@lythos/skill-arena 0.14.5 → 0.15.0

package/README.md

@@ -16,24 +16,31 @@
 ```bash
 bun add -d @lythos/skill-arena
 # or use directly
-bunx @lythos/skill-arena@0.14.5 <command>
+bunx @lythos/skill-arena@0.15.0 <command>
 ```
 
 ## Quick Start
 
 ```bash
 # single — test one deck (most common)
-bunx @lythos/skill-arena@latest single \
+bunx @lythos/skill-arena@0.15.0 single \
   --deck ./examples/decks/scout.toml \
   --brief "Generate auth flow diagram" \
   --out ./output
 
+# single with explicit player
+bunx @lythos/skill-arena@0.15.0 single \
+  --deck ./examples/decks/scout.toml \
+  --brief "Generate auth flow diagram" \
+  --player kimi \
+  --out ./output
+
 # cross-deck vs — compare two decks (agent-orchestrated)
 # Create arena.toml declaring sides with different decks, then:
-bunx @lythos/skill-arena@latest vs --config ./arena.toml
+bunx @lythos/skill-arena@0.15.0 vs --config ./arena.toml
 
 # cross-player vs — compare kimi vs codex (CLI only)
-bunx @lythos/skill-arena@latest vs --config ./arena.toml --player kimi
+bunx @lythos/skill-arena@0.15.0 vs --config ./arena.toml --player kimi
 ```
 
 **What happens**: Agent creates isolated `/tmp` workdir per side, `deck link` skills, spawns parallel subagents, collects artifacts, judge scores outputs. Parent deck restored after.
@@ -43,42 +50,34 @@ bunx @lythos/skill-arena@latest vs --config ./arena.toml --player kimi
 ### `single` — one deck, one task
 
 ```bash
-bunx @lythos/skill-arena@latest single \
+bunx @lythos/skill-arena@0.15.0 single \
   --deck ./deck.toml \
   --brief "Produce a .docx report with radar chart" \
   --timeout 600000 \
   --out ./output
-```
 
-### `vs` — multi-deck comparison
-
-```bash
-bunx @lythos/skill-arena@latest vs --config ./arena.toml
-bunx @lythos/skill-arena@latest vs --config ./arena.toml --dry-run
+# with explicit player
+bunx @lythos/skill-arena@0.15.0 single \
+  --deck ./deck.toml \
+  --brief "Produce a .docx report with radar chart" \
+  --player kimi \
+  --out ./output
 ```
 
-### `scaffold` — legacy directory setup
+### `vs` — multi-deck comparison
 
 ```bash
-bunx @lythos/skill-arena@latest scaffold \
-  --task "Generate auth flow diagram" \
-  --decks "./decks/minimal.toml,./decks/rich.toml"
+bunx @lythos/skill-arena@0.15.0 vs --config ./arena.toml
+bunx @lythos/skill-arena@0.15.0 vs --config ./arena.toml --dry-run
 ```
 
 ### `prepare-workdir` — isolate + link skills (agent-orchestrated)
 
 ```bash
-bunx @lythos/skill-arena@latest prepare-workdir \
+bunx @lythos/skill-arena@0.15.0 prepare-workdir \
   --deck ./skill-deck.toml \
   --out /tmp/arena-side-a \
   --brief "task description"
-
-# Plan-first: review before executing
-bunx @lythos/skill-arena@latest prepare-workdir \
-  --deck ./skill-deck.toml \
-  --out /tmp/arena-side-a \
-  --brief "task" \
-  --dry-run
 ```
 
 Creates `/tmp`-isolated workdir with deck copied, AGENTS.md written, and `deck link` run. `--dry-run` prints the plan (skills, workdir path, link needed) without creating anything.
@@ -86,25 +85,18 @@ Creates `/tmp`-isolated workdir with deck copied, AGENTS.md written, and `deck l
 ### `archive` — collect agent outputs (agent-orchestrated)
 
 ```bash
-bunx @lythos/skill-arena@latest archive \
+bunx @lythos/skill-arena@0.15.0 archive \
   --from /tmp/arena-side-a \
   --to ./playground/output \
   --sides side-a
-
-# Plan-first: review what would be copied
-bunx @lythos/skill-arena@latest archive \
-  --from /tmp/arena-side-a \
-  --to ./playground/output \
-  --sides side-a \
-  --dry-run
 ```
 
 Copies agent artifacts from workdir(s) to output, skipping internal files (`.claude`, `skill-deck.toml`, `skill-deck.lock`, `AGENTS.md`). Single-side archives fall back to workdir root when the named side subdirectory doesn't exist. `--dry-run` shows the per-side plan before copying.
 
-### `viz` — render results
+### `viz` — render results (WIP — HTML report generation pending)
 
 ```bash
-bunx @lythos/skill-arena@latest viz runs/arena-<id>/
+bunx @lythos/skill-arena@0.15.0 viz runs/arena-<id>/
 ```
 
 ## Parameters
@@ -113,7 +105,7 @@ bunx @lythos/skill-arena@latest viz runs/arena-<id>/
 |------|---------|-------------|
 | `--brief "<text>"` | single | Inline task brief |
 | `--deck <path\|url>` | single | Deck file (URL auto-fetched) |
-| `--player <name>` | single, vs | Only for cross-player: kimi\|codex\|deepseek\|claude |
+| `--player <name>` | single, vs | Agent player: kimi\|codex\|deepseek\|claude |
 | `--timeout <ms>` | single | Subagent timeout (300000–600000 for complex tasks) |
 | `--from <dir>` | archive | Source workdir |
 | `--to <dir>` | archive | Output directory |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lythos/skill-arena",
-  "version": "0.14.5",
+  "version": "0.15.0",
   "description": "Skill Arena — benchmark skill effectiveness with controlled-variable comparison",
   "keywords": [
     "ai-agent",
@@ -42,15 +42,15 @@
     "bun": ">=1.0.0"
   },
   "dependencies": {
-    "@lythos/cold-pool": "^0.14.5",
-    "@lythos/infra": "^0.14.5",
-    "@lythos/test-utils": "^0.14.5",
+    "@lythos/cold-pool": "^0.15.0",
+    "@lythos/infra": "^0.15.0",
+    "@lythos/test-utils": "^0.15.0",
     "zod": "^3.24.0",
     "zod-to-json-schema": "^3.25.2"
   },
   "optionalDependencies": {
-    "@lythos/agent-adapter-claude-sdk": "^0.14.5",
-    "@lythos/agent-adapter-deepseek-serve": "^0.14.5",
-    "@lythos/agent-adapter-codex": "^0.14.5"
+    "@lythos/agent-adapter-claude-sdk": "^0.15.0",
+    "@lythos/agent-adapter-deepseek-serve": "^0.15.0",
+    "@lythos/agent-adapter-codex": "^0.15.0"
   }
 }

package/src/cli.ts

@@ -232,7 +232,7 @@ async function singleRun(args: string[]) {
     if (!res?.ok) {
       const errorDetail = res ? `HTTP ${res.status}` : 'unreachable'
       console.error(`❌ Cannot reach ${url} (${errorDetail})`)
-      if (allFailed) console.error('   Set LYTHOSKILL_GH_MIRROR to use a custom mirror.')
+      if (allFailed) console.error('   Set LYTHOS_GH_MIRROR to use a custom mirror.')
       console.error('   Or download manually and reference the local file.')
       process.exit(1)
     }