feat(deepseek): add DeepSeek Harness (dsh) as a ninth CLI run mode

Adds `mode: 'deepseek'` alongside claude/shell/opencode/codex/gemini/
antigravity/pi/grok, plus a shortcut that opens the harness's own browser UI
as a Codeman web tab.

DeepSeek is wired unlike its siblings in three ways, each of which is the
reason for a design decision rather than an accident:

1. The agent is a PROFILE, not the binary. `dsh` is a launcher over
   $DSH_HOME/profiles/<name>, and DeepSeek ships only `web`, `headless` and
   `base` -- the interactive terminal front door is always a third-party
   plugin. So availability is two questions: `isDeepSeekAvailable()` (binary)
   and `isDeepSeekRunnable()` (binary AND a pane-capable profile). The Run
   button gates on the latter, because reporting only the binary would spawn a
   pane that dies on arrival. When the binary is present but no profile is,
   the run menu offers to install one (POST /api/deepseek/install-profile).

2. The permission switch is an env var, not a flag. The harness has no
   command-line permission option; its sandbox/approval rows read
   DSH_PERMISSION_MODE (read-only / workspace-write / danger-full-access).
   Exported via `tmux setenv`, never on the spawn line. Absent = the harness's
   own workspace-write, which still asks, so the multi-user clamp is the
   only-if-sent branch and clamps to workspace-write, never read-only.

3. It is the only non-claude mode that passes hooksAvailableForMode(), and it
   earned that. The terminal front door reports idle/working/blocked to a
   supervising process over a generic env-gated contract; a generated shim
   (deepseek-status-shim.ts) makes Codeman that supervisor and forwards each
   report to /api/hook-event as stop / agent_working / permission_prompt. So a
   dsh session gets definitive respawn triggers, real wait-endpoint signals and
   real Approvals Inbox items instead of output-stabilization guesswork.
   `agent_working` is new (157th SSE constant) and joins
   APPROVAL_RESOLVING_EVENTS so a dialog answered in the terminal clears its
   alert at once.

The resolver needs the strictest identity probe of the family: `dsh` is not
merely a squattable npm name, Debian ships an unrelated `dsh` (dancer's shell),
so `dsh --help` must print the harness's own banner before a candidate is
handed a spawn line.

Model is deliberately not a session field -- it is a composition entry in the
profile's config tree. Env allowlist gains DSH_* and DEEPSEEK_* only; provider
keys named by a settings-file `apiKeyEnv` stay out, which is pi's
34-provider-key problem in a new shape.

Verified live against dsh 0.1.1-rc.2 and @deepseek-harness-tui/dsh-tui: the
status endpoint's two-part answer, the no-profile refusal, the profile
bootstrap, a real session whose pane runs `dsh --profile dsh-tui` with the
permission mode injected via setenv, and the full status bridge -- a
send-and-wait returned signal "stop" from a real turn, and blocked/working
created and cleared an Approvals Inbox item.

Docs: docs/deepseek-integration.md (guide), docs/deepseek-integration-plan.md
(decisions + honest gaps). Tests: test/deepseek-mode.test.ts,
test/deepseek-cli-resolver.test.ts.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer
2026-08-24 03:37:56 +02:00
parent 9cfd8e8989
commit 4cda150493
48 changed files with 2489 additions and 66 deletions
+4 -4
View File
@@ -237,7 +237,7 @@ minutes, never retry the credential.
flushed slightly *after* the `stop` hook fires, so a read taken the instant the wait
returns is too early (verified live: empty on the first call, full prose seconds later).
It is also `""` before the worker's first completed turn, and permanently `""` for
`shell`, `opencode`, `gemini`, `antigravity`, `pi` and `grok`, which write no Claude transcript.
`shell`, `opencode`, `gemini`, `antigravity`, `pi`, `grok` and `deepseek`, which write no Claude transcript.
**Fix** Poll it, bounded (10 tries, 1 s apart). If it is still empty on a hook-less mode,
that is expected, not a failure: read `terminal?tail=` and strip ANSI instead.
@@ -336,14 +336,14 @@ ESC=$(printf '\033')
`POST /api/v1/quick-start` body (all optional):
`{"caseName":"worker-1","mode":"claude","sessionName":"w9-worker","effort":"high"}`
, `mode` ∈ `claude|shell|opencode|codex|gemini|antigravity|pi|grok`; response is
, `mode` ∈ `claude|shell|opencode|codex|gemini|antigravity|pi|grok|deepseek`; response is
`.data.{sessionId, caseName, casePath}`. Creates the case directory (a real directory
on the user's disk) if missing, do not retry it in a loop, and remember the name.
⚠️ A `mode` whose CLI is **not installed on the server** fails the spawn with
`OPERATION_FAILED`; it never falls back to claude. Probe first whenever you did not pick
the mode yourself: `GET /api/v1/claude/status`, `GET /api/v1/opencode/status`,
`GET /api/v1/codex/status`, `GET /api/v1/gemini/status`, `GET /api/v1/antigravity/status`, `GET /api/v1/grok/status`
`GET /api/v1/codex/status`, `GET /api/v1/gemini/status`, `GET /api/v1/antigravity/status`, `GET /api/v1/grok/status`, `GET /api/v1/deepseek/status`
and `GET /api/v1/pi/status` each return `.data.{available, path}` (no session needed).
Pi's and grok's also carry `.data.version`, because `pi` is a short generic name and
`grok` is a name with npm squatters, so an unrelated binary on `$PATH` can shadow either:
@@ -464,7 +464,7 @@ Quirks that will bite you:
- ⚠️ **`active-tools` proves presence, never absence.** It is fed by the BashToolParser,
which reads Claude's rendered `● Bash(…)` lines, and `_processExpensiveParsers`
returns early for every external CLI mode (`session.ts:2261`), so it is permanently
`[]` on `opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`. ⚠️ **`shell` is NOT one of those**
`[]` on `opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`/`deepseek`. ⚠️ **`shell` is NOT one of those**
(`isExternalCliMode`, `session.ts:174-183`, lists only those six), so the parser does
run on a shell worker, and `TEXT_COMMAND_PATTERN` (`bash-tool-parser.ts:89`) matches
bare `tail|cat|head|less|grep|watch|multitail <path>` lines with no `● Bash(` wrapper:
+2 -2
View File
@@ -56,7 +56,7 @@ own head: the worker enforcing the cap is the one who has to be told about it.
| synchronize on end of turn | HTTP `wait until=stop` (fires for message-initiated turns too, verified live) |
| liveness / death check | HTTP `wait?until=exit` |
| interrupt a running turn (break-glass) | HTTP input, a bare `\x1b` with no `\r` |
| non-claude modes (`shell`/`opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`) | HTTP only (no other CLI has messaging) |
| non-claude modes (`shell`/`opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`/`deepseek`) | HTTP only (no other CLI has messaging) |
| delete | HTTP, via SKILL.md's `delete_session` guard |
## Availability: probe, never assume
@@ -347,7 +347,7 @@ Without a break-glass, a pair with a bad brief is a token bonfire with no off sw
### Mixed fleets: the pairing matrix
Non-claude workers (`shell`, `opencode`, `codex`, `gemini`, `antigravity`, `pi`, `grok`) cannot be peers
Non-claude workers (`shell`, `opencode`, `codex`, `gemini`, `antigravity`, `pi`, `grok`, `deepseek`) cannot be peers
at all; no other CLI has this feature. Their tasks route over HTTP, and you never mention
messaging in their briefs. The claude half of the fleet can use messaging among itself,
subject to the namespace rule: **messaging works between two sessions that share one
+1 -1
View File
@@ -188,7 +188,7 @@ for _ in $(seq 1 10); do
done
printf '%s\n' "$TXT"
# (.data is {text,timestamp}; text is also "" before the first completed turn and
# always "" for shell/opencode/gemini/antigravity/pi/grok, which have no transcript, use
# always "" for shell/opencode/gemini/antigravity/pi/grok/deepseek, which have no transcript, use
# the terminal tail there, and here only to diagnose an unsubmitted prompt.)
# 6. clean up: exact id, own list only, through the fail-closed preamble helper
+3 -3
View File
@@ -343,7 +343,7 @@ recovered by submitting it with `{"input":"\r"}`.
⚠️ `stop` and `blocked` fire for `claude` sessions only (they are Claude Code hooks,
and only when the workspace actually has them, see [§5.1](#51-where-to-spawn)). On
`shell`/`opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`, requesting them explicitly is a
`shell`/`opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`/`deepseek`, requesting them explicitly is a
400, and lifecycle transitions there are coarse (a short shell command may emit **no**
`idle` transition at all, verified live), so synchronize those with markers.
@@ -369,7 +369,7 @@ from the transcript file, which is flushed slightly *after* the `stop` hook fire
single read taken the instant send-and-wait returns comes back `""` even though the
turn finished (verified live: empty on the first call, full text seconds later). `text`
is also `""` before the worker's first completed turn, and always `""` for modes with
no transcript (`shell`, `opencode`, `gemini`, `antigravity`, `pi`, `grok`; the first four
no transcript (`shell`, `opencode`, `gemini`, `antigravity`, `pi`, `grok`, `deepseek`; the first four
verified live, pi from the same source path), which is
why the loop above is bounded rather than open-ended. Fall back to the terminal buffer
there, tail in **bytes** (`textOutput` in `GET .../output` stays empty for interactive
@@ -454,7 +454,7 @@ turn), and both better than diffing terminal samples:
```
⚠️ `active-tools` is parsed out of Claude's own output format, so it is **empty for
`opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`** (those parsers are skipped wholesale) and
`opencode`/`codex`/`gemini`/`antigravity`/`pi`/`grok`/`deepseek`** (those parsers are skipped wholesale) and
in practice empty for `shell`. Source-verified, not measured live.
Only if neither helps: sample `terminal?tail=` twice a few seconds apart. A changing