harness-evolver 1.8.0 → 1.9.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "harness-evolver",
-  "version": "1.8.0",
+  "version": "1.9.0",
   "description": "Meta-Harness-style autonomous harness optimization for Claude Code",
   "author": "Raphael Valdetaro",
   "license": "MIT",

package/skills/evolve/SKILL.md

@@ -36,15 +36,34 @@ python3 -c "import json; s=json.load(open('.harness-evolver/summary.json')); pri
 
 ### 1.5. Gather LangSmith Traces (MANDATORY after every evaluation)
 
-**Run these commands unconditionally after EVERY evaluation** (including baseline). If langsmith-cli is not installed or there are no runs, the commands fail silently — that's fine. But you MUST attempt them.
+**Run these commands unconditionally after EVERY evaluation** (including baseline). Do NOT guess project names — discover them.
+
+**Step 1: Find the actual LangSmith project name**
 
 ```bash
-langsmith-cli --json runs list --project harness-evolver-{last_evaluated_version} --failed --fields id,name,error,inputs --limit 10 > .harness-evolver/langsmith_diagnosis.json 2>/dev/null || echo "[]" > .harness-evolver/langsmith_diagnosis.json
+langsmith-cli --json projects list --name-pattern "harness-evolver*" --limit 10 2>/dev/null
+```
 
-langsmith-cli --json runs stats --project harness-evolver-{last_evaluated_version} > .harness-evolver/langsmith_stats.json 2>/dev/null || echo "{}" > .harness-evolver/langsmith_stats.json
+This returns all projects matching the prefix. Pick the most recently updated one, or the one matching the current version. Save the project name:
+
+```bash
+LS_PROJECT=$(langsmith-cli --json projects list --name-pattern "harness-evolver*" --limit 1 2>/dev/null | python3 -c "import sys,json; data=json.load(sys.stdin); print(data[0]['name'] if data else '')" 2>/dev/null || echo "")
 ```
 
-For the first iteration, use `baseline` as the version. For subsequent iterations, use the latest evaluated version.
+If `LS_PROJECT` is empty, langsmith-cli is not available or no projects exist — skip to step 2.
+
+**Step 2: Gather traces from the discovered project**
+
+```bash
+if [ -n "$LS_PROJECT" ]; then
+  langsmith-cli --json runs list --project "$LS_PROJECT" --failed --fields id,name,error,inputs --limit 10 > .harness-evolver/langsmith_diagnosis.json 2>/dev/null || echo "[]" > .harness-evolver/langsmith_diagnosis.json
+  langsmith-cli --json runs stats --project "$LS_PROJECT" > .harness-evolver/langsmith_stats.json 2>/dev/null || echo "{}" > .harness-evolver/langsmith_stats.json
+  echo "$LS_PROJECT" > .harness-evolver/langsmith_project.txt
+else
+  echo "[]" > .harness-evolver/langsmith_diagnosis.json
+  echo "{}" > .harness-evolver/langsmith_stats.json
+fi
+```
 
 These files are included in the proposer's `<files_to_read>` so it has real trace data for diagnosis.
 

package/tools/evaluate.py

@@ -118,12 +118,17 @@ def cmd_run(args):
             api_key = os.environ.get(ls.get("api_key_env", "LANGSMITH_API_KEY"), "")
             if api_key:
                 version = os.path.basename(os.path.dirname(traces_dir))
+                ls_project = f"{ls.get('project_prefix', 'harness-evolver')}-{version}"
                 langsmith_env = {
                     **os.environ,
                     "LANGCHAIN_TRACING_V2": "true",
                     "LANGCHAIN_API_KEY": api_key,
-                    "LANGCHAIN_PROJECT": f"{ls.get('project_prefix', 'harness-evolver')}-{version}",
+                    "LANGCHAIN_PROJECT": ls_project,
                 }
+                # Write the project name so the evolve skill knows where to find traces
+                ls_project_file = os.path.join(os.path.dirname(os.path.dirname(traces_dir)), "langsmith_project.txt")
+                with open(ls_project_file, "w") as f:
+                    f.write(ls_project)
 
     for task_file in task_files:
         task_path = os.path.join(tasks_dir, task_file)