codeer-cli 0.1.6__py3-none-any.whl → 0.1.7__py3-none-any.whl

codeer_cli/commands/eval_cmd.py

@@ -154,7 +154,9 @@ def register(subparsers):
     g.add_argument("--latest", action="store_true",
                    help="Auto-select the newest AgentHistory (default)")
     p.add_argument("--cases", default=None, help="Comma-separated case UUIDs (default: all)")
-    p.add_argument("--evaluators", required=True, help="Comma-separated evaluator UUIDs")
+    g = p.add_mutually_exclusive_group()
+    g.add_argument("--evaluator", default=None, help="Evaluator UUID; common path for running many cases with one tester")
+    g.add_argument("--evaluators", default=None, help="Comma-separated evaluator UUIDs")
     p.add_argument("--poll-timeout", type=int, default=POLL_TIMEOUT)
     p.add_argument("--full", action="store_true",
                    help="Use longer previews in stdout. Raw outputs/tool calls still require --out.")
@@ -195,10 +197,12 @@ def register(subparsers):
     p.set_defaults(func=run_cases_apply)
 
     # codeer eval rubrics
-    p = sub.add_parser("rubrics", help="Read per-(case, evaluator) rubrics")
+    p = sub.add_parser("rubrics", help="Read assigned per-(case, evaluator) rubrics")
     p.add_argument("--agent", required=True)
     p.add_argument("--evaluators", default=None, help="Comma-separated evaluator UUIDs")
     p.add_argument("--cases", default=None, help="Comma-separated case UUIDs")
+    p.add_argument("--all-pairs", action="store_true",
+                   help="With omitted --evaluators, scan every workspace evaluator instead of assigned pairs only.")
     p.add_argument("--full", action="store_true",
                    help="Print complete rubric text. Default prints matrix summaries/previews.")
     p.add_argument("--out", default=None,
@@ -599,6 +603,56 @@ def run_evaluator_update(args, client) -> int:
 # eval run
 # ---------------------------------------------------------------------------
 
+def _assigned_evaluators_by_case(info_rows: list[dict]) -> dict[str, dict[str, dict]]:
+    out: dict[str, dict[str, dict]] = {}
+    for row in info_rows:
+        case_id = row.get("case_id")
+        if not case_id:
+            continue
+        out[str(case_id)] = {
+            str(info.get("evaluator_id")): info
+            for info in (row.get("evaluators") or [])
+            if info.get("evaluator_id")
+        }
+    return out
+
+
+def _planned_eval_pairs(
+    *,
+    case_ids: list[str],
+    assigned_by_case: dict[str, dict[str, dict]],
+    requested_evaluator_ids: list[str] | None,
+) -> tuple[list[dict[str, str]], list[dict[str, str]]]:
+    pairs: list[dict[str, str]] = []
+    skipped: list[dict[str, str]] = []
+
+    if requested_evaluator_ids:
+        for case_id in case_ids:
+            assigned = assigned_by_case.get(case_id, {})
+            for evaluator_id in requested_evaluator_ids:
+                if evaluator_id in assigned:
+                    pairs.append({"case_id": case_id, "evaluator_id": evaluator_id})
+                else:
+                    skipped.append({
+                        "case_id": case_id,
+                        "evaluator_id": evaluator_id,
+                        "reason": "not_assigned",
+                    })
+        return pairs, skipped
+
+    for case_id in case_ids:
+        for evaluator_id in assigned_by_case.get(case_id, {}):
+            pairs.append({"case_id": case_id, "evaluator_id": evaluator_id})
+    return pairs, skipped
+
+
+def _group_case_ids_by_evaluator(pairs: list[dict[str, str]]) -> dict[str, list[str]]:
+    grouped: dict[str, list[str]] = defaultdict(list)
+    for pair in pairs:
+        grouped[pair["evaluator_id"]].append(pair["case_id"])
+    return dict(grouped)
+
+
 def run_run(args, client) -> int:
     workspace_id, _ = client.resolve_scope()
     if args.latest or not args.history:
@@ -625,41 +679,76 @@ def run_run(args, client) -> int:
         log("error: no cases to run")
         return 2
 
-    evaluator_ids = _ids(args.evaluators) or []
-    if not evaluator_ids:
-        log("error: --evaluators is required")
+    evaluator_ids = [args.evaluator] if args.evaluator else (_ids(args.evaluators) or [])
+    requested_evaluator_ids = evaluator_ids or None
+
+    assignment_rows = eval_mod.get_case_evaluator_infos(client, case_ids=case_ids)
+    assigned_by_case = _assigned_evaluators_by_case(assignment_rows)
+    pairs, skipped_unassigned = _planned_eval_pairs(
+        case_ids=case_ids,
+        assigned_by_case=assigned_by_case,
+        requested_evaluator_ids=requested_evaluator_ids,
+    )
+    if not pairs:
+        if skipped_unassigned:
+            log("error: none of the requested case/evaluator pairs are assigned")
+        else:
+            log("error: no assigned case/evaluator pairs to run")
+        print_json({
+            "agent_id": args.agent,
+            "history_id": args.history,
+            "requested_case_count": len(case_ids),
+            "requested_evaluator_count": len(evaluator_ids),
+            "triggered_pair_count": 0,
+            "skipped_unassigned": skipped_unassigned,
+        })
         return 2
+
+    evaluator_ids = _dedupe_preserve_order([pair["evaluator_id"] for pair in pairs])
     evaluators = [eval_mod.get_evaluator(client, eid) for eid in evaluator_ids]
 
     case_label_by_id = {c["id"]: truncate(c.get("input") or "", 60) for c in case_objs}
     evaluator_name_by_id = {e["id"]: e.get("name", e["id"]) for e in evaluators}
 
-    log(f"triggering: {len(case_ids)} cases x {len(evaluator_ids)} evaluators on history {args.history}")
-    eval_mod.trigger(client, case_ids=case_ids, evaluator_ids=evaluator_ids,
-                     agent_history_id=args.history)
+    if skipped_unassigned:
+        log(f"skipping {len(skipped_unassigned)} unassigned requested pairs")
+    log(f"triggering: {len(pairs)} assigned case/evaluator pairs on history {args.history}")
+    trigger_response = eval_mod.trigger_pairs(
+        client,
+        case_evaluator_pairs=pairs,
+        agent_history_id=args.history,
+    )
 
     deadline = time.time() + args.poll_timeout
     results_by_eval: dict[str, list[dict]] = {}
+    case_ids_by_evaluator = _group_case_ids_by_evaluator(pairs)
+    target_pair_keys = {(pair["case_id"], pair["evaluator_id"]) for pair in pairs}
     while time.time() < deadline:
         results_by_eval = {}
-        done = 0
-        total = len(case_ids) * len(evaluator_ids)
-        for ev_id in evaluator_ids:
+        done_pairs: set[tuple[str, str]] = set()
+        total = len(pairs)
+        for ev_id, ev_case_ids in case_ids_by_evaluator.items():
             rows = eval_mod.get_results(
-                client, case_ids=case_ids, evaluator_id=ev_id,
+                client, case_ids=ev_case_ids, evaluator_id=ev_id,
                 agent_history_id=args.history, workspace_id=workspace_id,
                 include_output=True, include_reasoning_steps=True,
             )
             results_by_eval[ev_id] = rows
-            done += sum(1 for r in rows if r.get("score") is not None)
-        log(f"  progress: {done}/{total}")
-        if done >= total:
+            for row in rows:
+                key = (row.get("case_id") or row.get("evaluation_case_id"), ev_id)
+                if key in target_pair_keys and row.get("score") is not None:
+                    done_pairs.add(key)
+        log(f"  progress: {len(done_pairs)}/{total}")
+        if len(done_pairs) >= total:
             break
         time.sleep(POLL_INTERVAL)
 
     flat: list[dict] = []
     for ev_id, rows in results_by_eval.items():
         for r in rows:
+            row_case_id = r.get("case_id") or r.get("evaluation_case_id")
+            if (row_case_id, ev_id) not in target_pair_keys:
+                continue
             result_summary = parse_eval_result(r)
             tool_calls = parse_eval_tool_calls(r)
             total_tool_duration_ms = sum(
@@ -684,7 +773,15 @@ def run_run(args, client) -> int:
                 "raw_result": r,
             })
 
-    all_perfect = all((r.get("score") or 0.0) >= 1.0 for r in flat) if flat else False
+    scored_pair_keys = {
+        (r.get("case_id"), r.get("evaluator_id"))
+        for r in flat
+        if r.get("score") is not None
+    }
+    all_perfect = (
+        len(scored_pair_keys) == len(target_pair_keys)
+        and all((r.get("score") or 0.0) >= 1.0 for r in flat)
+    )
     log("\n" + "=" * 80)
     log(f"RESULTS  agent={args.agent}  history={args.history}")
     log("=" * 80)
@@ -726,15 +823,25 @@ def run_run(args, client) -> int:
     out = {
         "agent_id": args.agent,
         "history_id": args.history,
+        "requested_case_count": len(case_ids),
+        "requested_evaluator_count": len(requested_evaluator_ids or evaluator_ids),
+        "triggered_pair_count": len(pairs),
+        "scored_pair_count": len(scored_pair_keys),
+        "skipped_unassigned_count": len(skipped_unassigned),
         "all_perfect": all_perfect,
         "result_count": len(result_summaries),
         "non_perfect_count": len(non_perfect),
         "wrote_full_detail": bool(args.out),
+        "trigger_response": trigger_response,
+        "skipped_unassigned": skipped_unassigned,
         "results": result_summaries,
     }
     full_out = {
         "agent_id": args.agent,
         "history_id": args.history,
+        "triggered_pairs": pairs,
+        "trigger_response": trigger_response,
+        "skipped_unassigned": skipped_unassigned,
         "all_perfect": all_perfect,
         "results": flat,
     }
@@ -1359,18 +1466,29 @@ def run_rubrics(args, client) -> int:
         log("error: no cases for this agent")
         return 2
 
+    assignment_rows = eval_mod.get_case_evaluator_infos(client, case_ids=case_ids)
+    assigned_by_case = _assigned_evaluators_by_case(assignment_rows)
+
     if args.evaluators:
         evaluator_ids = _ids(args.evaluators) or []
         evaluators = [eval_mod.get_evaluator(client, eid) for eid in evaluator_ids]
-    else:
+    elif args.all_pairs:
         evaluators = eval_mod.list_evaluators(client, workspace_id)
         evaluator_ids = [e["id"] for e in evaluators]
+    else:
+        evaluator_ids = _dedupe_preserve_order([
+            evaluator_id
+            for case_id in case_ids
+            for evaluator_id in assigned_by_case.get(case_id, {})
+        ])
+        evaluators = [eval_mod.get_evaluator(client, eid) for eid in evaluator_ids]
     evaluator_name = {e["id"]: e.get("name", e["id"]) for e in evaluators}
     if not evaluator_ids:
-        log("error: no evaluators in workspace")
+        log("error: no assigned evaluators for these cases")
         return 2
 
-    log(f"reading {len(case_ids)} cases x {len(evaluator_ids)} evaluators...")
+    mode = "all requested pairs" if args.evaluators or args.all_pairs else "assigned pairs"
+    log(f"reading {mode}: {len(case_ids)} cases, {len(evaluator_ids)} evaluators...")
 
     rubrics = eval_mod.get_case_rubrics(
         client, agent_id=args.agent, workspace_id=workspace_id,
@@ -1383,8 +1501,14 @@ def run_rubrics(args, client) -> int:
             log(f"CASE {cid}")
             log(f"  input: {truncate(case_input.get(cid, ''), 120)}")
             for ev_id in evaluator_ids:
+                is_assigned = ev_id in assigned_by_case.get(cid, {})
+                if not is_assigned and not (args.evaluators or args.all_pairs):
+                    continue
                 ev_name = evaluator_name.get(ev_id, ev_id)
                 rubric_text = (rubrics.get(cid) or {}).get(ev_id, "")
+                if not is_assigned:
+                    log(f"  [{ev_name}] (not assigned)")
+                    continue
                 if not rubric_text:
                     log(f"  [{ev_name}] (rubric not set)")
                 else:
@@ -1396,9 +1520,13 @@ def run_rubrics(args, client) -> int:
     for cid in case_ids:
         rubrics_summary = {}
         for ev_id in evaluator_ids:
+            is_assigned = ev_id in assigned_by_case.get(cid, {})
+            if not is_assigned and not (args.evaluators or args.all_pairs):
+                continue
             rubric_text = (rubrics.get(cid) or {}).get(ev_id, "")
             rubrics_summary[ev_id] = {
                 "evaluator_name": evaluator_name.get(ev_id, ev_id),
+                "is_assigned": is_assigned,
                 "is_set": bool(rubric_text),
                 "chars": len(rubric_text),
                 "preview": truncate(rubric_text, 240),
@@ -1412,6 +1540,7 @@ def run_rubrics(args, client) -> int:
     out = {
         "agent_id": args.agent,
         "workspace_id": workspace_id,
+        "mode": mode,
         "evaluators": [{"id": e["id"], "name": e.get("name")} for e in evaluators],
         "cases": [
             {
@@ -1420,7 +1549,9 @@ def run_rubrics(args, client) -> int:
                 "rubrics_by_evaluator": {
                     ev_id: (rubrics.get(cid) or {}).get(ev_id)
                     for ev_id in evaluator_ids
+                    if ev_id in assigned_by_case.get(cid, {}) or args.evaluators or args.all_pairs
                 },
+                "assigned_evaluator_ids": list(assigned_by_case.get(cid, {})),
             }
             for cid in case_ids
         ],
@@ -1432,6 +1563,7 @@ def run_rubrics(args, client) -> int:
         print_json({
             "agent_id": args.agent,
             "workspace_id": workspace_id,
+            "mode": mode,
             "evaluator_count": len(evaluators),
             "case_count": len(case_ids),
             "wrote_full_detail": bool(args.out),

codeer_cli/eval_.py

@@ -23,6 +23,7 @@ def create_case(
     rubric: Optional[str] = None,
     attachment_ids: Optional[List[str]] = None,
     label_ids: Optional[List[str]] = None,
+    evaluators: Optional[List[dict[str, Any]]] = None,
     meta: Optional[dict] = None,
     note: Optional[str] = None,
 ) -> dict:
@@ -44,6 +45,8 @@ def create_case(
         body["attachment_ids"] = attachment_ids
     if label_ids is not None:
         body["label_ids"] = label_ids
+    if evaluators is not None:
+        body["evaluators"] = evaluators
     if meta:
         body["meta"] = meta
     if note is not None:
@@ -93,6 +96,31 @@ def delete_case(client: CodeerClient, case_id: str) -> dict:
     return client.delete(f"/external/eval/cases/{case_id}")
 
 
+# --- case/evaluator assignments ------------------------------------------
+
+def get_case_evaluator_infos(client: CodeerClient, *, case_ids: List[str]) -> list[dict]:
+    """Read assigned evaluator metadata for each case.
+
+    Returns rows shaped like ``{"case_id": str, "evaluators": [...]}``, where
+    each evaluator entry is the assigned ``{"evaluator_id", "rubric"}`` pair.
+    """
+    return client.post("/eval/case-evaluator-infos:batch", json={"case_ids": case_ids})
+
+
+def replace_case_evaluator_infos(
+    client: CodeerClient,
+    *,
+    case_id: str,
+    evaluators: list[dict[str, Any]],
+) -> dict:
+    """Replace a case's assigned evaluators.
+
+    This is intentionally separate from rubric upsert: replacing removes
+    evaluator assignments that are not included in ``evaluators``.
+    """
+    return client.put(f"/eval/cases/{case_id}/case-evaluator-infos", json={"evaluators": evaluators})
+
+
 # --- case labels -----------------------------------------------------------
 
 def list_case_labels(client: CodeerClient, *, workspace_id: str) -> list[dict]:
@@ -202,6 +230,22 @@ def trigger(
     return client.post("/external/eval/runs", json=body)
 
 
+def trigger_pairs(
+    client: CodeerClient,
+    *,
+    case_evaluator_pairs: list[dict[str, str]],
+    agent_history_id: str,
+) -> dict:
+    """Kick off evaluation for explicit assigned case/evaluator pairs."""
+    return client.post(
+        "/eval/trigger",
+        json={
+            "case_evaluator_pairs": case_evaluator_pairs,
+            "agent_history_id": agent_history_id,
+        },
+    )
+
+
 def stop(client: CodeerClient, *, case_id: str, evaluator_id: str) -> Any:
     return client.post("/external/eval/runs:stop", json={"case_id": case_id, "evaluator_id": evaluator_id})
 
@@ -451,9 +495,9 @@ def create_case_with_rubrics(
     is filled in for every evaluator it will be judged by.
 
     ``rubrics_by_evaluator`` maps ``evaluator_id → rubric_text``. Each entry
-    becomes a ``POST /eval/rubric`` call after the case is created. Use
-    different rubric wording per evaluator when the evaluators judge different
-    aspects (e.g. Style/Tone vs Content Compliance).
+    becomes a case/evaluator assignment on create. Use different rubric wording
+    per evaluator when the evaluators judge different aspects (e.g. Style/Tone
+    vs Content Compliance).
     """
     case = create_case(
         client,
@@ -462,12 +506,11 @@ def create_case_with_rubrics(
         expected_output=expected_output,
         attachment_ids=attachment_ids,
         label_ids=label_ids,
+        evaluators=[
+            {"evaluator_id": ev_id, "rubric": rubric}
+            for ev_id, rubric in rubrics_by_evaluator.items()
+        ],
         meta=meta,
         note=note,
     )
-    set_rubric_bulk(
-        client,
-        evaluation_case_id=case["id"],
-        rubrics_by_evaluator=rubrics_by_evaluator,
-    )
     return case

{codeer_cli-0.1.6.dist-info → codeer_cli-0.1.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codeer-cli
-Version: 0.1.6
+Version: 0.1.7
 Summary: Command line tools for managing Codeer agents over the Codeer API.
 Project-URL: Homepage, https://www.codeer.ai
 Author: Codeer.AI
@@ -143,7 +143,7 @@ Use this pattern during agent lifecycle work:
 ```bash
 codeer agent list
 codeer history list --agent <agent-id> --limit 50
-codeer eval run --agent <agent-id> --evaluators <evaluator-id> --out .codeer/eval_run.json
+codeer eval run --agent <agent-id> --cases <case-ids> --evaluator <evaluator-id> --out .codeer/eval_run.json
 ```
 
 Flags:

{codeer_cli-0.1.6.dist-info → codeer_cli-0.1.7.dist-info}/RECORD

@@ -5,7 +5,7 @@ codeer_cli/chats.py,sha256=YVrZJhoa-d67o6tzX6riGXsbA-ehyhOxrZ8zRCcJNro,2675
 codeer_cli/cli.py,sha256=g-WR2D5MkaUdc13ZrpRCavXD1940CHE9eBELC034tic,4443
 codeer_cli/client.py,sha256=LpHVqf1IYNg1wFfIHnO9q4xg2h3IiGOitzCnvwB-Bcw,9809
 codeer_cli/constants.py,sha256=D1pV3wCoqYybrKGKeoupYjjFWLfaFviKp1yL7oh6Qso,2323
-codeer_cli/eval_.py,sha256=z9RXFiYXOEHPKIh31nbooNe_WmlJ-L63GWBDw3CJhmM,15614
+codeer_cli/eval_.py,sha256=XwmPxNOtxSyZq2EOae9FZe5NFp0YyVbIswTn22S8noc,17050
 codeer_cli/histories.py,sha256=tk28git_peX4x703CIDU8u72JtlGaytyrtlHfxlK-7A,5979
 codeer_cli/kb.py,sha256=Ad4h65NByq5Rq5BTeMghLTKlWRhmOC2jxL0BaTGX3EM,10631
 codeer_cli/parse.py,sha256=qrjZn0MUTjGfucp4cwxy8Pt7WS-0x15kK5F7kWTY8Ps,21818
@@ -13,11 +13,11 @@ codeer_cli/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 codeer_cli/commands/_util.py,sha256=VOB_HMWYzHFNY1ElLOED1HB6fpFpsniqH6Yx3VUlMrY,1644
 codeer_cli/commands/agent.py,sha256=amvfVVrbPOkbYKCGvA6EJB30C-aY6WSdfR7u7FklXbs,14793
 codeer_cli/commands/check.py,sha256=lTxolx1mIJ8jldPhJ5FXqie9nbCLVOO-sDPOHTSy1-w,3817
-codeer_cli/commands/eval_cmd.py,sha256=3Fi_dwpoJ2hceitACunPtR2kVZ84WT2r_CyL-MaJaMw,62902
+codeer_cli/commands/eval_cmd.py,sha256=fQu8ZRzGO7GWL_Og9NeZ0xYwHoN_iocmCnWw-kPNRkc,68599
 codeer_cli/commands/history.py,sha256=Jv7t0GhSZcbZ8OuIXZT34CixXt7ECEVP3nZ-WW_Ya9E,12026
 codeer_cli/commands/kb.py,sha256=kVEinBVM6NN8_0djOqIQErh46dLmArwFngXMNzvGeAI,28345
 codeer_cli/commands/profile.py,sha256=IdlXC_6cqobsfN3JRrAnt-1OgBUsIFneS9QtR4Un6Kc,6521
-codeer_cli-0.1.6.dist-info/METADATA,sha256=HDNq9yUPii8TA-KRxu3Mh0sScklObu3pl9OvUthgsdg,5981
-codeer_cli-0.1.6.dist-info/WHEEL,sha256=lCkmxWfQsSc9CfIClYeavTdQeEX2toPqufh9gI35EQA,87
-codeer_cli-0.1.6.dist-info/entry_points.txt,sha256=-nXIrlm5SR5r7gg3y8AS0tN66MwmvNHsrlwLNQNGD50,47
-codeer_cli-0.1.6.dist-info/RECORD,,
+codeer_cli-0.1.7.dist-info/METADATA,sha256=z8yvV20PQ1ysK27LpsMuurXdAPWJ4Kz-o9-LuxrHczg,5999
+codeer_cli-0.1.7.dist-info/WHEEL,sha256=lCkmxWfQsSc9CfIClYeavTdQeEX2toPqufh9gI35EQA,87
+codeer_cli-0.1.7.dist-info/entry_points.txt,sha256=-nXIrlm5SR5r7gg3y8AS0tN66MwmvNHsrlwLNQNGD50,47
+codeer_cli-0.1.7.dist-info/RECORD,,