dsh-pr-watch
DeepSeek Harness 插件：报告你创建的 pull request 自上次检查以来的变化——已合并、已关闭或已变得过时。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:Shyboy0499/dsh-pr-watch#00d98fa286dae02db38fba7e7ea5378031c42eb6Pr Watch 以 dsh-pr-watch 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Reports what changed in your authored pull requests since your last check — merged, closed, or gone stale.
dsh-pr-watch is a dependency-free DeepSeek Harness (dsh) plugin that exposes one agent tool, pr_watch. It tracks every pull request you authored, across all repositories — including ones you have never cloned — and tells you only what changed since you last looked.
Status: pre-release. The design and implementation plan are complete; the implementation is in progress. Nothing is published to npm yet, so the install command below does not work today. It is included so the intended path is clear, not because it is ready.
An agent has no memory of your last check, so every status question gets re-derived from scratch. That is fine for one pull request and useless for thirty. The friction is not seeing your pull requests — it is re-checking the same ones over and over and having to remember what the state was last time.
pr_watch closes that gap by storing a snapshot and reporting deltas.
| Behaviour | Detail |
|---|---|
| Merged | A pull request you authored was merged |
| Closed without merge | Distinguished from a merge, not lumped in with it |
| Became stale | No activity for 14 days (configurable) |
| Newly noticed | A pull request appeared that the snapshot did not know about |
| Uncloned repositories | Tracked by owner/repo#number, so a local checkout is never required |
| Reported once, then silent | Merges and staleness never repeat on later checks |
The naive approach — fetch open pull requests, diff against the snapshot — cannot work. The moment a pull request merges it leaves the open list, so a bare diff cannot tell "merged" from "closed unmerged", and an empty result looks identical to a failed gh call.
So pr_watch fetches in two phases:
Only pull requests that actually changed incur a second call — normally zero or one per check.
dsh plugin --profile web add dsh-pr-watch
Not yet published — see the status note above.
Requires the GitHub CLI (gh) on your PATH, authenticated:
gh auth login
dsh-pr-watch stores no credentials of its own. It relies entirely on gh's own keyring-backed authentication.
Ask the agent to check your pull requests, or call the tool directly.
{
"staleDays": 14,
"all": false
}
Typical output:
✅ Merged (2):
octo/repo#41 — Add Russian locale (last activity 1 day ago)
octo/repo#38 — Fix broken link (last activity 3 days ago)
⏳ Became stale (1):
octo/repo#29 — docs: clarify install steps (last activity 21 days ago)
🆕 Newly noticed (1):
octo/repo#44 — Add MCP server entry (last activity today)
Run it a second time and only genuine changes appear. A merge reported today is never reported again.
| Parameter | Type | Description |
|---|---|---|
staleDays | number | Days without activity before a pull request counts as stale. Defaults to 14. |
all | boolean | List every open pull request instead of only what changed. Useful on first run, where everything is "newly noticed". Defaults to false. |
v1 exposes everything through the tool's two parameters above. It reads no settings file, so there is nothing else to configure yet.
| Setting | Default | Settable in v1 | Purpose |
|---|---|---|---|
staleDays | 14 | Yes — tool parameter | Days without activity before a pull request is reported stale |
pruneDays | 90 | No — compile-time constant | Drop entries that reached a terminal state this long ago |
| Snapshot path | $DSH_HOME/pr-watch/snapshot.json | No — derived from the environment | Falls back to ~/.dsh/pr-watch/snapshot.json when DSH_HOME is unset |
Two further keys appear in the design doc —
ignoreRepos and a user-settable snapshotPath — but they are deferred to v2
and not implemented. Honouring them needs a settings loader that does not exist
yet, and ignoreRepos additionally needs a rule to evict ignored entries from
the snapshot: an entry dropped from enumeration but kept in the snapshot would
never resolve, so every check would report it as unresolved forever. See the
plan's refinements section for the full reasoning.
gh fails partway through, the snapshot is left untouched so pending changes are not silently marked as seen.snapshot.json.corrupt-<n> and the tool says so in its output. The alternative — silently resetting — would lose pending changes with no way to tell that from "nothing happened".A pull request opened and merged between two checks is invisible. It is absent from the open set (it already merged) and absent from the snapshot (it did not exist when the snapshot was taken), so neither phase sees it. This is a direct consequence of enumerating by current state rather than by activity window, and it only becomes likely if you check infrequently. The fix — an activity-window query — is recorded in the design doc as a v2 candidate.
New comments and reviews are not reported. An outcome like "merged" is not the same as "a maintainer replied asking for changes", and the latter is often what should change your next action. It is deferred rather than overlooked: it needs a separate data source and a per-entry comment cursor.
CI status is not reported.
One snapshot per GitHub identity. Running under a second account would share a snapshot and produce spurious "newly noticed" entries.
pnpm install
pnpm run build # tsdown → lib/
pnpm test # vitest — no network access
pnpm run lint # oxlint
pnpm run typecheck # tsc --noEmit
pnpm run format # prettier --write .
The test suite makes no network requests. delta.ts is pure — no filesystem, no network, no clock — so every state-transition rule is a fixture-driven unit test with no mocking.