
243
|
// The JSON Codex writes to the hook's stdin, or null. A leading BOM is dropped (seen on
|
|
98
244
|
// Windows). Input that does not parse is kept (its first 4 KB) in last-bad-stdin, so a
|
|
99
245
|
// hook that ran and gave up can be told from one Codex never ran.
|
|
@@ -122,7 +268,7 @@ function ranAs() {
|
|
|
122
268
|
// last of them ends, with all their results, so it reviews the parallel parts together.
|
|
123
269
|
// A run that stops to ask a question or fails wakes it at once (with whatever else has
|
|
124
270
|
// ended by then); the rest keep waiting for the next Stop.
|
|
125
|
-
export async function runHook(input, { shape, wait = core.api.wait, now = Date.now, chunk_s = 10, self = ranAs() } = {}) {
|
|
271
|
+
export async function runHook(input, { shape, wait = core.api.wait, now = Date.now, chunk_s = 10, self = ranAs(), lang } = {}) {
|
|
126
272
|
fs.mkdirSync(dir(), { recursive: true, mode: 0o700 })
|
|
127
273
|
fs.writeFileSync(aliveFile(), JSON.stringify({ at: now(), ...self }))
|
|
128
274
|
const thread = input?.session_id
|
|
@@ -152,8 +298,12 @@ export async function runHook(input, { shape, wait = core.api.wait, now = Date.n
|
|
|
152
298
|
if (st.needs_input || st.state !== 'completed') urgent = true
|
|
153
299
|
}
|
|
154
300
|
if (ended.size && (urgent || !running.length)) {
|
|
301
|
+
// Marked delivered only once the message exists, so a failure here loses no result.
|
|
302
|
+
const results = [...ended].map(([run_id, st]) => ({ run_id, ...shape(st) }))
|
|
303
|
+
const language = lang ?? codexLang()
|
|
304
|
+
const out = { decision: 'block', reason: reasonFor(results, running, language), systemMessage: summaryFor(results, running, language) }
|
|
155
305
|
for (const [runId, st] of ended) delivered(runId, st)
|
|
156
|
-
return
|
|
306
|
+
return out
|
|
157
307
|
}
|
|
158
308
|
if (!running.length) return null
|
|
159
309
|
if (now() > deadline) return null
|
|
@@ -161,6 +311,6 @@ export async function runHook(input, { shape, wait = core.api.wait, now = Date.n
|
|
|
161
311
|
}
|
|
162
312
|
|
|
163
313
|
// The hook entry for Codex's config.toml (see register.mjs, which also writes it).
|
|
164
|
-
export function hookCommand(root = core.ROOT, node = stableNodePath(), { platform } = {}) {
|
|
165
|
-
return codexHookEntry(node, path.join(root, 'src', 'server.mjs'), { platform, home: core.config.batonHome })
|
|
314
|
+
export function hookCommand(root = core.ROOT, node = stableNodePath(), { platform, harness = Boolean(process.versions.electron) } = {}) {
|
|
315
|
+
return codexHookEntry(node, path.join(root, 'src', 'server.mjs'), { platform, home: core.config.batonHome, harness })
|
|
166
316
|
}
|
package/src/mcp.mjs
CHANGED
|
@@ -5,7 +5,7 @@ import path from 'node:path'
|
|
|
5
5
|
import * as core from './core.mjs'
|
|
6
6
|
import { stableNodePath } from './setup.mjs'
|
|
7
7
|
import { conversationFolder, within } from './folder.mjs'
|
|
8
|
-
import { threadOf, remember, delivered, hookActive, hookUntrusted, noteOnce } from './codex-hook.mjs'
|
|
8
|
+
import { threadOf, remember, delivered, hookActive, hookUntrusted, hookSkipReason, noteOnce } from './codex-hook.mjs'
|
|
9
9
|
|
|
10
10
|
const SERVER = { name: 'dsh-baton', version: core.VERSION }
|
|
11
11
|
const PROTOCOLS = ['2025-06-18', '2025-03-26', '2024-11-05']
|
|
@@ -36,6 +36,7 @@ const codeModeYield = () => {
|
|
|
36
36
|
// while dsh-baton's Stop hook is waiting to be trusted.
|
|
37
37
|
const TRUST_NOTE = 'One step left: in Codex, open Settings → Hooks and trust the Stop hook "dsh-baton: waiting for the Harness run". After that, Codex no longer uses your quota while it waits for DeepSeek Harness.'
|
|
38
38
|
const NO_POLL = 'While waiting, make no other calls (no dsh_status, dsh_session_activity or dsh_read_session) and do not list or read the target folder to check progress.'
|
|
39
|
+
const INSTRUCTIONS = 'Hands tasks to a local DeepSeek Harness and brings the results back: start with dsh_send.'
|
|
39
40
|
const ARCHIVED = 'Sessions not in dsh_list_sessions are archived or gone: do not look for them on disk.'
|
|
40
41
|
// A shell command that blocks until a run ends and prints its reply. Run in the
|
|
41
42
|
// background by a client that wakes the model when the command exits (Claude Code),
|
|
@@ -125,8 +126,8 @@ const TOOLS = [
|
|
|
125
126
|
{
|
|
126
127
|
name: 'dsh_send',
|
|
127
128
|
annotations: annotations('Send message', hints(false, false, false)),
|
|
128
|
-
description: '
|
|
129
|
-
inputSchema: { type: 'object', required: ['message'], properties: { message: str('The task or reply to send'), session_id: str('Existing session to continue'), cwd: str('Workspace folder for a new session; leave out to use the folder this conversation works in'), workspace_id: str('Harness workspace for a new session (from dsh_list_workspaces)'), mode: { type: 'string', enum: ['followup', 'steer'], description: "followup queues after the current turn; steer injects into a running turn. Omit to follow Harness's busy-send setting" }, model: str('Only when the user names a model for this run (e.g. "DeepSeek-V4 Pro", "v4-pro"); leave out otherwise and the session uses its own model, or Harness\'s default model for a new session. Matched against Harness\'s model list ignoring case, spaces, hyphens and a leading DeepSeek; a name that matches no model or several fails the send with the list (provider/model picks one). Sets this session only; Harness\'s default model is left as it was'), reasoning_effort: str('Only when the user names a reasoning effort, e.g. high; one of the efforts dsh_list_models shows for the model'), checks: { type: 'array', items: { type: 'string' }, description: 'The project\'s own test commands, e.g. npm test
|
|
129
|
+
description: 'Hand a task to DeepSeek Harness, or continue a session: returns at once with a run_id and a hint saying how to wait for the reply; follow it. Call it directly, no need to list anything first. A new session starts in the folder this conversation works in, or in cwd or workspace_id (a new cwd is registered first); session_id continues that session. message arrives verbatim as a user message, and Harness does not see this conversation: make it self-contained, in the user\'s language, the full, explicit spec, asking for tests that cover each requirement. For a large task, write a concrete spec (goal, modules and the files each owns, level of detail, acceptance criteria) rather than passing the user\'s words on, and send independent parts to separate sessions in parallel, each owning its own files; review once all are back, then send specific fixes. With checks, a short request for a sub-agent review table is appended. To a busy session, mode followup queues the message and steer adds it to the running turn; left out, the Harness setting decides.',
|
|
130
|
+
inputSchema: { type: 'object', required: ['message'], properties: { message: str('The task or reply to send'), session_id: str('Existing session to continue'), cwd: str('Workspace folder for a new session; leave out to use the folder this conversation works in'), workspace_id: str('Harness workspace for a new session (from dsh_list_workspaces)'), mode: { type: 'string', enum: ['followup', 'steer'], description: "followup queues after the current turn; steer injects into a running turn. Omit to follow Harness's busy-send setting" }, model: str('Only when the user names a model for this run (e.g. "DeepSeek-V4 Pro", "v4-pro"); leave out otherwise and the session uses its own model, or Harness\'s default model for a new session. Matched against Harness\'s model list ignoring case, spaces, hyphens and a leading DeepSeek; a name that matches no model or several fails the send with the list (provider/model picks one). Sets this session only; Harness\'s default model is left as it was'), reasoning_effort: str('Only when the user names a reasoning effort, e.g. high; one of the efforts dsh_list_models shows for the model'), checks: { type: 'array', items: { type: 'string' }, description: 'The project\'s own test commands, e.g. npm test; never check scripts you write yourself. dsh-baton runs them in the folder when the run ends and returns exit codes and the last output lines as evidence.' } } },
|
|
130
131
|
run: async (a, { meta } = {}) => {
|
|
131
132
|
// A new session goes to this conversation's folder unless the call names another one;
|
|
132
133
|
// a different folder is allowed but said back, so a wrong guess does not go unnoticed.
|
|
@@ -147,9 +148,13 @@ const TOOLS = [
|
|
|
147
148
|
return { ...st, hint: `Run started. End your turn now: reply to the user in one short line (in their language) that the task is with DeepSeek Harness. Do not call dsh_wait, dsh_status or any other tool, and do not read the target folder. When all the runs you started end (or one stops to ask something or fails), dsh-baton continues this conversation by itself with their results together (as dsh_wait returns them), so you review them in one go. If the conversation is ever resumed without it, call dsh_wait with this run_id.` }
|
|
148
149
|
}
|
|
149
150
|
// Not trusted yet: the user is told once per conversation, until they trust it.
|
|
150
|
-
const
|
|
151
|
+
const untrusted = thread && hookUntrusted()
|
|
152
|
+
const note = untrusted && noteOnce(thread) ? { note_for_user: TRUST_NOTE } : null
|
|
151
153
|
const relay = note ? 'First, start your reply to the user with note_for_user, in their language, on a line of its own. ' : ''
|
|
152
|
-
|
|
154
|
+
// Not added at all: the reason, once per conversation.
|
|
155
|
+
const reason = thread && !untrusted ? hookSkipReason() : null
|
|
156
|
+
const why = reason && noteOnce(thread) ? `${reason} Tell the user so in one line, in their language. ` : ''
|
|
157
|
+
return { ...st, ...note, hint: `${relay}${why}Run started. Call dsh_wait with this run_id; it returns when the run ends or stops to ask the user something. ${NO_POLL} ${codeModeYield()}` }
|
|
153
158
|
}
|
|
154
159
|
return {
|
|
155
160
|
...st,
|
|
@@ -168,7 +173,7 @@ const TOOLS = [
|
|
|
168
173
|
{
|
|
169
174
|
name: 'dsh_wait',
|
|
170
175
|
annotations: annotations('Wait for run'),
|
|
171
|
-
description: () => `Wait for a run sent with dsh_send to end and return its state and final reply.${isCodex() ? '
|
|
176
|
+
description: () => `Wait for a run sent with dsh_send to end and return its state and final reply.${!isCodex() ? ' Prefer the background wait_command from dsh_send if your client wakes you when a background command exits: it costs no turns.' : hookActive() ? ' Call it only when a hint says so: when dsh_send\'s hint says to end your turn, end it, and the result comes back by itself.' : ''} It also returns at once when the run stops to ask a person: needs_input answer (question and relay; reply with dsh_answer) or harness-ui (an approval only a person can give in Harness). Each call waits up to ${waitSeconds()} s; if it returns timed_out: true, call dsh_wait again with the same run_id, without a progress note.${isCodex() ? ` ${NO_POLL} ${codeModeYield()}` : ''}`,
|
|
172
177
|
inputSchema: { type: 'object', required: ['run_id'], properties: { run_id: str('Run id from dsh_send') } },
|
|
173
178
|
run: async (a, { progress }) => {
|
|
174
179
|
const result = await waitInChunks(a, progress)
|
|
@@ -180,7 +185,7 @@ const TOOLS = [
|
|
|
180
185
|
{
|
|
181
186
|
name: 'dsh_answer',
|
|
182
187
|
annotations: annotations('Answer question', hints(false, false, false)),
|
|
183
|
-
description:
|
|
188
|
+
description: `Answer the questions a waiting run asked (needs_input: answer in dsh_wait or dsh_status). ${core.ASKED} Per question: option numbers or labels in choose, text for a free answer, or skip. The answer reaches Harness once every question has one (submitted: true; remaining lists the rest); then wait for the run again. If the user already answered in Harness, it reports that there is no open question.`,
|
|
184
189
|
inputSchema: {
|
|
185
190
|
type: 'object', required: ['run_id', 'answers'], properties: {
|
|
186
191
|
run_id: str('Run id that is waiting (needs_input: answer)'),
|
|
@@ -298,7 +303,10 @@ async function handle(req) {
|
|
|
298
303
|
protocolVersion: PROTOCOLS.includes(asked) ? asked : PROTOCOLS[0],
|
|
299
304
|
capabilities: { tools: {} },
|
|
300
305
|
serverInfo: SERVER,
|
|
301
|
-
|
|
306
|
+
// One sentence: Codex repeats it in front of every tool's description, while a client
|
|
307
|
+
// that lists MCP tools by name only (Claude Code's tool search) still learns what the
|
|
308
|
+
// server is for. The rules live in the tools' own descriptions.
|
|
309
|
+
instructions: INSTRUCTIONS,
|
|
302
310
|
}
|
|
303
311
|
}
|
|
304
312
|
case 'ping':
|
package/src/register.mjs
CHANGED
|
@@ -130,13 +130,17 @@ export const hookWrapperPath = (home = batonHome(), platform = process.platform)
|
|
|
130
130
|
// A path with spaces (a user name with a space): on Windows its 8.3 short form, else
|
|
131
131
|
// PowerShell's call form of the whole line (PowerShell being Codex's shell on Windows);
|
|
132
132
|
// elsewhere the path in double quotes, for the shell Codex runs the command with.
|
|
133
|
-
|
|
133
|
+
//
|
|
134
|
+
// harness: node is Harness's own binary (no Node.js of the user's own, see harnessRuntime),
|
|
135
|
+
// which runs cli.mjs only in Node mode, so the wrapper sets ELECTRON_RUN_AS_NODE=1 first.
|
|
136
|
+
// The entry stays the same either way: only the script changes.
|
|
137
|
+
export function codexHookEntry(node, script, { platform = process.platform, home = batonHome(), shortPath = winShortPath, harness = false } = {}) {
|
|
134
138
|
const line = codexHookCommand(node, script)
|
|
135
139
|
const file = hookWrapperPath(home, platform)
|
|
136
140
|
const sh = (p) => `'${p.replace(/'/g, `'\\''`)}'`
|
|
137
141
|
const body = platform === 'win32'
|
|
138
|
-
?
|
|
139
|
-
: `#!/bin/sh\
|
|
142
|
+
? `${harness ? '@set ELECTRON_RUN_AS_NODE=1\r\n' : ''}@${line.replace(/%/g, '%%')}\r\n`
|
|
143
|
+
: `#!/bin/sh\n${harness ? 'ELECTRON_RUN_AS_NODE=1 ' : ''}exec ${sh(node)} ${sh(path.join(path.dirname(script), 'cli.mjs'))} codex-stop-hook "$@"\n`
|
|
140
144
|
fs.mkdirSync(path.dirname(file), { recursive: true })
|
|
141
145
|
let old = null
|
|
142
146
|
try { old = fs.readFileSync(file, 'utf8') } catch { /* first time */ }
|
|
@@ -145,7 +149,7 @@ export function codexHookEntry(node, script, { platform = process.platform, home
|
|
|
145
149
|
if (!/\s/.test(file)) return file
|
|
146
150
|
if (platform !== 'win32') return JSON.stringify(file)
|
|
147
151
|
const at = shortPath(file)
|
|
148
|
-
return at && !/\s/.test(at) ? at :
|
|
152
|
+
return at && !/\s/.test(at) ? at : `${harness ? "$env:ELECTRON_RUN_AS_NODE='1'; " : ''}& ${line}`
|
|
149
153
|
}
|
|
150
154
|
|
|
151
155
|
// The 8.3 short form of an existing path, or null (8.3 names can be off for a drive).
|
|
@@ -443,24 +447,39 @@ export function autoRegister({ root, home = os.homedir(), env = process.env, nod
|
|
|
443
447
|
|
|
444
448
|
// The Codex Stop hook goes in with the server, so Codex waits for runs without model
|
|
445
449
|
// requests (see codex-hook.mjs). It runs cli.mjs beside the server Codex is set up with,
|
|
446
|
-
// with the same
|
|
447
|
-
// Hooks); until then dsh-baton keeps to
|
|
448
|
-
//
|
|
450
|
+
// with the same runtime: the user's Node.js, or Harness's own in Node mode. Codex runs a
|
|
451
|
+
// new hook only once the user trusts it (Settings → Hooks); until then dsh-baton keeps to
|
|
452
|
+
// dsh_wait. Not added without Codex, with DSH_BATON_CODEX_HOOK=0, or when the entry has
|
|
453
|
+
// no cli.mjs to run (a bare command such as npx, or a server folder that is gone).
|
|
454
|
+
// What happened, and why, is noted in hookResultFile for dsh_send to pass on.
|
|
449
455
|
function addCodexHook(codex, env, fallback, home) {
|
|
456
|
+
const done = (state, reason = null, command = null) => {
|
|
457
|
+
try {
|
|
458
|
+
const file = hookResultFile(env, home)
|
|
459
|
+
fs.mkdirSync(path.dirname(file), { recursive: true, mode: 0o700 })
|
|
460
|
+
fs.writeFileSync(file, JSON.stringify({ state, reason, command, at: Date.now() }))
|
|
461
|
+
} catch { /* nowhere to note it */ }
|
|
462
|
+
return state
|
|
463
|
+
}
|
|
450
464
|
try {
|
|
451
|
-
if (!codex?.present
|
|
465
|
+
if (!codex?.present) return 'off'
|
|
466
|
+
if (env.DSH_BATON_CODEX_HOOK === '0') return done('off', 'disabled')
|
|
452
467
|
const e = readCodexEntry(fs.existsSync(codex.file) ? fs.readFileSync(codex.file, 'utf8') : '')
|
|
453
468
|
const script = e?.args?.[0]
|
|
454
|
-
|
|
455
|
-
|
|
456
|
-
|
|
457
|
-
|
|
458
|
-
|
|
459
|
-
|
|
460
|
-
return 'failed'
|
|
469
|
+
if (!e || !/[\\/]/.test(e.command) || !script || !fs.existsSync(path.join(path.dirname(script), 'cli.mjs'))) return done('skipped', 'no-cli')
|
|
470
|
+
const harness = e.env?.ELECTRON_RUN_AS_NODE === '1' || Boolean(fallback && path.resolve(e.command) === path.resolve(fallback.command))
|
|
471
|
+
const entry = codexHookEntry(e.command, script, { home: batonHome(env, home), harness })
|
|
472
|
+
return done(rewrite(codex.file, (t) => editCodexHook(t, entry)) === 'updated' ? 'added' : 'unchanged', null, entry)
|
|
473
|
+
} catch (err) {
|
|
474
|
+
return done('failed', err.message)
|
|
461
475
|
}
|
|
462
476
|
}
|
|
463
477
|
|
|
478
|
+
// What the plugin last did about the hook ({ state, reason, command, at }), see addCodexHook.
|
|
479
|
+
// command is the hook command as written to config.toml (the wrapper path, its 8.3 form,
|
|
480
|
+
// or PowerShell's call form), so a check need not parse TOML.
|
|
481
|
+
export const hookResultFile = (env = process.env, home = os.homedir()) => path.join(batonHome(env, home), 'codex-hook', 'registered.json')
|
|
482
|
+
|
|
464
483
|
// Where the Stop hook notes each run (codex-hook.mjs): when, and the node and cli.mjs it
|
|
465
484
|
// ran as, so a hook rewritten since can be told from the one Codex trusted.
|
|
466
485
|
export const hookAliveFile = (env = process.env, home = os.homedir()) => path.join(batonHome(env, home), 'codex-hook', 'alive')
|