@gobing-ai/spur 0.3.35 → 0.3.37

package/config/corpus-baseline.json

@@ -15,34 +15,6 @@
             "reason": "GENUINE PRE-FIX BYPASS. Closed 2026-08-06, well after the rule existed (2026-07-24), via the `--no-lifecycle` hole closed on 2026-08-07. Its Solution needs one file:line citation. The only entry here representing real unpaid debt.",
             "since": "2026-08-07"
         },
-        {
-            "kind": "feature",
-            "id": "M",
-            "code": "L3.ac-bdd-error",
-            "reason": "CHECKER GAP, not corpus debt. M is a wayfinder MAP; its Acceptance Criteria section carries an explicit prose disclaimer ('This feature is a wayfinder MAP... It has no acceptance criteria — its target is the ## Goal'). The BDD validator requires a `Feature:` declaration and has no notion of the map feature type. Correct fix is to teach `feature check` about wayfinder maps, not to bolt fake Gherkin onto a map.",
-            "since": "2026-08-07"
-        },
-        {
-            "kind": "feature",
-            "id": "M",
-            "code": "L3.ac-bdd-invalid",
-            "reason": "Downstream of the M ac-bdd-error entry — same missing-Feature-declaration cause, reported twice by the validator.",
-            "since": "2026-08-07"
-        },
-        {
-            "kind": "feature",
-            "id": "F82",
-            "code": "L3.ac-bdd-error",
-            "reason": "CHECKER GAP, same class as M: wayfinder map with a deliberate no-AC prose disclaimer (plus a noted exception for two implementation-ready child tickets). Not a syntax error to fix.",
-            "since": "2026-08-07"
-        },
-        {
-            "kind": "feature",
-            "id": "F82",
-            "code": "L3.ac-bdd-invalid",
-            "reason": "Downstream of the F82 ac-bdd-error entry — same cause, reported twice.",
-            "since": "2026-08-07"
-        },
         {
             "kind": "feature",
             "id": "F821",

package/config/launchd/ai.gobing.spur.history.daily.plist

@@ -0,0 +1,56 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>Label</key>
+    <string>ai.gobing.spur.history.daily</string>
+
+    <!-- ── Program: run the nightly history pipeline (task 0470+) ──────────── -->
+    <!-- Replace SPUR_BIN with the absolute path to your `spur` binary          -->
+    <!-- (e.g. /opt/homebrew/bin/spur or the bun-linked monorepo CLI).           -->
+    <!-- Replace PROJECT_DIR with the absolute path to your Spur project root.   -->
+    <key>ProgramArguments</key>
+    <array>
+        <string>SPUR_BIN</string>
+        <string>history</string>
+        <string>daily</string>
+        <string>--json</string>
+    </array>
+
+    <!-- Working directory: the Spur project root. The daily command resolves    -->
+    <!-- .spur/reports, .spur/logs, and the SQLite ledger relative to this.       -->
+    <key>WorkingDirectory</key>
+    <string>PROJECT_DIR</string>
+
+    <!-- ── Schedule: daily wall-clock trigger (R3) ─────────────────────────── -->
+    <!-- 02:00 local time — picks a low-activity hour. Adjust Hour to taste.      -->
+    <!-- launchd survives reboot and runs missed CalendarInterval jobs at the     -->
+    <!-- next login, so a laptop closed overnight self-heals.                     -->
+    <key>StartCalendarInterval</key>
+    <dict>
+        <key>Hour</key>
+        <integer>2</integer>
+        <key>Minute</key>
+        <integer>0</integer>
+    </dict>
+
+    <!-- ── Log capture (R4): failures before Spur's own logging initializes ── -->
+    <!-- are still written here. launchd owns these file handles from the first   -->
+    <!-- byte — there is no window where output is lost.                          -->
+    <key>StandardOutPath</key>
+    <string>PROJECT_DIR/.spur/logs/history-daily.out</string>
+    <key>StandardErrorPath</key>
+    <string>PROJECT_DIR/.spur/logs/history-daily.err</string>
+
+    <!-- RunAtLoad=false: do NOT fire every time the agent loads (boot/login).   -->
+    <!-- StartCalendarInterval already re-fires a missed slot when the machine   -->
+    <!-- wakes, so RunAtLoad would only cause duplicate runs.                    -->
+
+    <!-- If the process exits non-zero, do NOT auto-restart — the daily command  -->
+    <!-- has its own retry semantics (checkpoint resume), and a tight retry loop  -->
+    <!-- would mask a configuration error. The operator checks the four detection -->
+    <!-- layers (R5) instead.                                                     -->
+    <key>KeepAlive</key>
+    <false/>
+</dict>
+</plist>

package/config/rules/strict/runtime-boundaries.yaml

@@ -60,6 +60,7 @@ rules:
             - "packages/app/src/services/token-ledger-service.ts" # FD byte-window log tailing
             - "packages/app/src/services/token-ledger-watcher.ts" # node:fs watch() live watcher
             - "packages/app/src/services/project-registry.ts" # atomic projects.json persistence
+            - "packages/app/src/services/history-service.ts" # versioned analyze artifact + bounded-errors sidecar + latest.json symlink pointer (task 0474); ts-runtime FileSystem seam has no symlink, so the pointer uses node:fs directly (mirrors project-registry.ts persistence exemption)
             - "packages/app/src/observability/workflow-run-log-sink.ts" # sync FD append for mid-run tail-able all-in-one run log (task 0426 / feature D2); append() is sync from the observability bus
             - "apps/cli/src/commands/workflow.ts" # FD byte-window tail of the mid-run run log for `workflow trace --follow` streaming (task 0428 / feature D2); readSync at offset over the observability sink's FDs
             - "apps/web/src/modules/discover.ts" # Vite/Astro module scanner fallback under bun test

package/config/templates/AGENTS.md

@@ -140,7 +140,7 @@ spur <noun> <verb> … --json
 spur <noun> --help
 ```
 
-**Long-tail:** Additional `/sp:dev-*` commands (handover, gitmsg, fixall, dogfood, reverse, arch,
+**Long-tail:** Additional `/sp:dev-*` commands (handover, gitmsg, fixall, findconflict, dogfood, reverse, arch,
 …) are indexed in the project plugin README (`plugins/sp/README.md` when present).
 
 **Outside spur-cli:** Nouns not fully documented in `sp:spur-cli` (`agent`, `history`, `message`,

package/config/workflows/task-pipeline.yaml

@@ -57,9 +57,11 @@ vars:
   # `--vars '{"agent":"claude"}'`. Pinned (not left to the AiRunner's <default>
   # selection) so a broken/misconfigured agent on the box can't silently capture the run.
   agent: "omp"
-  # Implement-only executor override (R1, task 0454). Defaults to same as agent.
-  # Override with `--vars '{"implementAgent":"omp-zai"}'` to pin implement to a
-  # specific executor while other hops keep the default agent.
+  # Implement-only executor override (R1, task 0454). Resolves to this YAML literal
+  # unless overridden. The `--agent` flag (execution-batch.md §3.2) forwards into BOTH
+  # `agent` and `implementAgent`, so a pinned `--agent X` reaches implement too. To
+  # pin ONLY implement while other hops keep the default, pass
+  # `--vars '{"implementAgent":"omp-zai"}'`.
   implementAgent: "omp"
   # Step-level timeout for agentic hops (review / verify / test-fix) in ms.
   # Soft quality-gate shells are unbounded by this var (host shell only).
@@ -82,7 +84,7 @@ vars:
   # and the fixall slash input all use this same var so the command stays single-sourced.
   # TRUSTED CONFIG ONLY — this string is executed via `sh -c` (see test/test-recheck). Never
   # interpolate untrusted operator/LLM input into qualityGateCmd (task 0436 SECUA residual).
-  qualityGateCmd: "bun run autofix && bun run spur-check"
+  qualityGateCmd: "bun run format && bun run spur-check"
   # Max /sp:dev-fixall attempts after a red quality-gate probe/recheck (bounded; no thrash).
   # Attempt counter: .spur/run/<wbs>-test-fix-attempt. Default 2 = two fixall hops before failed.
   qualityGateMaxFixAttempts: "2"
@@ -90,6 +92,12 @@ vars:
   # project can point it at its own formatter; invoked best-effort (a missing or
   # failing formatter must never abort a run — the quality gate is the real gate).
   formatCmd: "bun run format"
+  # Bounded `file:line` anchors extracted from the failing quality-gate log by the
+  # `test` / `test-recheck` hops (deduped, max 20, space-separated on one line).
+  # `test-fix` reads `.spur/run/<wbs>-test-gate.findings` into this var and names the
+  # anchors directly in the /sp:dev-fixall input, so the fix agent starts AT the failing
+  # file:line instead of re-deriving it from a fresh gate run (0482 R3).
+  gateFindings: ""
   # Max R-items in ## Requirements before size precheck fails (R2, task 0454).
   # Override with `--vars '{"maxImplementReqs":"12"}'`.
   maxImplementReqs: "5"
@@ -147,7 +155,7 @@ states:
             SIZE_FILE=".spur/run/$wbs-precheck-size.status" &&
             mkdir -p .spur/run &&
             bun plugins/sp/scripts/task-size-precheck.ts "$wbs"
-            --max-reqs "$maxImplementReqs" --max-plan-items "$maxImplementPlanItems" &&
+            --spur-bin "$spurBin" --max-reqs "$maxImplementReqs" --max-plan-items "$maxImplementPlanItems" &&
             exit 0
 
   - id: implement
@@ -214,10 +222,14 @@ states:
           command: >-
             mkdir -p .spur/run &&
             STATUS_FILE=".spur/run/$wbs-test-gate.status" &&
+            LOG_FILE=".spur/run/$wbs-test-gate.log" &&
             ATTEMPT_FILE=".spur/run/$wbs-test-fix-attempt" &&
             echo 0 > "$ATTEMPT_FILE" &&
             set +e &&
-            ( sh -c "$qualityGateCmd" ); gate_rc=$?; set -e &&
+            ( sh -c "$qualityGateCmd" ) > "$LOG_FILE" 2>&1; gate_rc=$?; set -e &&
+            cat "$LOG_FILE" &&
+            FINDINGS_FILE=".spur/run/$wbs-test-gate.findings" &&
+            set +e; grep -oE '[A-Za-z0-9_./-]+\.[A-Za-z]+:[0-9]+' "$LOG_FILE" | sort -u | head -20 | tr '\n' ' ' > "$FINDINGS_FILE"; set -e &&
             if [ "$gate_rc" -eq 0 ]; then
               printf 'PASS\n' > "$STATUS_FILE";
             else
@@ -238,10 +250,19 @@ states:
             ATTEMPT_FILE=".spur/run/$wbs-test-fix-attempt" &&
             n=$(cat "$ATTEMPT_FILE" 2>/dev/null || echo 0) &&
             printf '%s\n' "$((n + 1))" > "$ATTEMPT_FILE"
+      # R3 (0482): project the extracted gate anchors into a var so the dispatch input
+      # can NAME the failing file:line, not merely point at a log. A vars template cannot
+      # run a shell, so the read is an action, not an inline `$(cat ...)` substitution.
+      - kind: file.read.into-var
+        options:
+          path: .spur/run/${vars.wbs}-test-gate.findings
+          var: gateFindings
       - kind: agent.run
         options:
           agent: ${vars.agent}
-          input: /sp:dev-fixall "${vars.qualityGateCmd}"
+          # R3 (0482): `--findings` names the failing anchors inline; `--gate-log` remains
+          # the full-context escape hatch when the digest is not enough.
+          input: /sp:dev-fixall "${vars.qualityGateCmd}" --gate-log .spur/run/${vars.wbs}-test-gate.log --findings "${vars.gateFindings}"
           timeoutMs: ${vars.stepTimeoutMs}
 
   - id: test-recheck
@@ -256,8 +277,12 @@ states:
           command: >-
             mkdir -p .spur/run &&
             STATUS_FILE=".spur/run/$wbs-test-gate.status" &&
+            LOG_FILE=".spur/run/$wbs-test-gate.log" &&
             set +e &&
-            ( sh -c "$qualityGateCmd" ); gate_rc=$?; set -e &&
+            ( sh -c "$qualityGateCmd" ) > "$LOG_FILE" 2>&1; gate_rc=$?; set -e &&
+            cat "$LOG_FILE" &&
+            FINDINGS_FILE=".spur/run/$wbs-test-gate.findings" &&
+            set +e; grep -oE '[A-Za-z0-9_./-]+\.[A-Za-z]+:[0-9]+' "$LOG_FILE" | sort -u | head -20 | tr '\n' ' ' > "$FINDINGS_FILE"; set -e &&
             if [ "$gate_rc" -eq 0 ]; then
               printf 'PASS\n' > "$STATUS_FILE";
             else
@@ -290,8 +315,10 @@ states:
   - id: verify
     description: >
       Functional verification (BDD + traceability) via /sp:dev-verify. The agent's
-      captured answer is written to `.spur/run/<wbs>-verify-answer.txt`; a deterministic
-      shell step then derives the verdict and writes the gate artifact
+      captured answer is written to `.spur/run/<wbs>-verify-answer.txt` and MUST follow
+      the answer-file schema contract (explicit `Verdict: PASS|PARTIAL|FAIL` line plus
+      `| Req | Status | Evidence |` and `| AC | Status | Evidence Type | Evidence |` tables);
+      a deterministic shell step then derives the verdict and writes the gate artifact
       `.spur/run/<wbs>-verdict.json` (so the completion gate reads a real verdict, not
       agent discretion — R9). The verdict is PASS only if the agent both reported PASS
       AND `spur task check` passes; otherwise FAIL.

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.3.35",
+    "version": "0.3.37",
     "description": "Spur CLI — local-first harness for mainstream coding agents: constraint checking, workflow orchestration, agent health, and history analytics. Bun-native; exposes the `spur` command.",
     "keywords": [
         "spur",
@@ -50,14 +50,14 @@
     },
     "devDependencies": {
         "@commander-js/extra-typings": "^14.0.0",
-        "@gobing-ai/ts-db": "^0.4.22",
-        "@gobing-ai/ts-ai-runner": "^0.4.22",
-        "@gobing-ai/ts-dual-workflow-engine": "^0.4.22",
-        "@gobing-ai/ts-infra": "^0.4.22",
-        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.22",
-        "@gobing-ai/ts-rule-engine": "^0.4.22",
-        "@gobing-ai/ts-runtime": "^0.4.22",
-        "@gobing-ai/ts-utils": "^0.4.22",
+        "@gobing-ai/ts-db": "^0.4.23",
+        "@gobing-ai/ts-ai-runner": "^0.4.23",
+        "@gobing-ai/ts-dual-workflow-engine": "^0.4.23",
+        "@gobing-ai/ts-infra": "^0.4.23",
+        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.23",
+        "@gobing-ai/ts-rule-engine": "^0.4.23",
+        "@gobing-ai/ts-runtime": "^0.4.23",
+        "@gobing-ai/ts-utils": "^0.4.23",
         "@types/bun": "1.3.14",
         "@types/figlet": "^1.7.0",
         "@types/node-notifier": "8.0.5",