Phase 23 refinement — per-staffer tool_level variance

Staffer.tool_level now controls which subsystems a specific run gets: full — qwen3.5 + qwen3 + cloud T3 + cloud rescue local — qwen3.5 + qwen3 + local gpt-oss:20b T3 + rescue basic — qwen2.5 + qwen2.5 + local T3, no rescue minimal — qwen2.5 + qwen2.5, NO T3, NO rescue. Playbook inheritance only. applyToolLevel() mutates module-scoped ACTIVE_* slots each run from the env defaults, so prior staffer's overrides never leak. Hot-path code reads ACTIVE_EXECUTOR / ACTIVE_REVIEWER / ACTIVE_T3_DISABLED / ACTIVE_OVERVIEW_CLOUD / ACTIVE_RETRY_ON_FAIL instead of the baked constants. The architectural question this answers: does playbook_memory inheritance carry enough knowledge to let a weakly-tooled coordinator still produce usable outcomes? "Minimal" Alex runs qwen2.5 exec + no reviewer overseer + no cloud rescue. If Alex still fills events at a reasonable rate, the playbook system is the real knowledge carrier — the senior stack is nice-to-have, not the sine qua non. Demo personas mapped: Maria (senior, 48mo, full) James (mid, 14mo, local) Sam (junior, 4mo, basic) Alex (trainee, 1mo, minimal) Same 3 contracts (Nashville downtown, Joliet warehouse, Indianapolis assembly) across all four → 12 runs. KB + kb_staffer_report.py leaderboard already wired; competence_score will now reflect real tool asymmetry instead of LLM sampling variance.
2026-04-20 22:50:05 -05:00
parent 6b71c8e9b2
commit 5e89407939
14 changed files with 119 additions and 42 deletions
@@ -13,7 +13,8 @@
    "id": "S-001",
    "name": "Maria Chen",
    "tenure_months": 48,
-    "role": "senior"
+    "role": "senior",
+    "tool_level": "full"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-001",
    "name": "Maria Chen",
    "tenure_months": 48,
-    "role": "senior"
+    "role": "senior",
+    "tool_level": "full"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-001",
    "name": "Maria Chen",
    "tenure_months": 48,
-    "role": "senior"
+    "role": "senior",
+    "tool_level": "full"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-002",
    "name": "James Park",
    "tenure_months": 14,
-    "role": "mid"
+    "role": "mid",
+    "tool_level": "local"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-002",
    "name": "James Park",
    "tenure_months": 14,
-    "role": "mid"
+    "role": "mid",
+    "tool_level": "local"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-002",
    "name": "James Park",
    "tenure_months": 14,
-    "role": "mid"
+    "role": "mid",
+    "tool_level": "local"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-003",
    "name": "Sam Torres",
    "tenure_months": 4,
-    "role": "junior"
+    "role": "junior",
+    "tool_level": "basic"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-003",
    "name": "Sam Torres",
    "tenure_months": 4,
-    "role": "junior"
+    "role": "junior",
+    "tool_level": "basic"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-003",
    "name": "Sam Torres",
    "tenure_months": 4,
-    "role": "junior"
+    "role": "junior",
+    "tool_level": "basic"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-004",
    "name": "Alex Rivera",
    "tenure_months": 1,
-    "role": "trainee"
+    "role": "trainee",
+    "tool_level": "minimal"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-004",
    "name": "Alex Rivera",
    "tenure_months": 1,
-    "role": "trainee"
+    "role": "trainee",
+    "tool_level": "minimal"
  },
  "events": [
    {
@@ -13,7 +13,8 @@
    "id": "S-004",
    "name": "Alex Rivera",
    "tenure_months": 1,
-    "role": "trainee"
+    "role": "trainee",
+    "tool_level": "minimal"
  },
  "events": [
    {