agentbyte 0.45.0__tar.gz → 0.46.0__tar.gz

{agentbyte-0.45.0 → agentbyte-0.46.0}/CHANGELOG.md

@@ -6,6 +6,19 @@ The format follows Keep a Changelog principles and semantic versioning.
 
 ## [Unreleased]
 
+## [0.46.0] - 2026-10-05
+
+### Added
+
+- Evaluation UI: read-only optimization pages (spec 0068 phase 3). The Evaluations home page lists
+  stored optimization runs (suite, optimizer, seed → best, cost); `#/evals/optimizations/<id>`
+  renders the report — proposed changes as seed/best text, per-task outcomes, remaining failures
+  with the judge's reasoning, reflector diagnoses and edits, candidates, cost — with Copy markdown
+  and Download report.md.
+- `GET /api/eval/optimizations?suite=` and `GET /api/eval/optimizations/{id}` (`{run, report,
+  markdown}`). They read the history store directly, so runs recorded for suites outside the
+  server's catalog (e.g. notebook suites) are shown.
+
 ## [0.45.0] - 2026-10-05
 
 ### Added

{agentbyte-0.45.0 → agentbyte-0.46.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: agentbyte
-Version: 0.45.0
+Version: 0.46.0
 Summary: A toolkit for designing multiagent systems
 Author-email: MrDataPsycho <mr.data.psycho@gmail.com>
 License-Expression: LicenseRef-Proprietary
@@ -77,7 +77,7 @@ Description-Content-Type: text/markdown
 
 Agentbyte is an observability-first agentic AI framework for building and studying multiagent systems with a learning-first, implementation-oriented workflow.
 
-Current release: **0.45.0**
+Current release: **0.46.0**
 
 ## Building an Agent
 

{agentbyte-0.45.0 → agentbyte-0.46.0}/README.md

@@ -2,7 +2,7 @@
 
 Agentbyte is an observability-first agentic AI framework for building and studying multiagent systems with a learning-first, implementation-oriented workflow.
 
-Current release: **0.45.0**
+Current release: **0.46.0**
 
 ## Building an Agent
 

agentbyte-0.46.0/src/agentbyte/__about__.py

@@ -0,0 +1,2 @@
+__version__ = "0.46.0"
+VERSION = __version__

{agentbyte-0.45.0 → agentbyte-0.46.0}/src/agentbyte/webui/eval_routes.py

@@ -188,6 +188,30 @@ def register_eval_routes(
 
         return EventSourceResponse(stream())
 
+    # Optimization runs (spec 0068 phase 3): read-only, straight from the history store, so a
+    # run is listed even when its suite is not in this server's catalog (e.g. defined in a
+    # notebook). Launching an optimization stays in code.
+
+    @app.get("/api/eval/optimizations")
+    async def list_optimization_runs(suite: str | None = None, limit: int = 50, offset: int = 0) -> Any:
+        store = manager().coordinator.store
+        records = await store.list_optimizations(
+            suite=suite, limit=max(1, min(limit, 200)), offset=max(0, offset)
+        )
+        return [record.model_dump(mode="json", exclude={"trace"}) for record in records]
+
+    @app.get("/api/eval/optimizations/{optimization_id}")
+    async def get_optimization_run(optimization_id: str) -> Any:
+        record = await manager().coordinator.store.get_optimization(optimization_id)
+        if record is None:
+            raise HTTPException(status_code=404, detail=f"Unknown optimization run {optimization_id}")
+        report = record.report()
+        return {
+            "run": record.model_dump(mode="json", exclude={"trace"}),
+            "report": report.model_dump(mode="json"),
+            "markdown": report.to_markdown(),
+        }
+
     @app.post("/api/eval/runs/{run_id}/cancel")
     async def cancel_eval_run(run_id: str) -> Any:
         current = manager()