loki-mode 8.16.0 → 8.16.2

package/SKILL.md

@@ -3,7 +3,7 @@ name: loki-mode
 description: Autonomous spec-driven build system with a built-in trust layer. It does not call work done until it is verified (RARV-C closure loop, 8 quality gates, completion council, verified-completion evidence gate). Triggers on "Loki Mode". Takes a spec (PRD, GitHub issue, OpenAPI doc, etc.) to deployed product with minimal human intervention. Provider-agnostic. Requires --dangerously-skip-permissions flag.
 ---
 
-# Loki Mode v8.16.0
+# Loki Mode v8.16.2
 
 **You are an autonomous agent. You make decisions. You do not ask questions. You do not stop.**
 
@@ -469,4 +469,4 @@ See `CHANGELOG.md` entries [7.5.7], [7.5.8], [7.5.13] for the per-fix list and r
 
 ---
 
-**v8.16.0 | [Autonomi](https://www.autonomi.dev/) flagship product | ~410 lines core**
+**v8.16.2 | [Autonomi](https://www.autonomi.dev/) flagship product | ~410 lines core**

package/VERSION

@@ -1 +1 @@
-8.16.0
+8.16.2

package/autonomy/lib/trust_metrics.py

@@ -376,11 +376,17 @@ def _proof_cost(proof):
         usd = None
     tokens = cost.get("total_tokens")
     if tokens is None:
-        # Some proofs carry input/output separately.
-        it = cost.get("input_tokens")
-        ot = cost.get("output_tokens")
-        if it is not None or ot is not None:
-            tokens = _to_int(it, 0) + _to_int(ot, 0)
+        # Some proofs carry the components separately. Sum ALL of them,
+        # including the cache tiers: the proof generator records
+        # cache_read_tokens, and on real traffic they are ~98% of input volume.
+        # Adding only input+output reported 16,436 tokens for a proof whose own
+        # record totals 893,701 -- a 54x undercount feeding cost-per-verified,
+        # which is a published benchmark number.
+        parts = [cost.get(k) for k in
+                 ("input_tokens", "output_tokens",
+                  "cache_read_tokens", "cache_creation_tokens")]
+        if any(v is not None for v in parts):
+            tokens = sum(_to_int(v, 0) for v in parts)
     try:
         tokens = int(tokens) if tokens is not None else None
     except (TypeError, ValueError):

package/dashboard/__init__.py

@@ -7,7 +7,7 @@ Modules:
     control: Session control API (start/stop/pause/resume)
 """
 
-__version__ = "8.16.0"
+__version__ = "8.16.2"
 
 # Expose the control app for easy import
 try:

package/dashboard/server.py

@@ -7338,13 +7338,33 @@ def _get_model_pricing() -> dict:
     return _MODEL_PRICING
 
 
-def _calculate_model_cost(model: str, input_tokens: int, output_tokens: int) -> float:
-    """Calculate USD cost for a model's token usage."""
+def _calculate_model_cost(
+    model: str,
+    input_tokens: int,
+    output_tokens: int,
+    cache_read_tokens: int = 0,
+    cache_creation_tokens: int = 0,
+) -> float:
+    """Calculate USD cost for a model's token usage, including cache tiers.
+
+    Cache tokens DOMINATE real traffic -- a measured iteration carried 797,496
+    cache-read against 10,272 plain input tokens. Pricing them at zero, which
+    this did, under-counted a real iteration by roughly 5x. This is the third
+    route to carry that same bug (bash check_budget_limit and the TS budget
+    breaker were fixed in v8.12); the rates match both.
+
+    An unpriced cache tier falls back to the FULL input rate rather than zero:
+    for anything driving a spend display the safe direction on an unknown rate
+    is to over-state, never to silently under-count.
+    """
     pricing_table = _get_model_pricing()
     pricing = pricing_table.get(model.lower(), pricing_table.get("sonnet", {}))
-    input_cost = (input_tokens / 1_000_000) * pricing.get("input", 3.00)
+    inp_rate = pricing.get("input", 3.00)
+    input_cost = (input_tokens / 1_000_000) * inp_rate
     output_cost = (output_tokens / 1_000_000) * pricing.get("output", 15.00)
-    return round(input_cost + output_cost, 6)
+    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)
 
 
 @app.get("/api/cost", dependencies=[Depends(auth.require_scope("read"))])
@@ -7365,6 +7385,8 @@ def _compute_cost_snapshot() -> dict:
 
     total_input = 0
     total_output = 0
+    total_cache_read = 0
+    total_cache_creation = 0
     estimated_cost = 0.0
     by_phase: dict = {}
     by_model: dict = {}
@@ -7390,15 +7412,22 @@ def _compute_cost_snapshot() -> dict:
 
                 inp = data.get("input_tokens", 0)
                 out = data.get("output_tokens", 0)
+                # Cache tiers: recorded per iteration since v6.82.0 and
+                # typically ~98% of input volume. Omitting them made this
+                # endpoint report roughly 1% of a run's real token count.
+                cr = data.get("cache_read_tokens", 0) or 0
+                cw = data.get("cache_creation_tokens", 0) or 0
                 model = data.get("model", "sonnet").lower()
                 phase = data.get("phase", "unknown")
 
                 total_input += inp
                 total_output += out
+                total_cache_read += cr
+                total_cache_creation += cw
 
                 cost = data.get("cost_usd")
                 if cost is None:
-                    cost = _calculate_model_cost(model, inp, out)
+                    cost = _calculate_model_cost(model, inp, out, cr, cw)
                 estimated_cost += cost
 
                 # Aggregate by phase
@@ -7464,9 +7493,18 @@ def _compute_cost_snapshot() -> dict:
         except (json.JSONDecodeError, KeyError):
             pass
 
+    # Cache hit ratio against everything read IN. Null (not 0.0) when nothing
+    # was read: a zero is a claim about a COLD cache, which is a real and
+    # expensive condition, so reporting it for a run with no data would send
+    # someone hunting a caching problem that does not exist.
+    _read_in = total_input + total_cache_read
     return {
         "total_input_tokens": total_input,
         "total_output_tokens": total_output,
+        "total_cache_read_tokens": total_cache_read,
+        "total_cache_creation_tokens": total_cache_creation,
+        "total_tokens": total_input + total_output + total_cache_read + total_cache_creation,
+        "cache_hit_ratio": round(total_cache_read / _read_in, 4) if _read_in > 0 else None,
         "estimated_cost_usd": round(estimated_cost, 6),
         "by_phase": {k: {
             "input_tokens": v["input_tokens"],

package/loki-ts/dist/loki.js

@@ -1,5 +1,5 @@
 // @bun
-var h_=Object.create;var{getPrototypeOf:v_,defineProperty:rK,getOwnPropertyNames:g_}=Object;var m_=Object.prototype.hasOwnProperty;function u_(Z){return this[Z]}var p_,d_,c_=(Z,X,Q)=>{var Y=Z!=null&&typeof Z==="object";if(Y){var J=X?p_??=new WeakMap:d_??=new WeakMap,z=J.get(Z);if(z)return z}Q=Z!=null?h_(v_(Z)):{};let K=X||!Z||!Z.__esModule?rK(Q,"default",{value:Z,enumerable:!0}):Q;for(let $ of g_(Z))if(!m_.call(K,$))rK(K,$,{get:u_.bind(Z,$),enumerable:!0});if(Y)J.set(Z,K);return K};var qQ=(Z,X)=>()=>(X||Z((X={exports:{}}).exports,X),X.exports);var l_=(Z)=>Z;function i_(Z,X){this[Z]=l_.bind(null,X)}var l0=(Z,X)=>{for(var Q in X)rK(Z,Q,{get:X[Q],enumerable:!0,configurable:!0,set:i_.bind(X,Q)})};var p=(Z,X)=>()=>(Z&&(X=Z(Z=0)),X);var e0=import.meta.require;var kO={};l0(kO,{lokiDir:()=>j0,homeLokiDir:()=>P4,findRepoRootForVersion:()=>eK,REPO_ROOT:()=>r0});import{resolve as n7,dirname as tK}from"path";import{fileURLToPath as a_}from"url";import{existsSync as GQ}from"fs";import{homedir as s_}from"os";function n_(){let Z=RO;for(let X=0;X<6;X++){if(GQ(n7(Z,"VERSION"))&&GQ(n7(Z,"autonomy/run.sh")))return Z;let Q=tK(Z);if(Q===Z)break;Z=Q}return n7(RO,"..","..","..")}function eK(Z){let X=Z;for(let Q=0;Q<6;Q++){if(GQ(n7(X,"VERSION"))&&GQ(n7(X,"autonomy/run.sh")))return X;let Y=tK(X);if(Y===X)break;X=Y}return n7(Z,"..","..","..")}function j0(){return process.env.LOKI_DIR??n7(process.cwd(),".loki")}function P4(){return n7(s_(),".loki")}var RO,r0;var G8=p(()=>{RO=tK(a_(import.meta.url));r0=n_()});import{readFileSync as o_}from"fs";import{resolve as r_,dirname as t_}from"path";import{fileURLToPath as e_}from"url";function f3(){if(h5!==null)return h5;let Z="8.16.0";if(typeof Z==="string"&&Z.length>0)return h5=Z,h5;try{let X=t_(e_(import.meta.url)),Q=eK(X);h5=o_(r_(Q,"VERSION"),"utf-8").trim()}catch{h5="unknown"}return h5}var h5=null;var HQ=p(()=>{G8()});var bO={};l0(bO,{runOrThrow:()=>Of,run:()=>E0,readStreamCapped:()=>UQ,commandVersion:()=>Af,commandExists:()=>X9,ShellError:()=>Z$,MAX_STDOUT_BYTES:()=>yO});async function UQ(Z,X=yO){let Q=Z.getReader(),Y=new TextDecoder,J="",z=0;try{while(z<X){let{done:K,value:$}=await Q.read();if(K)break;if(!$)continue;if(z+=$.byteLength,z>X){let W=$.byteLength-(z-X);J+=Y.decode($.subarray(0,W),{stream:!0});break}J+=Y.decode($,{stream:!0})}J+=Y.decode()}finally{try{await Q.cancel()}catch{}Q.releaseLock()}return J}async function E0(Z,X={}){let Q=Bun.spawn({cmd:[...Z],stdout:"pipe",stderr:"pipe",env:X.env?{...process.env,...X.env}:process.env,cwd:X.cwd}),Y,J;if(X.timeoutMs&&X.timeoutMs>0)Y=setTimeout(()=>{try{Q.kill("SIGTERM")}catch{}J=setTimeout(()=>{try{Q.kill("SIGKILL")}catch{}},2000)},X.timeoutMs);try{let[z,K,$]=await Promise.all([UQ(Q.stdout),new Response(Q.stderr).text(),Q.exited]);return{stdout:z,stderr:K,exitCode:$}}finally{if(Y)clearTimeout(Y);if(J)clearTimeout(J)}}async function Of(Z,X={}){let Q=await E0(Z,X);if(Q.exitCode!==0)throw new Z$(`command failed (${Q.exitCode}): ${Z.join(" ")}`,Q.exitCode,Q.stdout,Q.stderr);return Q}async function X9(Z){let X=Lf(Z),Q=await E0(["sh","-c",`command -v ${X}`],{timeoutMs:5000});if(Q.exitCode===0)return Q.stdout.trim()||null;return null}function Lf(Z){if(!/^[A-Za-z0-9._/-]+$/.test(Z))throw Error(`refused to shell-escape suspect token: ${Z}`);return Z}async function Af(Z,X="--version"){if(!await X9(Z))return null;let Y=await E0([Z,X],{timeoutMs:5000});if(Y.exitCode!==0)return null;return((Y.stdout||Y.stderr).split(/\r?\n/)[0]?.trim()??"")||null}var yO=16777216,Z$;var x9=p(()=>{Z$=class Z$ extends Error{message;exitCode;stdout;stderr;constructor(Z,X,Q,Y){super(Z);this.message=Z;this.exitCode=X;this.stdout=Q;this.stderr=Y;this.name="ShellError"}}});function o7(Z){return jf?"":Z}var jf,L0,k8,p0,ZV0,i0,H8,Q9,v;var S6=p(()=>{jf=(process.env.NO_COLOR??"").length>0;L0=o7("\x1B[0;31m"),k8=o7("\x1B[0;32m"),p0=o7("\x1B[1;33m"),ZV0=o7("\x1B[0;34m"),i0=o7("\x1B[0;36m"),H8=o7("\x1B[1m"),Q9=o7("\x1B[2m"),v=o7("\x1B[0m")});import{existsSync as xf}from"fs";async function E7(){if(k4!==void 0)return k4;let Z="/opt/homebrew/bin/python3.12";if(xf(Z))return k4=Z,Z;let X=await X9("python3.12");if(X)return k4=X,X;let Q=await X9("python3");return k4=Q,Q}async function Y7(Z,X={}){let Q=await E7();if(!Q)return{stdout:"",stderr:"python3 not found",exitCode:127};return E0([Q,"-c",Z],X)}var k4;var r7=p(()=>{x9()});var ZL={};l0(ZL,{runStatus:()=>Yh});import{existsSync as Y9,readFileSync as v3,readdirSync as iO,statSync as aO}from"fs";import{resolve as h8,basename as sf}from"path";import{homedir as nf}from"os";function sO(Z){let X=Math.trunc(Z);if(X>=1e6)return`${(Math.trunc(X/1e6*10)/10).toFixed(1)}M`;if(X>=1000)return`${(Math.trunc(X/1000*10)/10).toFixed(1)}K`;return String(X)}function nO(Z,X,Q){if(X===0)return null;let Y=Math.trunc(Z*100/X),J=Math.trunc(Z*NQ/X);if(J>NQ)J=NQ;let z=NQ-J,K=k8;if(Y>=80)K=L0;else if(Y>=50)K=p0;let $="=".repeat(Math.max(0,J))+" ".repeat(Math.max(0,z)),W=sO(Z),V=sO(X);return`  ${H8}${Q}${v} ${K}[${$}]${v} ${Y}% (${W} / ${V})`}async function rf(){if(await X9("jq"))return!0;return process.stdout.write(`${L0}Error: jq is required but not installed.${v}
+var h_=Object.create;var{getPrototypeOf:v_,defineProperty:rK,getOwnPropertyNames:g_}=Object;var m_=Object.prototype.hasOwnProperty;function u_(Z){return this[Z]}var p_,d_,c_=(Z,X,Q)=>{var Y=Z!=null&&typeof Z==="object";if(Y){var J=X?p_??=new WeakMap:d_??=new WeakMap,z=J.get(Z);if(z)return z}Q=Z!=null?h_(v_(Z)):{};let K=X||!Z||!Z.__esModule?rK(Q,"default",{value:Z,enumerable:!0}):Q;for(let $ of g_(Z))if(!m_.call(K,$))rK(K,$,{get:u_.bind(Z,$),enumerable:!0});if(Y)J.set(Z,K);return K};var qQ=(Z,X)=>()=>(X||Z((X={exports:{}}).exports,X),X.exports);var l_=(Z)=>Z;function i_(Z,X){this[Z]=l_.bind(null,X)}var l0=(Z,X)=>{for(var Q in X)rK(Z,Q,{get:X[Q],enumerable:!0,configurable:!0,set:i_.bind(X,Q)})};var p=(Z,X)=>()=>(Z&&(X=Z(Z=0)),X);var e0=import.meta.require;var kO={};l0(kO,{lokiDir:()=>j0,homeLokiDir:()=>P4,findRepoRootForVersion:()=>eK,REPO_ROOT:()=>r0});import{resolve as n7,dirname as tK}from"path";import{fileURLToPath as a_}from"url";import{existsSync as GQ}from"fs";import{homedir as s_}from"os";function n_(){let Z=RO;for(let X=0;X<6;X++){if(GQ(n7(Z,"VERSION"))&&GQ(n7(Z,"autonomy/run.sh")))return Z;let Q=tK(Z);if(Q===Z)break;Z=Q}return n7(RO,"..","..","..")}function eK(Z){let X=Z;for(let Q=0;Q<6;Q++){if(GQ(n7(X,"VERSION"))&&GQ(n7(X,"autonomy/run.sh")))return X;let Y=tK(X);if(Y===X)break;X=Y}return n7(Z,"..","..","..")}function j0(){return process.env.LOKI_DIR??n7(process.cwd(),".loki")}function P4(){return n7(s_(),".loki")}var RO,r0;var G8=p(()=>{RO=tK(a_(import.meta.url));r0=n_()});import{readFileSync as o_}from"fs";import{resolve as r_,dirname as t_}from"path";import{fileURLToPath as e_}from"url";function f3(){if(h5!==null)return h5;let Z="8.16.2";if(typeof Z==="string"&&Z.length>0)return h5=Z,h5;try{let X=t_(e_(import.meta.url)),Q=eK(X);h5=o_(r_(Q,"VERSION"),"utf-8").trim()}catch{h5="unknown"}return h5}var h5=null;var HQ=p(()=>{G8()});var bO={};l0(bO,{runOrThrow:()=>Of,run:()=>E0,readStreamCapped:()=>UQ,commandVersion:()=>Af,commandExists:()=>X9,ShellError:()=>Z$,MAX_STDOUT_BYTES:()=>yO});async function UQ(Z,X=yO){let Q=Z.getReader(),Y=new TextDecoder,J="",z=0;try{while(z<X){let{done:K,value:$}=await Q.read();if(K)break;if(!$)continue;if(z+=$.byteLength,z>X){let W=$.byteLength-(z-X);J+=Y.decode($.subarray(0,W),{stream:!0});break}J+=Y.decode($,{stream:!0})}J+=Y.decode()}finally{try{await Q.cancel()}catch{}Q.releaseLock()}return J}async function E0(Z,X={}){let Q=Bun.spawn({cmd:[...Z],stdout:"pipe",stderr:"pipe",env:X.env?{...process.env,...X.env}:process.env,cwd:X.cwd}),Y,J;if(X.timeoutMs&&X.timeoutMs>0)Y=setTimeout(()=>{try{Q.kill("SIGTERM")}catch{}J=setTimeout(()=>{try{Q.kill("SIGKILL")}catch{}},2000)},X.timeoutMs);try{let[z,K,$]=await Promise.all([UQ(Q.stdout),new Response(Q.stderr).text(),Q.exited]);return{stdout:z,stderr:K,exitCode:$}}finally{if(Y)clearTimeout(Y);if(J)clearTimeout(J)}}async function Of(Z,X={}){let Q=await E0(Z,X);if(Q.exitCode!==0)throw new Z$(`command failed (${Q.exitCode}): ${Z.join(" ")}`,Q.exitCode,Q.stdout,Q.stderr);return Q}async function X9(Z){let X=Lf(Z),Q=await E0(["sh","-c",`command -v ${X}`],{timeoutMs:5000});if(Q.exitCode===0)return Q.stdout.trim()||null;return null}function Lf(Z){if(!/^[A-Za-z0-9._/-]+$/.test(Z))throw Error(`refused to shell-escape suspect token: ${Z}`);return Z}async function Af(Z,X="--version"){if(!await X9(Z))return null;let Y=await E0([Z,X],{timeoutMs:5000});if(Y.exitCode!==0)return null;return((Y.stdout||Y.stderr).split(/\r?\n/)[0]?.trim()??"")||null}var yO=16777216,Z$;var x9=p(()=>{Z$=class Z$ extends Error{message;exitCode;stdout;stderr;constructor(Z,X,Q,Y){super(Z);this.message=Z;this.exitCode=X;this.stdout=Q;this.stderr=Y;this.name="ShellError"}}});function o7(Z){return jf?"":Z}var jf,L0,k8,p0,ZV0,i0,H8,Q9,v;var S6=p(()=>{jf=(process.env.NO_COLOR??"").length>0;L0=o7("\x1B[0;31m"),k8=o7("\x1B[0;32m"),p0=o7("\x1B[1;33m"),ZV0=o7("\x1B[0;34m"),i0=o7("\x1B[0;36m"),H8=o7("\x1B[1m"),Q9=o7("\x1B[2m"),v=o7("\x1B[0m")});import{existsSync as xf}from"fs";async function E7(){if(k4!==void 0)return k4;let Z="/opt/homebrew/bin/python3.12";if(xf(Z))return k4=Z,Z;let X=await X9("python3.12");if(X)return k4=X,X;let Q=await X9("python3");return k4=Q,Q}async function Y7(Z,X={}){let Q=await E7();if(!Q)return{stdout:"",stderr:"python3 not found",exitCode:127};return E0([Q,"-c",Z],X)}var k4;var r7=p(()=>{x9()});var ZL={};l0(ZL,{runStatus:()=>Yh});import{existsSync as Y9,readFileSync as v3,readdirSync as iO,statSync as aO}from"fs";import{resolve as h8,basename as sf}from"path";import{homedir as nf}from"os";function sO(Z){let X=Math.trunc(Z);if(X>=1e6)return`${(Math.trunc(X/1e6*10)/10).toFixed(1)}M`;if(X>=1000)return`${(Math.trunc(X/1000*10)/10).toFixed(1)}K`;return String(X)}function nO(Z,X,Q){if(X===0)return null;let Y=Math.trunc(Z*100/X),J=Math.trunc(Z*NQ/X);if(J>NQ)J=NQ;let z=NQ-J,K=k8;if(Y>=80)K=L0;else if(Y>=50)K=p0;let $="=".repeat(Math.max(0,J))+" ".repeat(Math.max(0,z)),W=sO(Z),V=sO(X);return`  ${H8}${Q}${v} ${K}[${$}]${v} ${Y}% (${W} / ${V})`}async function rf(){if(await X9("jq"))return!0;return process.stdout.write(`${L0}Error: jq is required but not installed.${v}
 `),process.stdout.write(`Install with:
 `),process.stdout.write(`  brew install jq    (macOS)
 `),process.stdout.write(`  apt install jq     (Debian/Ubuntu)
@@ -1222,4 +1222,4 @@ Set LOKI_LEGACY_BASH=1 to force the bash CLI for every command.
 `),2}case"start":{let{runStart:Y}=await Promise.resolve().then(() => (b_(),y_));return Y(Q)}default:return process.stderr.write(`Unknown command: ${X}
 `),process.stderr.write(__),2}}cO();process.on("SIGINT",()=>process.exit(130));process.on("SIGTERM",()=>process.exit(143));var fW0=await _W0(Bun.argv.slice(2));process.exit(fW0);
 
-//# debugId=DFDF2BB86BC44DA164756E2164756E21
+//# debugId=F9BF1A9706826A5864756E2164756E21

package/mcp/__init__.py

@@ -75,4 +75,4 @@ try:
 except ImportError:
     __all__ = ['mcp']
 
-__version__ = '8.16.0'
+__version__ = '8.16.2'

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "loki-mode",
   "mcpName": "io.github.asklokesh/loki-mode",
-  "version": "8.16.0",
+  "version": "8.16.2",
   "description": "Loki Mode by Autonomi. Autonomous spec-to-product system: takes a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief to a deployed app via the RARV-C closure loop with 8 quality gates. Provider-agnostic (Claude Code, OpenAI Codex, Cline, Aider).",
   "keywords": [
     "agent",

package/plugins/loki-mode/.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "loki-mode",
   "displayName": "Loki Mode",
-  "version": "8.16.0",
+  "version": "8.16.2",
   "description": "Autonomous spec-to-product build system with a built-in trust layer (RARV-C closure loop, 8 quality gates, completion council). Ships Loki's spec-hardening, drift-detection, and deterministic PR verification commands plus the Loki MCP server.",
   "author": {
     "name": "Autonomi",