@gobing-ai/spur 0.3.68 → 0.3.69

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
     "plugins": [
         {
             "name": "sp",
-            "version": "0.3.68",
+            "version": "0.3.69",
             "source": "./plugins/sp"
         }
     ]

package/config/workflow-composition-baseline.json

@@ -320,14 +320,14 @@
                 },
                 "precheck:onEnter:2": {
                     "kind": "shell",
-                    "invocation": "if [ \"$profile\" = auto ]; then\n  FID=$($spurBin task show $wbs --json 2>/dev/null |\n  jq -r '.feature_id // .frontmatter.feature_id // empty' 2>/dev/null);\n  if [ -n \"$FID\" ]; then\n    $spurBin feature sync \"$FID\" --force --json 2>/dev/null ||\n    $spurBin feature update \"$FID\" active 2>/dev/null || true;\n  fi;\nfi; exit 0",
+                    "invocation": "if [ \"$profile\" = auto ]; then\n  FID=$($spurBin task show $wbs --json 2>/dev/null |\n  jq -r '.feature_id // .frontmatter.feature_id // empty' 2>/dev/null);\n  if [ -n \"$FID\" ]; then\n    if ! $spurBin feature sync \"$FID\" --force 2>/dev/null; then\n    if ! $spurBin feature update \"$FID\" active 2>/dev/null; then\n    echo \"precheck: FAIL - feature reactivation $FID failed;\" >&2;\n    echo \"precheck: feature sync + feature update both errored\" >&2;\n    exit 1;\n    fi;\n    fi;\n  fi;\nfi; exit 0",
                     "stateEffect": "write",
                     "evidenceEffect": "none",
                     "disposition": "GLUE"
                 },
                 "precheck:onEnter:3": {
                     "kind": "shell",
-                    "invocation": "SIZE_FILE=\".spur/run/$wbs-precheck-size.status\" && mkdir -p .spur/run && if [ -f plugins/sp/scripts/task-size-precheck.ts ]; then bun plugins/sp/scripts/task-size-precheck.ts \"$wbs\" --spur-bin \"$spurBin\" --max-reqs \"$maxImplementReqs\" --max-plan-items \"$maxImplementPlanItems\"; else\n  echo \"task-size-precheck skipped — plugins/sp/scripts/task-size-precheck.ts not present in project.\" >&2 &&\n  echo \"PASS\" > \"$SIZE_FILE\";\nfi && exit 0",
+                    "invocation": "SIZE_FILE=\".spur/run/$wbs-precheck-size.status\" && mkdir -p .spur/run && if [ -f plugins/sp/scripts/task-size-precheck.ts ]; then bun plugins/sp/scripts/task-size-precheck.ts \"$wbs\" --spur-bin \"$spurBin\" --max-reqs \"$maxImplementReqs\" --max-plan-items \"$maxImplementPlanItems\"; else\n  echo \"task-size-precheck failed closed — checker script\" >&2 &&\n  echo \"plugins/sp/scripts/task-size-precheck.ts absent.\" >&2 &&\n  echo \"FAIL\" > \"$SIZE_FILE\";\nfi && exit 0",
                     "stateEffect": "read",
                     "evidenceEffect": "write",
                     "disposition": "EXT"

package/config/workflows/basic.yaml

@@ -24,7 +24,7 @@ failureStates:
 vars:
   # `task` is reserved by the engine runtime — use taskLabel for the free-form label.
   taskLabel: "task"
-  agent: "omp"
+  agent: "auto"
   stepTimeoutMs: "1800000"
   # Override per project: `--vars '{"qualityGateCmd":"bun run lint && bun run test"}'`
   qualityGateCmd: "bun run check"

package/config/workflows/docs-pipeline.yaml

@@ -30,7 +30,7 @@ vars:
   wbs: "0000"
   profile: "standard"
   spurBin: "spur"
-  agent: "omp"
+  agent: "auto"
   stepTimeoutMs: "1800000"
   # Proof-state bracket (task 0704, mirroring task-pipeline 0612/0703). `proofDigest` is the
   # canonical capture at verify entry; `proofDigestNow` is the live re-capture compared against

package/config/workflows/feature-dev.yaml

@@ -44,7 +44,7 @@ failureStates:
   - failed
 vars:
   featureId: ""
-  agent: "omp"
+  agent: "auto"
   profile: "standard"
   spurBin: "spur"
   stepTimeoutMs: "1800000"

package/config/workflows/idea-pipeline.yaml

@@ -65,7 +65,7 @@ vars:
   spurBin: "spur"
   # R8 (0366): injected by WorkflowAppService.run(); stamps discovery artifact provenance.
   __runId: ""
-  agent: "omp"
+  agent: "auto"
   planningAgent: ""
   stepTimeoutMs: "1800000"
 

package/config/workflows/task-pipeline.yaml

@@ -54,15 +54,16 @@ vars:
   # runs and `workflow validate` resolve the template. (See AGENTS.md / ADR-026.)
   spurBin: "spur"
   # Agent the pipeline's agent.run steps invoke. Override per run with
-  # `--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). Resolves to this YAML literal
-  # unless overridden. The `--agent` flag (execution-batch.md §3.2) forwards into BOTH
+  # `--vars '{"agent":"claude"}'`. `auto` is the reserved config-resolving selector:
+  # `agent.default` role -> tier -> cheapest USABLE executor. A named literal here would
+  # pin a box-specific binary into tracked SSOT and escape that usability ladder.
+  agent: "auto"
+  # Implement-only executor override (R1, task 0454). Resolves like `agent` 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"
+  implementAgent: "auto"
   # Step-level timeout for agentic hops (review / verify / test-fix) in ms.
   # Soft quality-gate shells are unbounded by this var (host shell only).
   # Raised 600s → 1800s (task 0398 R4 / H6 dogfood). Override:
@@ -174,6 +175,10 @@ states:
       # R1 (0453): auto-profile precheck reopens a done feature before task check.
       # Under profile=auto, resolve feature_id, sync (preferred) or update to active.
       # Under non-auto, leave R4 message to guide the operator.
+      # R3 (0723): a real reactivation failure is surfaced, not swallowed —
+      # the default 'fail' onEnter policy halts the sequence and routes the
+      # run to `failed` before implementation. Verbs stay single-shot:
+      # one sync, then one update fallback, never retried in a loop.
       - kind: shell
         options:
           command: >-
@@ -181,17 +186,23 @@ states:
               FID=$($spurBin task show $wbs --json 2>/dev/null |
               jq -r '.feature_id // .frontmatter.feature_id // empty' 2>/dev/null);
               if [ -n "$FID" ]; then
-                $spurBin feature sync "$FID" --force --json 2>/dev/null ||
-                $spurBin feature update "$FID" active 2>/dev/null || true;
+                if ! $spurBin feature sync "$FID" --force 2>/dev/null; then
+                if ! $spurBin feature update "$FID" active 2>/dev/null; then
+                echo "precheck: FAIL - feature reactivation $FID failed;" >&2;
+                echo "precheck: feature sync + feature update both errored" >&2;
+                exit 1;
+                fi;
+                fi;
               fi;
             fi;
             exit 0
-      # R2 (0454): task size precheck — evaluate R-item and Plan-item counts.
-      # Writes PASS/FAIL to .spur/run/<wbs>-precheck-size.status. Always exit 0
-      # (soft check, like doctor). The precheck→implement guard reads the file.
-      # Temporary config-only bypass (0723): keep deterministic size limits but defer
-      # the executor-tier policy to the dedicated task-pipeline upgrade. This avoids
-      # the script's second `spur agent doctor` call while the precheck path is repaired.
+      # R2 (0454, 0723): task size precheck — deterministic count-only
+      # evaluation of R-item and Plan-item counts. No executor-tier policy:
+      # dispatch-time requiresCapabilities at `agent.run` is the
+      # authoritative capability check. Writes PASS/FAIL to
+      # .spur/run/<wbs>-precheck-size.status. Always exit 0 (soft action);
+      # the precheck→implement guard reads the file, so a missing checker
+      # fails closed (writes FAIL, never PASS).
       - kind: shell
         options:
           command: >-
@@ -199,10 +210,12 @@ states:
             mkdir -p .spur/run &&
             if [ -f plugins/sp/scripts/task-size-precheck.ts ]; then
             bun plugins/sp/scripts/task-size-precheck.ts "$wbs"
-            --spur-bin "$spurBin" --max-reqs "$maxImplementReqs" --max-plan-items "$maxImplementPlanItems";
+            --spur-bin "$spurBin" --max-reqs "$maxImplementReqs"
+            --max-plan-items "$maxImplementPlanItems";
             else
-              echo "task-size-precheck skipped — plugins/sp/scripts/task-size-precheck.ts not present in project." >&2 &&
-              echo "PASS" > "$SIZE_FILE";
+              echo "task-size-precheck failed closed — checker script" >&2 &&
+              echo "plugins/sp/scripts/task-size-precheck.ts absent." >&2 &&
+              echo "FAIL" > "$SIZE_FILE";
             fi &&
             exit 0
 

package/config/workflows/wayfinder-resolution.yaml

@@ -27,7 +27,7 @@ vars:
   wbs: "0000"
   profile: "standard"
   spurBin: "spur"
-  agent: "omp"
+  agent: "auto"
   stepTimeoutMs: "1800000"
   approval: "required"
   resolutionMode: "research"

package/config/workflows/wrapup-pipeline.yaml

@@ -49,7 +49,7 @@ vars:
   profile: "standard"
   merge: "false"
   spurBin: "spur"
-  agent: "omp"
+  agent: "auto"
   stepTimeoutMs: "1800000"
   # Corpus-aware quality gate for the feature-transition hop (R1, task 0625).
   # The per-task gate (`spur-check`) deliberately excludes corpus-check — the only

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.3.68",
+    "version": "0.3.69",
     "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",

package/plugins/sp/plugin.json

@@ -1,6 +1,6 @@
 {
     "name": "sp",
-    "version": "0.3.68",
+    "version": "0.3.69",
     "description": "Spur — a local-first harness engineering toolkit that wraps mainstream coding agents with constraint checking, workflow orchestration, and history analytics.",
     "extensions": {
         "pi": ["./hooks/pi/guard-extension.ts"]

package/plugins/sp/scripts/surface-drift-inventory.ts

@@ -473,11 +473,7 @@ export function executeScripts(root: string = PLUGIN_ROOT): void {
         writeFileSync(
             fake,
             `#!/bin/sh
-if [ "$1" = task ] && [ "$2" = show ]; then
-    printf '%s' '{"content":"### Requirements\\n- [ ] R1. x\\n### Plan\\n- [ ] p1"}'
-else
-    printf '%s' '{"agents":[{"capabilityTier":"standard"}]}'
-fi
+printf '%s' '{"content":"### Requirements\\n- [ ] R1. x\\n### Plan\\n- [ ] p1"}'
 `,
         );
         chmodSync(fake, 0o755);
@@ -485,7 +481,7 @@ fi
         try {
             execFileSync(
                 process.execPath,
-                [join(root, 'scripts', 'task-size-precheck.ts'), '0487', '--spur-bin', fake, '--executor', 'standard'],
+                [join(root, 'scripts', 'task-size-precheck.ts'), '0487', '--spur-bin', fake],
                 { cwd: dir, encoding: 'utf8', timeout: 30_000, stdio: 'pipe' },
             );
             const content = readFileSync(statusPath, 'utf8');
@@ -687,15 +683,6 @@ export function probeJsonShapes(run: CliRunner = runCli): void {
             { file: 'plugins/sp/scripts/surface-drift-inventory.ts', line: 1 },
         );
     }
-    const doctor = jsonEnvelopeShapes['spur agent doctor omp'];
-    const capOk = (doctor?.keys ?? []).some((k) => k.endsWith('.capabilityTier'));
-    record(
-        'agent doctor <name> --json -> agents[0].capabilityTier (asserted by task-size-precheck.ts:130)',
-        'json-exec(field-presence)',
-        capOk ? 'ok' : 'mismatch',
-        capOk ? 'field present in live envelope' : 'field ABSENT from live envelope',
-        { file: 'plugins/sp/scripts/task-size-precheck.ts', line: 130 },
-    );
     // Curated prose flag-claims: assertions phrased as prose ("no explicit `--flag`") that the
     // generic backtick-span extractor cannot scope to a command. Extend this list when a prose
     // claim is found; each entry is verified against the live help capture.

package/plugins/sp/scripts/task-size-precheck.ts

@@ -1,24 +1,23 @@
 #!/usr/bin/env bun
 /**
- * task-size-precheck — pipeline size precheck guard (R2, task 0454) plus the
- * size-vs-executor-capability gate (R3, task 0487).
+ * task-size-precheck — pipeline size precheck guard (R2, task 0454; count-only
+ * since task 0723).
  *
  * Shells `spur task show <wbs> --json`, evaluates R-item count and Plan
- * checklist count against limits, writes PASS/FAIL to status file. With
- * `--executor`, also shells `spur agent doctor <exec> --json` and blocks a large
- * task routed to a sub-`capable-1` executor.
+ * checklist count against limits, writes PASS/FAIL to status file. No executor
+ * or doctor involvement: executor liveness/routing/capabilities are attested
+ * fail-closed at the `agent.run` dispatch boundary, not predicted here.
  *
- * Always exits 0 (soft check, like doctor). The precheck→implement guard in
- * task-pipeline.yaml reads the status file.
+ * Always exits 0 (soft action). The precheck→implement guard in
+ * task-pipeline.yaml reads the status file; a missing or failing checker writes
+ * FAIL, so readiness fails closed.
  *
  * Ships with the plugin to arbitrary projects, so it stays node-builtin-only —
- * no workspace imports. The capability tier therefore comes from the CLI rather
- * than from `getExecutorTier` directly; `spur agent doctor --json` exposes it as
- * `capabilityTier` precisely so the inference regex is not duplicated here.
+ * no workspace imports.
  *
  * Usage:
  *   bun plugins/sp/scripts/task-size-precheck.ts <wbs> [--spur-bin <path>]
- *     [--max-reqs <n>] [--max-plan-items <n>] [--executor <name>]
+ *     [--max-reqs <n>] [--max-plan-items <n>]
  *
  * Env: SPUR_BIN, MAX_IMPLEMENT_REQS, MAX_IMPLEMENT_PLAN_ITEMS
  */
@@ -27,7 +26,6 @@ import { execFileSync } from 'node:child_process';
 import { existsSync, mkdirSync, writeFileSync } from 'node:fs';
 import { join } from 'node:path';
 import { fileURLToPath } from 'node:url';
-import { STAGE_FLOOR_TIER, TIER_ORDER } from './stage-registry-adapter';
 
 // ─── Regex (sync with packages/app/src/services/task-size-precheck.ts) ───────
 
@@ -37,32 +35,11 @@ const R_ITEM_RE = /^\s*-\s*\[[ xX]\]\s*(\*\*)?R\d+\./m;
 /** Matches checklist items under the Plan section. */
 const CHECKLIST_ITEM_RE = /^\s*-\s*\[[ xX]\]/m;
 
-/**
- * Large-task thresholds for the capability gate (R3, task 0487) — the DEFAULT
- * caps, not the overridable `--max-*` limits. Raising the caps says "I accept a
- * big task"; it does not make a flash-tier model able to finish one inside
- * `implementTimeoutMs`.
- */
-const LARGE_TASK_REQS = 5;
-const LARGE_TASK_PLAN_ITEMS = 8;
-
-/**
- * Capability tiers strong enough for a large task (R3, task 0487). The floor is
- * the `review` stage's Layer-1 tier — `reviewer` per `references/roles.md`,
- * read via the stage-registry adapter (0538 R4: no tier literal here; roles.md
- * is the pointer). Tiers at or above the floor pass. An unreachable roles.md
- * degrades to the pre-reconcile band — fail-closed for a safety gate.
- */
-const CAPABLE_TIERS: ReadonlySet<string> = (() => {
-    const floor = STAGE_FLOOR_TIER.get('review') ?? 'capable-1';
-    return new Set(TIER_ORDER.slice(Math.max(0, TIER_ORDER.indexOf(floor))));
-})();
-
 // ─── CLI ─────────────────────────────────────────────────────────────────────
 
 function usage(): never {
     console.error(
-        'Usage: bun plugins/sp/scripts/task-size-precheck.ts <wbs> [--spur-bin <path>] [--max-reqs <n>] [--max-plan-items <n>] [--executor <name>]',
+        'Usage: bun plugins/sp/scripts/task-size-precheck.ts <wbs> [--spur-bin <path>] [--max-reqs <n>] [--max-plan-items <n>]',
     );
     process.exit(1);
 }
@@ -87,13 +64,14 @@ function parseArgs(argv: string[]): {
     spurBin: string;
     maxReqs: number;
     maxPlanItems: number;
-    executor: string;
 } {
     let spurBin = defaultSpurBin();
     let wbs = '';
-    let maxReqs = Number(process.env.MAX_IMPLEMENT_REQS) || 5;
-    let maxPlanItems = Number(process.env.MAX_IMPLEMENT_PLAN_ITEMS) || 8;
-    let executor = '';
+    // Doubled deterministic ceiling (0723 operator decision): 10 R-items / 16
+    // Plan items — keep in sync with DEFAULT_TASK_SIZE_LIMITS in
+    // packages/app/src/services/task-size-precheck.ts (asserted by test).
+    let maxReqs = Number(process.env.MAX_IMPLEMENT_REQS) || 10;
+    let maxPlanItems = Number(process.env.MAX_IMPLEMENT_PLAN_ITEMS) || 16;
 
     let i = 0;
     while (i < argv.length) {
@@ -102,13 +80,10 @@ function parseArgs(argv: string[]): {
             spurBin = argv[i + 1] ?? defaultSpurBin();
             i += 2;
         } else if (arg === '--max-reqs') {
-            maxReqs = Number(argv[i + 1]) || 5;
+            maxReqs = Number(argv[i + 1]) || 10;
             i += 2;
         } else if (arg === '--max-plan-items') {
-            maxPlanItems = Number(argv[i + 1]) || 8;
-            i += 2;
-        } else if (arg === '--executor') {
-            executor = argv[i + 1] ?? '';
+            maxPlanItems = Number(argv[i + 1]) || 16;
             i += 2;
         } else if (!arg.startsWith('--')) {
             wbs = arg;
@@ -119,7 +94,7 @@ function parseArgs(argv: string[]): {
     }
 
     if (!wbs) usage();
-    return { wbs, spurBin, maxReqs, maxPlanItems, executor };
+    return { wbs, spurBin, maxReqs, maxPlanItems };
 }
 
 /**
@@ -135,29 +110,8 @@ function runSpur(spurBin: string, args: string[]): string {
     });
 }
 
-/**
- * Capability tier of `executor` per `spur agent doctor <exec> --json`.
- * Unknown executor, unreadable doctor output, or an undeclared-and-uninferrable
- * tier all read as `standard` — conservative: a false block is one flag away,
- * a false pass costs a 30-minute timed-out implement.
- */
-function resolveCapabilityTier(spurBin: string, executor: string): { tier: string; resolvedName: string } {
-    try {
-        const out = runSpur(spurBin, ['agent', 'doctor', executor, '--json']);
-        const row = JSON.parse(out)?.agents?.[0];
-        const tier = row?.capabilityTier;
-        // R1 (0622 F2/F4 residue): `doctor <role>` resolves the role to its cheapest
-        // eligible executor (`coder` → `omp`); surface the resolved executor name in
-        // the block message, not the role the caller passed in.
-        const resolvedName = typeof row?.agent === 'string' && row.agent.length > 0 ? row.agent : executor;
-        return { tier: typeof tier === 'string' && tier ? tier : 'standard', resolvedName };
-    } catch {
-        return { tier: 'standard', resolvedName: executor };
-    }
-}
-
 function main(): void {
-    const { wbs, spurBin, maxReqs, maxPlanItems, executor } = parseArgs(process.argv.slice(2));
+    const { wbs, spurBin, maxReqs, maxPlanItems } = parseArgs(process.argv.slice(2));
 
     // Fetch task content via spur
     let taskContent: string;
@@ -166,7 +120,7 @@ function main(): void {
         const task = JSON.parse(result);
         taskContent = task.content ?? task.body ?? '';
     } catch {
-        // If spur fails, write FAIL and exit 0 (soft, like doctor)
+        // If spur fails, write FAIL and exit 0 — the status file carries the verdict
         const statusDir = join(process.cwd(), '.spur', 'run');
         if (!existsSync(statusDir)) mkdirSync(statusDir, { recursive: true });
         writeFileSync(join(statusDir, `${wbs}-precheck-size.status`), 'FAIL\n');
@@ -187,18 +141,6 @@ function main(): void {
     const planItemCount = planBody.match(new RegExp(CHECKLIST_ITEM_RE.source, 'gm'))?.length ?? 0;
 
     const reasons: string[] = [];
-    // R3 (0487): a large task on a sub-capable executor blocks even when the caller
-    // raised the caps — the caps are an acceptance of size, not a capability grant.
-    if (executor && (reqCount > LARGE_TASK_REQS || planItemCount > LARGE_TASK_PLAN_ITEMS)) {
-        const { tier, resolvedName } = resolveCapabilityTier(spurBin, executor);
-        if (!CAPABLE_TIERS.has(tier)) {
-            reasons.push(
-                `Task size (${reqCount} R-items / ${planItemCount} Plan items) requires a capable executor, ` +
-                    `but ${resolvedName} is tier ${tier}. ` +
-                    `Pass \`--agent <capable>\` or \`--vars '{"implementAgent":"<capable>"}'\`, or split the task.`,
-            );
-        }
-    }
     if (reqCount > maxReqs) {
         reasons.push(
             `Task has ${reqCount} R-items (max ${maxReqs}). ` +

package/plugins/sp/skills/spur-dev/references/cross-cutting.md

@@ -139,7 +139,8 @@ resolved in this order; first match wins:
 2. **`agent.default`** from `.spur/config.yaml` (project layer, then `~/.config/spur/config.yaml`) —
    `spur workflow run` injects it as the `agent` var when `vars.agent` was not set by the caller.
 3. **YAML literal `agent:` in the pipeline file** — the last-resort fallback declared in the
-   workflow YAML (e.g. `agent: "omp"` in `task-pipeline.yaml`). This fires only when no
+   workflow YAML. Every shipped pipeline declares `agent: "auto"`, so this rung resolves through
+   the role/tier ladder instead of pinning an executor name; it fires only when no
    `agent.default` is configured anywhere.
 
 `--agent auto` tier-resolves an executor (stage `model_policy` → `agent.default` → tier priority)

package/spur.js

@@ -78919,6 +78919,12 @@ function safeJsonParse(raw) {
     return null;
   }
 }
+function outputTail(text4) {
+  const trimmed = text4.trim();
+  if (trimmed === "")
+    return "";
+  return `: ${trimmed.length > 400 ? `\u2026${trimmed.slice(-400)}` : trimmed}`;
+}
 function validateHistoryRefreshPayload(raw) {
   if (typeof raw !== "object" || raw === null || Array.isArray(raw)) {
     throw new Error("history refresh payload must be a JSON object");
@@ -79005,7 +79011,7 @@ async function handleHistoryRefreshJob(deps, job) {
     throw new Error(split.error);
   const result = await deps.executor.run({
     command: split.command,
-    args: [...split.leadingArgs, "history", "daily", "--json", "--json-envelope"],
+    args: [...split.leadingArgs, "--no-logo", "history", "daily"],
     cwd: deps.cwd,
     env: {
       [HISTORY_REFRESH_CONTEXT_ENV]: JSON.stringify(payload),
@@ -79013,30 +79019,13 @@ async function handleHistoryRefreshJob(deps, job) {
     },
     maxOutput: HISTORY_REFRESH_MAX_OUTPUT
   });
-  const stderrDetail = result.stderr === "" ? "" : `: ${result.stderr.length > 400 ? `\u2026${result.stderr.slice(-400)}` : result.stderr}`;
+  const stderrDetail = outputTail(result.stderr);
   if (result.exitCode === null) {
     const signalDetail = result.signal === undefined ? "" : ` (${result.signal})`;
     throw new Error(`history refresh child terminated before a normal exit${signalDetail}${stderrDetail}`);
   }
   if (result.exitCode !== 0) {
-    let stdoutDetail = "";
-    try {
-      const failure = JSON.parse(result.stdout);
-      const message = failure.ok === false ? failure.error?.message : undefined;
-      if (typeof message === "string" && message !== "") {
-        stdoutDetail = `: ${message.length > 400 ? `\u2026${message.slice(-400)}` : message}`;
-      }
-    } catch {}
-    throw new Error(`history daily exited ${result.exitCode}${stdoutDetail || stderrDetail}`);
-  }
-  let parsed;
-  try {
-    parsed = JSON.parse(result.stdout);
-  } catch (e) {
-    throw new Error(`history daily emitted invalid JSON: ${e instanceof Error ? e.message : String(e)}`);
-  }
-  if (parsed.ok !== true || typeof parsed.data !== "object" || parsed.data === null) {
-    throw new Error("history daily emitted an unexpected JSON shape (expected {ok:true,data})");
+    throw new Error(`history daily exited ${result.exitCode}${outputTail(result.stdout) || stderrDetail}`);
   }
 }
 var HISTORY_REFRESH_JOB = "history.refresh", HISTORY_REFRESH_CONTEXT_ENV = "SPUR_HISTORY_REFRESH_CONTEXT", HISTORY_REFRESH_MAX_OUTPUT = 1e6;
@@ -82421,9 +82410,6 @@ var init_task_scaffold = __esm(() => {
 });
 
 // ../../packages/app/src/services/task-size-precheck.ts
-function isBelowCapable(tier) {
-  return TIER_RANK[tier ?? "standard"] < TIER_RANK["capable-1"];
-}
 function countRItems(content) {
   const matches = content.match(new RegExp(R_ITEM_RE.source, "gm"));
   return matches?.length ?? 0;
@@ -82439,13 +82425,10 @@ function countPlanItems(content) {
   const matches = planBody.match(new RegExp(CHECKLIST_ITEM_RE.source, "gm"));
   return matches?.length ?? 0;
 }
-function evaluateTaskSize(content, limits = DEFAULT_TASK_SIZE_LIMITS, executor) {
+function evaluateTaskSize(content, limits = DEFAULT_TASK_SIZE_LIMITS) {
   const reqCount = countRItems(content);
   const planItemCount = countPlanItems(content);
   const reasons = [];
-  if (executor !== undefined && isBelowCapable(executor.tier) && (reqCount > LARGE_TASK_THRESHOLDS.maxReqs || planItemCount > LARGE_TASK_THRESHOLDS.maxPlanItems)) {
-    reasons.push(`Task size (${reqCount} R-items / ${planItemCount} Plan items) requires a capable executor, ` + `but ${executor.name} is tier ${executor.tier ?? "standard"}. ` + `Pass \`--agent <capable>\` or \`--vars '{"implementAgent":"<capable>"}'\`, or split the task.`);
-  }
   if (reqCount > limits.maxReqs) {
     reasons.push(`Task has ${reqCount} R-items (max ${limits.maxReqs}). ` + `Consider decomposing into smaller tasks or raise maxImplementReqs via --vars.`);
   }
@@ -82459,14 +82442,12 @@ function evaluateTaskSize(content, limits = DEFAULT_TASK_SIZE_LIMITS, executor)
     reasons
   };
 }
-var DEFAULT_TASK_SIZE_LIMITS, LARGE_TASK_THRESHOLDS, R_ITEM_RE, CHECKLIST_ITEM_RE;
+var DEFAULT_TASK_SIZE_LIMITS, R_ITEM_RE, CHECKLIST_ITEM_RE;
 var init_task_size_precheck = __esm(() => {
-  init_src2();
   DEFAULT_TASK_SIZE_LIMITS = {
-    maxReqs: 5,
-    maxPlanItems: 8
+    maxReqs: 10,
+    maxPlanItems: 16
   };
-  LARGE_TASK_THRESHOLDS = DEFAULT_TASK_SIZE_LIMITS;
   R_ITEM_RE = /^\s*-\s*\[[ xX]\]\s*(\*\*)?R\d+\./m;
   CHECKLIST_ITEM_RE = /^\s*-\s*\[[ xX]\]/m;
 });
@@ -98246,7 +98227,7 @@ import { createRequire } from "module";
 var CLI_CONFIG = {
   binaryName: "spur",
   binaryLabel: "spur",
-  binaryVersion: "0.3.68",
+  binaryVersion: "0.3.69",
   configDir: ".spur",
   configFile: ".spur/config.yaml",
   databaseFile: ".spur/spur.db"