loki-mode 11.40.0 → 11.42.0

package/SKILL.md

@@ -3,7 +3,7 @@ name: loki-mode
 description: Runs an autonomous software factory that knows what it is supposed to deliver and proves it did, with a signed receipt. Use when the user says Loki Mode or asks to build, fix or verify software autonomously.
 ---
 
-# Loki Mode v11.40.0
+# Loki Mode v11.42.0
 
 **Current entry points (Loki 10 engine):** `loki "<task>"`, `loki owner/repo#N` and `loki quick "<task>"` run the Loki 10 engine and end with a signed receipt (`loki verify`). `loki backlog owner/repo --all` runs many issues in parallel. Guide: `docs/v10/GUIDE.md`. The skill instructions below, and `loki start`, describe the previous bash loop. PRD-file starts (`loki start ./prd.md`) and the opencode provider still run on it until FC38-SWEEP ports them; the legacy-engine command and the LOKI_ENGINE switch remain removed. Prefer `loki owner/repo#N` for issues.
 
@@ -476,4 +476,4 @@ Implemented, planned and deprecated items, with the version each landed in: `ski
 
 ---
 
-**v11.40.0 | [Autonomi](https://www.autonomi.dev/) flagship product | core skill**
+**v11.42.0 | [Autonomi](https://www.autonomi.dev/) flagship product | core skill**

package/VERSION

@@ -1 +1 @@
-11.40.0
+11.42.0

package/autonomy/lib/efficiency_cost.py

@@ -32,6 +32,7 @@ __all__ = [
     "read_child_ledger",
     "load_prices",
     "price_from_tokens",
+    "inference_geo_multiplier",
     "DEFAULT_PRICES_PATH",
 ]
 
@@ -48,6 +49,29 @@ DEFAULT_PRICES_PATH = os.path.join(
 # small helpers (self-contained copies; proof-generator.py keeps its own)
 # ---------------------------------------------------------------------------
 
+# Price multiplier for LOKI_INFERENCE_GEO, read from the same file the TS gate
+# reads (inference_geo_multipliers in loki-ts/data/model-pricing.json). Unset,
+# global and unknown values are 1.0; an unreadable file falls back to 1.1 for
+# "us" so a budget never silently under-counts.
+MODEL_PRICING_PATH = os.path.join(_REPO_ROOT, "loki-ts", "data", "model-pricing.json")
+
+
+def inference_geo_multiplier(env=None, pricing_path=None):
+    geo = ((env if env is not None else os.environ).get("LOKI_INFERENCE_GEO") or "").strip().lower()
+    if not geo:
+        return 1.0
+    table = None
+    try:
+        with open(pricing_path or MODEL_PRICING_PATH, "r") as f:
+            table = json.load(f).get("inference_geo_multipliers")
+    except Exception:
+        table = None
+    if not isinstance(table, dict):
+        table = {"us": 1.1}
+    m = table.get(geo)
+    return float(m) if isinstance(m, (int, float)) and m > 0 else 1.0
+
+
 def _read_json(path, default=None):
     try:
         with open(path, "r") as f:

package/autonomy/run.sh

@@ -18235,16 +18235,14 @@ metadata. This saves tokens without treating dependency changes as unreviewed.""
 
 _persona_line = (persona.strip() + "\n\n") if persona.strip() else ""
 
-prompt = f"""{_persona_line}You are {name}. Your SOLE focus is: {focus}.
-
-Review ONLY for: {checks}.
-
-Files changed:
+# #270: the shared Files and Review context block, evidence and calibration come FIRST and the per-reviewer
+# role last, so parallel reviewers of one gate share a byte-identical cacheable prefix. Mirrors
+# buildReviewerPrompt in loki-ts/src/runner/quality_gates.ts.
+prompt = f"""Files changed:
 {files}
 
 Review context:
 {diff}
-{requirements_section}
 
 {review_context_note}
 
@@ -18254,6 +18252,11 @@ Build: {json.dumps(build, sort_keys=True, ensure_ascii=True)}
 
 {severity_calibration}
 
+{_persona_line}You are {name}. Your SOLE focus is: {focus}.
+
+Review ONLY for: {checks}.
+{requirements_section}
+
 {output_format}"""
 
 prompt_bytes = prompt.encode("utf-8")
@@ -20502,8 +20505,16 @@ check_budget_limit() {
     # Calculate cost from per-iteration efficiency files (same source as /api/cost)
     if [ -d "$efficiency_dir" ]; then
         current_cost=$(python3 -c "
-import json, glob
+import json, glob, os, sys
 total = 0.0
+# LOKI_INFERENCE_GEO multiplier on token-priced records, from the same JSON the
+# TS gate reads (autonomy/lib/efficiency_cost.py); the fallback keeps us at 1.1.
+try:
+    sys.path.insert(0, '${SCRIPT_DIR}/lib')
+    from efficiency_cost import inference_geo_multiplier
+    geo = inference_geo_multiplier()
+except Exception:
+    geo = 1.1 if os.environ.get('LOKI_INFERENCE_GEO', '').strip().lower() == 'us' else 1.0
 pricing = {
     'fable': {'input': 10.00, 'output': 50.00, 'cache_read': 0.25, 'cache_write': 12.5, 'cache_write_1h': 20},
     'claude-fable-5': {'input': 10.00, 'output': 50.00, 'cache_read': 0.25, 'cache_write': 12.5, 'cache_write_1h': 20},
@@ -20544,8 +20555,9 @@ for f in glob.glob('${efficiency_dir}/*.json'):
             # same run reports two different spends.
             cr = d.get('cache_read_tokens', 0) or 0
             cw = d.get('cache_creation_tokens', 0) or 0
-            total += (inp / 1_000_000) * p['input'] + (out / 1_000_000) * p['output']
-            total += (cr / 1_000_000) * p.get('cache_read', p['input'] * 0.1) + (cw / 1_000_000) * p.get('cache_write', p['input'] * 1.25)
+            rec = (inp / 1_000_000) * p['input'] + (out / 1_000_000) * p['output']
+            rec += (cr / 1_000_000) * p.get('cache_read', p['input'] * 0.1) + (cw / 1_000_000) * p.get('cache_write', p['input'] * 1.25)
+            total += rec * geo
     except: pass
 print(round(total, 4))
 " 2>/dev/null || echo "0")

package/dashboard/__init__.py

@@ -7,6 +7,6 @@ Modules:
     control: Session control helpers (status, atomic writes, origin check)
 """
 
-__version__ = "11.40.0"
+__version__ = "11.42.0"
 
 __all__ = ["__version__"]

package/dashboard/server.py

@@ -7830,6 +7830,25 @@ def _record_is_measured(rec: Any) -> bool:
     return False
 
 
+def _inference_geo_multiplier() -> float:
+    """LOKI_INFERENCE_GEO price multiplier. Mirrors inference_geo_multiplier() in
+    autonomy/lib/efficiency_cost.py (same JSON key, us falls back to 1.1); kept as
+    a local copy for the same reason as _MEASURED_FIELDS."""
+    geo = (os.environ.get("LOKI_INFERENCE_GEO") or "").strip().lower()
+    if not geo:
+        return 1.0
+    table = None
+    try:
+        path = _Path(__file__).resolve().parent.parent / "loki-ts" / "data" / "model-pricing.json"
+        table = json.loads(path.read_text()).get("inference_geo_multipliers")
+    except Exception:
+        table = None
+    if not isinstance(table, dict):
+        table = {"us": 1.1}
+    m = table.get(geo)
+    return float(m) if isinstance(m, (int, float)) and m > 0 else 1.0
+
+
 def _calculate_model_cost(
     model: str,
     input_tokens: int,
@@ -7856,7 +7875,9 @@ def _calculate_model_cost(
     output_cost = (output_tokens / 1_000_000) * pricing.get("output", 15.00)
     cache_read_cost = (cache_read_tokens / 1_000_000) * pricing.get("cache_read", inp_rate * 0.1)
     cache_write_cost = (cache_creation_tokens / 1_000_000) * pricing.get("cache_write", inp_rate * 1.25)
-    return round(input_cost + output_cost + cache_read_cost + cache_write_cost, 6)
+    return round(
+        (input_cost + output_cost + cache_read_cost + cache_write_cost) * _inference_geo_multiplier(), 6
+    )
 
 
 @app.get("/api/cost", dependencies=[Depends(auth.require_scope("read"))])

package/docs/CLI-REFERENCE.md

@@ -1,6 +1,6 @@
 # CLI reference
 
-Generated from `loki-ts/src/cli/registry.ts` by `scripts/generate-stale-zero.sh` for v11.40.0. Do not edit by hand.
+Generated from `loki-ts/src/cli/registry.ts` by `scripts/generate-stale-zero.sh` for v11.42.0. Do not edit by hand.
 Hidden and legacy-only commands are omitted; see `docs/v10/CLI-MODERN.md` for the full inventory.
 
 | Command | Description |

package/docs/INSTALLATION.md

@@ -2,7 +2,7 @@
 
 Loki Mode, by [Autonomi](https://www.autonomi.dev/), turns a spec or an issue into a verified pull request with a receipt you can check. This page covers installing it, a first run, and the options around it.
 
-**Version:** v11.40.0
+**Version:** v11.42.0
 
 **Engine note:** `loki start` is the primary command. `loki start`, `loki "<task>"`, `loki owner/repo#N` and `loki quick` all run the Loki 10 engine, whatever the flag order or input form (PRD file, issue ref, task or one-word brief). The previous loop runs only on `--engine legacy`, `LOKI_ENGINE=legacy`, or for one call when a flag Loki 10 cannot honor is present. See the [user guide](v10/GUIDE.md) and the [5-minute quickstart](QUICKSTART.md).
 

package/loki-ts/data/model-pricing.json

@@ -3,6 +3,7 @@
   "_comment": "Rolling pricing table consumed by loki-ts/src/runner/budget.ts. Update this file when Anthropic / OpenAI / others publish new prices; no code change required. Pricing is USD per 1 million tokens. Aliases (opus/sonnet/haiku) point to the latest model of that family per providers/model_catalog.json.",
   "_updated": "2026-10-08",
   "default_max_cost_usd": 100,
+  "inference_geo_multipliers": {"us": 1.1},
   "_source": "https://platform.claude.com/docs/en/about-claude/pricing (docs.anthropic.com/en/docs/about-claude/pricing 301-redirects there), read 2026-10-08. Per MTok. fable=Claude Fable 5.1 $10/$50, cache read $0.25 (0.025x), 5m write $12.50, 1h write $20. opus=Claude Opus 5.5 $4/$20, cache read $0.20 (0.05x), 5m write $5, 1h write $8. sonnet=Claude Sonnet 5.5 $2/$10, cache read $0.10 (0.05x), 5m write $2.50, 1h write $4. haiku alias row prices as its catalog target claude-haiku-5-5 (providers/model_catalog.json cli_aliases), so it equals that row including over_100k; Haiku 4.5 ($1/$5) is no longer an alias target. claude-haiku-5-5 (exact id, same as the haiku alias): $0.10/$0.50, read $0.01, 5m $0.125, 1h $0.20 up to 100,000 prompt tokens; over_100k $0.50/$2.50, read $0.05, 5m $0.625, 1h $1. Fields: cache_write is the 5m write rate (legacy readers); cache_write_5m and cache_write_1h are the explicit tiers. Multipliers: 5m write 1.25x, 1h write 2x, read 0.1x (0.05x on Opus 5.5 and Sonnet 5.5, 0.025x on Fable 5.1). OpenAI rows (gpt-5.3-codex, gpt-5.6-sol/terra/luna): https://developers.openai.com/api/docs/pricing, read 2026-10-08, Standard tier, short context (up to 272K); cached input is the cache_read field; OpenAI bills no cache write, cache_write is a 1.25x placeholder.",
   "pricing": {
     "fable": {