@joshuafolkken/kit 1.1514.0 → 1.2114.0

package/.claude/skills/workflow-commands/pre-gate-cut.md

@@ -17,20 +17,12 @@ the fallback.
 ## It applies to a dispatched lane child, and to nothing else
 
 A person's interactive `fullrun` never relaunches itself. A dispatched child is told apart
-**mechanically, by a mark the dispatch sets** — never by reading its own prompt.
+**mechanically, by the `JOSH_LANE_CHILD` mark the dispatch sets** — never by reading its own prompt
+(`docs/josh-commands-run.md` → "`josh run:cut`").
 
-### The dispatch mark
-
-`lane:dispatch` starts each child generation with **`JOSH_LANE_CHILD`** set to the lane's issue number
-(`scripts/lane/lane-child-marker.ts`).
-
-- **Meaning**: "this session was launched for issue `<N>`, not typed by a person."
-- **Lifetime**: the child process — set at launch, never written by the run itself.
-- **Trust**: only where its value equals the lane's own issue; a leaked mark naming another issue, or
-  none, is read as a person. An interactive `fullrun` carries no mark.
-
-The name, meaning and lifetime are documented here and nowhere else. `run:cut` itself looks for an
-**open lane** for the issue instead (`not-a-lane` otherwise), so it is safe to issue unconditionally.
+An interactive `fullrun` carries no mark, and every
+guard in this file holds that boundary: **It fires for a marked child and nowhere else**. `run:cut`
+answers `not-a-lane` outside a lane, so it is safe to issue unconditionally.
 
 ## Taking the cut
 
@@ -43,29 +35,21 @@ pnpm josh run:cut <N>
 
 - `cut` (0) — record written and handed to the lane's launch owner (OpenAI supervisor starts the
   successor after this process exits; Anthropic relaunches directly). **End the turn immediately.**
-- `under-threshold` (0) — the newest request's billed input is under `CONTEXT_CUT_THRESHOLD`; **continue to the gate.**
+- `under-threshold` (0) — the newest request's billed input is under the `pnpm josh cost --cut` threshold; **continue to the gate.**
 - `not-a-lane` (0) — not a dispatched child. **Continue to the gate.**
 - `unready` (1) — the tree is clean or on the default branch. Continue to the gate.
 - `busy` (1) — a cut is already in flight for this tree. Do not relaunch.
 - `failed` (1) — no live OpenAI supervisor, or the Anthropic relaunch could not start. Continue.
 - `unknown` (1) — the git directory could not be read. Continue to the gate.
+- `split-unresolved` (1) — `split-assessment.md` → "Over the guide before the gate".
 
 **`cut` is the only verdict that ends the turn.**
 
 ### The gate refuses until the cut has been taken
 
-`pnpm josh rule:guard` **refuses `pnpm josh gate`** in a lane with no cut record carried, handing back
-the command above.
-
-- **It fires for a marked child and nowhere else**: the working directory is `<lane root>/<issue
-  number>` **and** `JOSH_LANE_CHILD` names that issue. `run:cut` uses an open-lane lookup instead, so
-  the guard and the command need not agree byte for byte.
-- **It fires only when the current context warrants a cut** (`cost_cli.session_verdict`, as `run:cut`).
-- **It is silent once the cut is carried**.
-- **It fires once per run.**
-- **`--resume`, `--end` and `--json` do not count as taking the cut.**
-
-Its row: `prompts/collaboration-workflow/rule-delivery.md`.
+The `pre-gate-cut` row of `pnpm josh rule:list` **refuses `pnpm josh gate`** in a lane with no cut record carried, handing back
+the command above — run it. When the guard fires: `docs/josh-commands-run.md` → "`josh run:cut`"; its
+row: `prompts/collaboration-workflow/rule-delivery.md`.
 
 ## Resuming — the fresh process's entry check
 
@@ -80,7 +64,8 @@ pnpm josh run:cut --resume <N>
   implementation**; re-read the issue body and comments, then go straight to `pnpm josh gate`.
 - `resume-impl` (0) — the cut was taken **during** implementation. Skip the title, the plan, the
   fresh hold claim and the split assessment, re-read the plan, then **continue implementation** — do
-  **not** go straight to the gate.
+  **not** go straight to the gate. A round 1 the resume prints is continued, not rerun
+  (`scripts/run/cut/run-cut-review.ts`).
 - `handed-off` (0) — a successor already adopted this cut. **End the turn quietly and do nothing**;
   no Telegram owed.
 - `stale` (1) — the record does not match the tree (branch, clean tree, expired, or unknown hand-off).
@@ -116,12 +101,11 @@ The child ends mid-implementation and a fresh one resumes **back into implementa
 ### The measurement is the parent hand-off's, never a second one
 
 Same `cost_verdict.per_request_cost` through `cost_cli.session_verdict` as `backlogrun-progress.md` →
-"The hand-off"; `run_cut.IMPLEMENTATION_CONTEXT_THRESHOLD` aliases the **135_000**
-`CONTEXT_CUT_THRESHOLD`.
+"The hand-off", against the same threshold `pnpm josh cost --cut` prints.
 
 ### It is a guard, fired at the edit that crosses the threshold
 
-**The trigger**: `pnpm josh rule:guard` refuses an `Edit` / `Write` in a dispatched lane child over
+**The trigger**: the `implementation-cut` row of `pnpm josh rule:list` refuses an `Edit` / `Write` in a dispatched lane child over
 threshold, handing back `pnpm josh run:cut --impl <N> --handoff <path>`. `cut` ends the turn; the
 fresh process's `run:cut --resume <N>` answers `resume-impl` — **the implementation resume clears the
 record**, so the cut may fire again. **A cut that relaunches its successor owes no Telegram** — the
@@ -129,15 +113,16 @@ record**, so the cut may fire again. **A cut that relaunches its successor owes
 clears. Outside a
 lane, `run:cut --impl` prints the held run's instruction: on `over`, keep the hold, send a
 `confirmation` Telegram naming `fullrun #<N>`, end the turn. **It fires on every threshold crossing,
-not once per run**; **An edit reissued right after a refusal passes**; **An unmeasurable session
+not once per run**; **An edit reissued right after a refusal passes**; **The run's own handoff
+`Write` always passes**; **An unmeasurable session
 warrants the cut**; **It is silent between a cut and its resume** (`scripts/rules/implementation-cut.ts`).
 A child that ended without cutting is detected by
 `pnpm josh run:ending <N> --output <path>`.
 
 ## The threshold
 
-`CONTEXT_CUT_THRESHOLD` and `cost_verdict.per_request_cost` live in
-`scripts/cost-runtime/context-cut-payback.ts`; both cuts and the parent hand-off read the same verdict,
+The threshold is the break-even context `scripts/cost-runtime/context-cut-payback.ts` prices at the
+session's model — `pnpm josh cost --cut` prints it, no fixed figure fits every model; both cuts and the parent hand-off read the same verdict,
 and an unmeasurable session is always cut. Both cuts end the turn **before** the gate, so the push is never a
 turn boundary (`chain-rule.md`).
 
@@ -146,16 +131,16 @@ turn boundary (`chain-rule.md`).
 **The trigger**: a dispatched lane child about to stop for a decision (Tier B, Tier C, an upstream
 defect) parks its own Issue first — `backlogrun-park.md` → "park and continue" — so `pnpm josh
 run:liveness` reads it `settled`. A `needs-human-review` or `already-done` stop already carries its
-label. `pnpm josh rule:guard` refuses `pnpm josh notify --task-type confirmation` from a marked child
-until then — **It fires once per run.** (`scripts/rules/lane-park.ts`).
+label. The `lane-park` row of `pnpm josh rule:list` refuses `pnpm josh notify --task-type confirmation` from a marked child
+until `pnpm josh run:park` has recorded the park — **It fires once per run.** (`scripts/rules/lane-park.ts`).
 
 **A split is not a park**: a child that promoted its Issue to an `epic` stops without
-`needs-decision` — `backlogrun-park.md` → "Splitting a child mid-run". `pnpm josh rule:guard` refuses a
+`needs-decision` — `backlogrun-park.md` → "Splitting a child mid-run". The `lane-split-park` row of `pnpm josh rule:list` refuses a
 `needs-decision` write onto that epic, on every occurrence (`scripts/rules/lane-split-park.ts`).
 
 ### The interactive ask is refused one call earlier
 
 **The trigger**: a headless session ends the turn on an interactive ask, so the notify guard never
-fires; `pnpm josh rule:guard` refuses `AskUserQuestion` for a marked lane child on every occurrence — park the question instead.
+fires; the `lane-interactive-ask` row of `pnpm josh rule:list` refuses `AskUserQuestion` for a marked lane child on every occurrence — park the question instead.
 `pnpm josh run:ending` lifts a slipped ask into the park basis (`scripts/rules/lane-interactive-ask.ts`,
 `scripts/agent/interactive-ask.ts`).

package/.claude/skills/workflow-commands/prerequisite.md

@@ -29,7 +29,7 @@ offer hands it back once its blockers merge.
 
 **A wait for the next published release is a dependency too** — never `needs-decision`. Record it
 with `pnpm josh issue:release <M> --wait` (`<M>` blocked by the release Issue, filed when none is
-open), then stash, comment and `pnpm josh run:release <M>` as for a prerequisite below; `fullrun` /
+open), then `pnpm josh run:pause <M> --for <the release Issue>` as for a prerequisite below; `fullrun` /
 `halfrun` stop, `backlogrun` continues. Closing the release Issue once a person has published it hands
 `<M>` back to `backlog:next` (`docs/josh-commands-backlog.md` → `josh issue:release`).
 
@@ -37,7 +37,7 @@ open), then stash, comment and `pnpm josh run:release <M>` as for a prerequisite
 so the observation row carries no `route:` label (`observation-filing.md`):
 
 ```bash
-pnpm josh issue:file "<title>" --body-file <body-file> --depth <n> --route tier-a
+pnpm josh issue:file "<title>" --body-file <body-file> --route tier-a
 ```
 
 The command lints the body against `prompts/collaboration-workflow/issue-template.md`, applies the
@@ -50,24 +50,19 @@ later steps name its number. **Its duplicate scan is read exactly as it is for a
 
 **Each entry point's own branch stays in that entry's file:**
 
-- **A named epic under `backlogrun`** files without confirmation, records the dependency with
-  `pnpm josh epic --add <E> <N> --before <M>` — `<E>` the epic, `<N>` the prerequisite just filed,
-  `<M>` the child in hand — and the run **continues rather than parking it** (`backlogrun-park.md` → "A
-  prerequisite discovered mid-run"). A child outside any epic records the same relation on itself
-  directly; that branch is the same section's.
+- **A named epic under `backlogrun`** files without confirmation, sets `<M>` — the child in hand —
+  aside with `run:pause` below, and the run **continues rather than parking it** (`backlogrun-park.md` →
+  "A prerequisite discovered mid-run").
 - **`fullrun` / `halfrun`** file the same way without asking, insert the prerequisite into the epic
   that already tracks the Issue or create one over both, and then **stop**, leaving the person one
   command to type (`fullrun.md` / `halfrun.md`). Typing `fullrun` approved implementing **one** Issue;
   a batch is a different authorization, so the stop stays.
 
-**Two steps every entry's procedure turns on:**
+**Once the prerequisite is filed, every entry sets `<M>` aside with `pnpm josh run:pause <M> --for <N>`**
+— the stash, the comment naming its `stash:pop`, the blocked-by and the release; a failure is rerun as
+is (`docs/josh-commands-run.md` → `josh run:pause`). Name the comment's pop in the Telegram too.
 
-- **`git stash push -u` — the `-u` is not optional.** The work in progress almost always includes a
-  new, untracked `*.test.ts`, which a stash without `-u` leaves for the next `pnpm josh ms` to refuse.
-- **The Issue comment is what gets the stash popped, not the Telegram.** The run that picks the Issue up
-  reads it and pops before implementing — **by message, `pnpm josh stash:pop "<the -m message>"`, never
-  a positional `git stash pop`** (the stack is shared by every lane). Say it in the Telegram too.
-
-**Automatic filing is capped at 10 Issues per run** at every entry point; `pnpm josh rule:guard`
-refuses the eleventh filing (`prompts/collaboration-workflow/rule-delivery.md`). On reaching it, stop
+**Automatic filing is capped at 10 Issues per originating work item** at every entry point;
+`pnpm josh issue:file` refuses the eleventh, and `--found-during <N>` names an origin the checkout
+does not (`docs/josh-commands-backlog.md` → "`josh issue:file`", step 2). On reaching it, stop
 and report. `kickoff` is exempt — it never implements, so it never discovers one.

package/.claude/skills/workflow-commands/progress-watcher.md

@@ -53,7 +53,7 @@ missing, say so. **A field's empty value is an observation, never a state** (`re
 
 **The heartbeat is ambient, never a Telegram.** `pnpm josh run:board` is its reader, in a pane of the
 person's own; **no session relays the stream** — name the board command once, at the first cut or when
-asked; `.vscode/tasks.json` starts it on folder open once VSCode's automatic-task prompt is allowed.
+asked; the person starts it, or the `josh: run board` task in `.vscode/tasks.json`, by hand.
 `pnpm josh run:event --watch` stays for following the raw events one by one. `pnpm josh run:wake --list` is the one-line read for a person who types for it.
 **A request for periodic progress is never a CronCreate job** — on screen, name `pnpm josh run:board`;
 off-screen, start `pnpm josh run:board --every <minutes>` in the background (`docs/josh-commands-run.md`).

package/.claude/skills/workflow-commands/prrun.md

@@ -20,13 +20,9 @@ Where `fullrun` runs `pnpm josh followup` and merges, `prrun` does three things
    review findings resolved. A failure stops the run exactly as it stops a `fullrun`.
 2. **Mark the stop — `pnpm josh run:hold <N> --prrun-stop`.** It records the commit the pull request is
    on in this run's own hold, the record `fullrun #<N>` adopts (its prrun resume, `working-tree-hold.md`). **The hold and `in-progress` stay**: the run is not finished until the merge's tail runs.
-3. **Send a `confirmation` Telegram with the resume commands, then stop.** **`fullrun #<N>` first** —
-   its `run:entry` reads where the pull request stands and resumes from there; the direct command
-   follows for finishing without an agent:
-   `pnpm josh notify --task-type confirmation --issue-url "<issue-url>" --body=$'prrun ready to
-   merge: <pr-url>\nNext: fullrun #<N>\nAfter a manual merge, without an agent: pnpm josh followup
-   "<title> #<N>"' --recommended "fullrun #<N>" --alternative "Merge by hand, then pnpm josh
-   followup"`. The stop report names the same two, in the same order.
+3. **Stop.** The mark has already sent the `confirmation` Telegram, its resume line `Next: fullrun
+   #<N>` — never compose one. The stop report names `fullrun #<N>` (recommended) and a manual merge followed by
+   `pnpm josh followup "<title> #<N>"`, in that order.
 
 **Invoking `prrun` is _not_ authorization to merge** — never run `pnpm josh followup` without
 `--no-merge` in a `prrun`. After a person merges by hand, the same `pnpm josh followup "<title> #<N>"`

package/.claude/skills/workflow-commands/retrospective.md

@@ -35,7 +35,7 @@ every regressed row, and the scout keeps a repeat sighting from filing twice.
 ledger** (drained by `pnpm josh observations:flush`). **File nothing when nothing passes.**
 
 **Exclude what is already filed or already done, through the existing scout** (`issue-scout.md`): file
-with `pnpm josh issue:file`, which scouts first — an **open** candidate covering it means do not file, a
+with `pnpm josh issue:file`, which scouts — an **open** candidate covering it means do not file, a
 `(closed)` one means already merged. It also runs `epic:bundle` on each new Issue.
 
 ## `auto-ok`, and closing the step
@@ -44,7 +44,7 @@ with `pnpm josh issue:file`, which scouts first — an **open** candidate coveri
 `- 人の判断: 不要`, so `issue:file` applies the label (with the run label
 `prompts/collaboration-workflow/issue-template.md` requires). **`backlogrun-steps.md` → "What one
 invocation approves" is that judgement's single source.** Every brake still counts these filings: the
-ten-per-invocation ceiling, the WIP cap, `--max` and the 150,000-token session budget.
+ten-per-origin ceiling (with no origin, counted with the invocation's other no-origin filings), the WIP cap, `--max` and the `pnpm josh cost --cut` session budget.
 
 **Close with `pnpm josh run:carry --retrospective --summary "<result>" --owner "$PPID"`.** It marks the
 carry record so `run:step` prints `stop` from then on; the mark survives a session cut and is removed at

package/.claude/skills/workflow-commands/split-assessment.md

@@ -37,6 +37,20 @@ threshold that splits more is required to say why the round-1 measurement does n
 files and lines, test files excluded, and answers `split` / `single` on size alone. Separability stays
 a judgement, so its `split` is the size condition met, not a decision to divide.
 
+## Over the guide before the gate
+
+**Trigger: `pnpm josh main:merge` prints a `split notice`** — the branch's diff, untracked files
+included, answers `split` on `split:assess`; the first `pnpm josh lint:related` or `pnpm josh
+test:related` past the guide prints it earlier, once per Issue. Take one action on it, before `pnpm josh run:cut <N>`
+(`chain-rule.md` step 1) — the cut ends the turn, and the resumed run does not see the notice:
+
+- Keep it one Issue — it must land together: one Issue comment with the line
+  `- 分割しない理由: <理由>`, citing the counts.
+- Carve the rest out — the unimplemented part merges separately: `pnpm josh issue:file --route split --found-during <N>`
+  it, narrow this Issue's acceptance criteria to this branch, then gate.
+
+Neither on record: the pre-gate `run:cut` answers `split-unresolved`. The notice never creates an epic.
+
 ## What each entry point does with the answer
 
 | Entry | Single | Two or more |
@@ -59,7 +73,7 @@ condition to evaluate.** **An entry point that applies a different condition is
 is the non-closing home for the split rationale.
 
 **Each split child is filed with the `route:split` label** —
-`pnpm josh issue:file "<sub-title>" --body-file <body-file> --depth <n> --route split` — and judged for
+`pnpm josh issue:file "<sub-title>" --body-file <body-file> --route split` — and judged for
 `auto-ok` like any filing (`kickoff.md` → "Words typed after `new`").
 
 ## Promote, or create a new epic

package/.claude/skills/workflow-commands/working-tree-hold.md

@@ -32,17 +32,17 @@ that checkout from `pnpm josh doctor` **first** (a read) and claims there.
 josh run:release --force` is the one spelling that removes a record this run did not write**, and the
 `busy` message names it.
 
-**Release what the claim recorded.** A `#N` entry releases `<N>`; a **`new` entry claimed before its
-Issue existed**, so it releases with the **bare** form — a `fullrun new` that stops on a split types
-`pnpm josh run:release`. The bare form removes no label, so every `new` stop that releases also runs
-`gh api -X DELETE repos/{owner}/{repo}/issues/<N>/labels/in-progress 2>/dev/null || true`.
+**Release what the claim recorded.** A `#N` entry releases `<N>`. A **`new` entry claimed before its
+Issue existed**, so once it files `<N>` it runs `pnpm josh run:hold --adopt <N>`, which re-keys the
+record to `<N>` and applies `in-progress`; from then on every stop releases with `run:release <N>`.
+A `new` stop before filing releases with the **bare** form.
 
 **Releasing is the run's, not a person's memory.** `pnpm josh followup` releases on a merged run; an
 abandoned record expires after 8 hours. **A stop that leaves the tree clean releases it explicitly** —
 a split, a prerequisite or a third-party target ends with `pnpm josh run:release <N>` (bare for a `new`
-entry, plus the label DELETE). **`halfrun`'s stop before commit keeps the hold**, as does a
-`needs-human-review` stop: the release command goes in the stop report and the Telegram for the person
-to type. **`fullrun #<N>` of the same issue adopts a `halfrun`'s kept hold** — "The halfrun resume"
+entry not yet adopted). **`halfrun`'s stop before commit keeps the hold** (`run:hold <N>
+--halfrun-stop`), as does a `needs-human-review` stop (`run:hold <N> --human-review-stop`); each is
+refused until `pnpm josh test:e2e` answered green on this tree, and sends its own `confirmation`. **`fullrun #<N>` of the same issue adopts a `halfrun`'s kept hold** — "The halfrun resume"
 below. **An expired record over a tree that still has uncommitted changes does not free it** — it
 answers `busy`; only an expired record over a clean tree is replaced.
 
@@ -54,10 +54,10 @@ run:hold` / `josh run:release`".
 
 **`fullrun #<N>` or `prrun #<N>` after a `halfrun` stop resumes it instead of claiming.** The stop is
 **recorded, never inferred**: the `halfrun` ends with `pnpm josh run:hold <N> --halfrun-stop`, marking
-its record (re-keying a `halfrun new`'s unnumbered one) — a `halfrun` still implementing or a
+its record (a `halfrun new` adopted its unnumbered one at filing) — a `halfrun` still implementing or a
 `backlogrun` child leaves the same dirty tree and is not adopted. On a marked hold for `#<N>`,
 `run:entry` asks the session budget, adopts the hold and prints `entry #<N> — resume: halfrun`. **Skip
-the title, the plan, the split assessment, `pnpm josh ms`, `latest:scope` and the implementation**;
+the title, the plan, the split assessment, `pnpm josh ms`, `latest:if-required` and the implementation**;
 re-read the issue (`pnpm josh issue:read <N>`), run the gate **in full** from the refactor
 (`chain-rule.md` → "Run the review-to-merge chain"), and ship as any `fullrun` does.
 

package/.codex/hooks.json

@@ -6,7 +6,7 @@
 				"hooks": [
 					{
 						"type": "command",
-						"command": "if project_root=\"$(unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null)\"; then unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; else project_root=\"$(git rev-parse --show-toplevel)\"; fi && cd \"$project_root\" && sh scripts/hooks/run-hook.sh audit-provision",
+						"command": "export JOSH_HOOK_CWD=\"$PWD\" && project_root=\"${CLAUDE_PROJECT_DIR:-$( (unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null) || git rev-parse --show-toplevel)}\" && cd \"$project_root\" && sh scripts/hooks/run-hook.sh audit-provision --session-start",
 						"timeout": 180
 					}
 				]
@@ -17,7 +17,7 @@
 				"hooks": [
 					{
 						"type": "command",
-						"command": "if project_root=\"$(unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null)\"; then unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; else project_root=\"$(git rev-parse --show-toplevel)\"; fi && cd \"$project_root\" && sh scripts/hooks/run-hook.sh session-lang",
+						"command": "export JOSH_HOOK_CWD=\"$PWD\" && project_root=\"${CLAUDE_PROJECT_DIR:-$( (unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null) || git rev-parse --show-toplevel)}\" && cd \"$project_root\" && sh scripts/hooks/run-hook.sh session-lang",
 						"timeout": 10
 					}
 				]
@@ -29,7 +29,7 @@
 				"hooks": [
 					{
 						"type": "command",
-						"command": "if project_root=\"$(unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null)\"; then unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; else project_root=\"$(git rev-parse --show-toplevel)\"; fi && cd \"$project_root\" && sh scripts/hooks/run-hook.sh codex-hook-adapter pretool",
+						"command": "export JOSH_HOOK_CWD=\"$PWD\" && project_root=\"${CLAUDE_PROJECT_DIR:-$( (unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null) || git rev-parse --show-toplevel)}\" && cd \"$project_root\" && sh scripts/hooks/run-hook.sh codex-hook-adapter pretool",
 						"timeout": 20
 					}
 				]
@@ -41,7 +41,7 @@
 				"hooks": [
 					{
 						"type": "command",
-						"command": "if project_root=\"$(unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null)\"; then unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; else project_root=\"$(git rev-parse --show-toplevel)\"; fi && cd \"$project_root\" && sh scripts/hooks/run-hook.sh codex-hook-adapter posttool",
+						"command": "export JOSH_HOOK_CWD=\"$PWD\" && project_root=\"${CLAUDE_PROJECT_DIR:-$( (unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null) || git rev-parse --show-toplevel)}\" && cd \"$project_root\" && sh scripts/hooks/run-hook.sh codex-hook-adapter posttool",
 						"timeout": 90
 					}
 				]
@@ -53,7 +53,7 @@
 				"hooks": [
 					{
 						"type": "command",
-						"command": "if project_root=\"$(unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null)\"; then unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; else project_root=\"$(git rev-parse --show-toplevel)\"; fi && cd \"$project_root\" && sh scripts/hooks/run-hook.sh stop-guard",
+						"command": "export JOSH_HOOK_CWD=\"$PWD\" && project_root=\"${CLAUDE_PROJECT_DIR:-$( (unset GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_DIR GIT_INDEX_FILE GIT_NAMESPACE GIT_OBJECT_DIRECTORY GIT_WORK_TREE; git rev-parse --show-toplevel 2>/dev/null) || git rev-parse --show-toplevel)}\" && cd \"$project_root\" && sh scripts/hooks/run-hook.sh stop-guard",
 						"timeout": 20
 					}
 				]

package/.github/actions/setup-node/action.yml

@@ -22,10 +22,19 @@ inputs:
     required: false
     default: ''
 
+# The exact version `'24'` resolved to on this runner (joshuafolkken/kit#4346). Runner images do not
+# all carry the same patch release, and ESLint folds `process.version` into every cache entry, so a
+# cache restored across two patch releases is cold; the ESLint cache key names this value.
+outputs:
+  node-version:
+    description: The Node.js version installed, as actions/setup-node reports it (e.g. `v24.22.0`).
+    value: ${{ steps.setup-node.outputs.node-version }}
+
 runs:
   using: composite
   steps:
     - name: Setup Node.js
+      id: setup-node
       uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
       with:
         node-version: '24'

package/.github/actions/setup-pnpm/action.yml

@@ -48,27 +48,20 @@ runs:
         test -n "$version"
         echo "version=$version" >> "$GITHUB_OUTPUT"
 
+    # The store is cached by pnpm/setup itself, keyed on the lockfile and the requested runtime and
+    # restored before the runtime is installed. A separate actions/cache step restored the store
+    # only after pnpm/setup had installed the runtime, so the job's runtime came from the registry
+    # every run, and a download that crawled at 100 KB/s timed the job out at 10 minutes
+    # (joshuafolkken/kit#5315). Caching it in pnpm's store, rather than taking Node from setup-node's
+    # tool cache, keeps setup-node the one place the default Node version is written.
     - name: Setup pnpm
-      uses: pnpm/setup@fbda4c85fc2e1e08721cd8763afea8f48d60f024 # v3.0.0
+      uses: pnpm/setup@a0881977cd8ea73b1ed212236c99ca10dcc80cf4 # v3.1.1
       with:
         version: ${{ steps.pnpm-version.outputs.version }}
         runtime: ${{ inputs.runtime }}
+        cache: ${{ inputs.install == 'true' && inputs.cache == 'true' }}
         install: false
 
-    - name: Resolve pnpm store path
-      if: inputs.install == 'true' && inputs.cache == 'true'
-      shell: bash
-      run: echo "PNPM_STORE_PATH=$(pnpm store path)" >> "$GITHUB_ENV"
-
-    - name: Setup pnpm store cache
-      if: inputs.install == 'true' && inputs.cache == 'true'
-      uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-      with:
-        path: ${{ env.PNPM_STORE_PATH }}
-        key: ${{ runner.os }}-pnpm-store-${{ hashFiles('pnpm-lock.yaml') }}
-        restore-keys: |
-          ${{ runner.os }}-pnpm-store-
-
     # The safe-chain release and the SHA-256 of that release's install-safe-chain.sh. The installer
     # puts the safe-chain binary under ~/.safe-chain/bin and adds it to PATH beside the shims;
     # `pnpm dlx … setup-ci` left only the shims, which then let every install through without a scan
@@ -77,8 +70,8 @@ runs:
       if: inputs.install == 'true'
       shell: bash
       env:
-        SAFE_CHAIN_INSTALLER_VERSION: 1.5.20
-        SAFE_CHAIN_INSTALLER_SHA256: 0ad25efe15d1fa56105157a454d647223e78eb0c53d1f85e3d10afcd722e7bfd
+        SAFE_CHAIN_INSTALLER_VERSION: 1.5.26
+        SAFE_CHAIN_INSTALLER_SHA256: 9e4af7107f06d9c0d758cb08fb36804c2af88e24972f3a9d3f8c2bd0ca002adf
       run: |
         installer="$RUNNER_TEMP/install-safe-chain.sh"
         curl --proto '=https' -fsSL "https://github.com/AikidoSec/safe-chain/releases/download/$SAFE_CHAIN_INSTALLER_VERSION/install-safe-chain.sh" -o "$installer"

package/.github/dependabot.yml

@@ -8,6 +8,34 @@ updates:
       - '/.github/actions/*'
     schedule:
       interval: 'weekly'
+    # One pull request for every minor and patch bump. Separate pull requests that touch the same
+    # workflow file leave the later merge writing workflow content its head does not hold, which
+    # `GITHUB_TOKEN` may not, so GitHub withdraws its auto-merge (joshuafolkken/kit#4148). kit's own
+    # file only: the distributed `templates/dependabot.yml` stays ungrouped, because a consumer's
+    # auto-merge holds a whole pull request that touches an upstream-managed workflow.
+    #
+    # The actions the publish jobs run with publish credentials, and those of the `pack` job that
+    # builds the tarball they publish, come first, in a pull request of their own:
+    # `.github/workflows/dependabot-auto-merge.yml` merges only the `github-actions` group, so a
+    # person reviews each bump of these (joshuafolkken/kit#4633, joshuafolkken/kit#4654). This list
+    # is the only one.
+    groups:
+      publish-actions:
+        patterns:
+          - 'actions/checkout'
+          - 'actions/download-artifact'
+          - 'actions/setup-node'
+          - 'actions/upload-artifact'
+          - 'pnpm/setup'
+        update-types:
+          - 'minor'
+          - 'patch'
+      github-actions:
+        update-types:
+          - 'minor'
+          - 'patch'
+    cooldown:
+      default-days: 3
   # Version updates are disabled: `josh latest` runs at the start of every fullrun / halfrun /
   # queue and already bumps npm dependencies to latest, so Dependabot's weekly PRs only duplicate
   # it and were being closed unmerged after consuming a full CI run. `open-pull-requests-limit: 0`
@@ -21,3 +49,7 @@ updates:
     schedule:
       interval: 'weekly'
     open-pull-requests-limit: 0
+    cooldown:
+      default-days: 3
+      exclude:
+        - 'vite'

package/.github/release.yml

@@ -7,11 +7,9 @@ changelog:
   categories:
     - title: Breaking Changes 🛠
       labels:
-        - Semver-Major
         - breaking-change
     - title: Exciting New Features 🎉
       labels:
-        - Semver-Minor
         - enhancement
     - title: Bug Fixes 🐛
       labels:

package/.github/workflows/auto-tag.yml

@@ -13,11 +13,44 @@ jobs:
       actions: write
       contents: write
     steps:
+      # The dispatch payload is only a claim: any holder of a contents:write token can send
+      # ci-passed-on-main with any sha, including a commit main's branch protection never saw
+      # (joshuafolkken/kit#4651). Only a commit main contains, whose push-event CI run reached its
+      # Notify Auto Tag job, is tagged — that job runs only once every check it needs has passed.
+      - name: Verify the dispatched commit
+        env:
+          GH_TOKEN: ${{ github.token }}
+          GH_REPO: ${{ github.repository }}
+          SHA: ${{ github.event.client_payload.sha }}
+        run: |
+          if ! [[ "$SHA" =~ ^[0-9a-f]{40}$ ]]; then
+            echo "::error::ci-passed-on-main carried no full commit sha: $SHA" >&2
+            exit 1
+          fi
+
+          STATUS=$(gh api "repos/$GH_REPO/compare/main...$SHA" --jq '.status')
+          if [ "$STATUS" != "identical" ] && [ "$STATUS" != "behind" ]; then
+            echo "::error::$SHA is not on main (compare status: $STATUS)" >&2
+            exit 1
+          fi
+
+          RUN_IDS=$(gh api "repos/$GH_REPO/actions/workflows/ci.yml/runs?head_sha=$SHA&event=push&branch=main" --jq '.workflow_runs[].id')
+          for RUN_ID in $RUN_IDS; do
+            if gh api "repos/$GH_REPO/actions/runs/$RUN_ID/jobs?per_page=100" --jq '.jobs[] | select(.name == "Notify Auto Tag") | "\(.status)/\(.conclusion)"' | grep -Eqx 'in_progress/null|completed/success'; then
+              echo "✅ $SHA is on main and passed CI run $RUN_ID"
+              exit 0
+            fi
+          done
+
+          echo "::error::No push-event CI run on main passed for $SHA" >&2
+          exit 1
+
       - name: Checkout code
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ github.event.client_payload.sha }}
           fetch-depth: 2
+          persist-credentials: false
 
       # No Node.js setup: this job installs nothing and reads package.json with jq, which the runner
       # image ships, so a Node.js version step would only add time (joshuafolkken/kit#3326).
@@ -68,10 +101,17 @@ jobs:
         id: tag_check
         if: steps.version_check.outputs.changed == 'true'
         env:
+          GH_TOKEN: ${{ github.token }}
           VERSION: ${{ steps.current_version.outputs.version }}
         run: |
           TAG="v$VERSION"
 
+          # The checkout keeps no credentials, so the token reaches git for this step only, through
+          # the environment rather than .git/config; a private repository needs it to fetch.
+          BASIC=$(printf 'x-access-token:%s' "$GH_TOKEN" | base64 -w0)
+          echo "::add-mask::$BASIC"
+          export GIT_CONFIG_COUNT=1 GIT_CONFIG_KEY_0=http.https://github.com/.extraheader GIT_CONFIG_VALUE_0="AUTHORIZATION: basic $BASIC"
+
           # Shallow checkout (fetch-depth: 2) does not fetch tags, so the existence
           # check would miss tags that already exist on the remote. Fetch them first.
           git fetch origin --tags --force
@@ -88,10 +128,15 @@ jobs:
         id: create_tag
         if: steps.version_check.outputs.changed == 'true' && steps.tag_check.outputs.exists == 'false'
         env:
+          GH_TOKEN: ${{ github.token }}
           VERSION: ${{ steps.current_version.outputs.version }}
         run: |
           TAG="v$VERSION"
 
+          BASIC=$(printf 'x-access-token:%s' "$GH_TOKEN" | base64 -w0)
+          echo "::add-mask::$BASIC"
+          export GIT_CONFIG_COUNT=1 GIT_CONFIG_KEY_0=http.https://github.com/.extraheader GIT_CONFIG_VALUE_0="AUTHORIZATION: basic $BASIC"
+
           git config user.name "github-actions[bot]"
           git config user.email "github-actions[bot]@users.noreply.github.com"