Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,28 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-

---

## [0.149.0] — 2026-08-18

### Removed

- Twelve modules and their tests: `reviewer`, `analyst/knowledge-capture`, `multi-toolchain-layer`, `dual-agent-bench`, `workspace-inspector`, `golden-matcher`, `ui-finding`, `slo`, `adapters/langchain`, `judge-runner`, `cost-report` and `worker-driver-seed`.

0.145.3 tiered the root barrel to consumer-imported symbols and documented front doors. These twelve lost their last export path in that pass and kept their source files. Each is unreachable from all 28 build entry points, so none has shipped in `dist` since 0.145.3, and the only importer each retained was its own test.

**The public export surface does not move.** A build of 0.148.0 and a build of this release each declare 3,447 export entries, and the two lists are identical. No consumer of any published version can be importing a deleted name, because none of them was reachable to import.

### Changed

- Four doc comments named a deleted symbol and now describe the surviving behaviour: `multi-layer-verifier` (twice), `fuzz/types` and `contract/self-improve`, plus the `docs/feature-guide` feature map. `dist` loses 753 bytes, all of it that doc-comment text.

### Migration

Nothing to do. No symbol removed here has been importable since 0.145.3.

One repository still names three of them. `starter-foundry` imports `runAssertions`, `WorkspaceAssertion` and `WorkspaceSnapshot` from this package and pins it to exactly `0.135.1`, where those symbols still exist, so it builds today and this release does not change that. The constraint it already carries is that it cannot move past 0.145.3 without porting them, and that predates this release by four versions. The workspace-assertion helpers were a thin projection over a snapshot it already builds itself.

---

## [0.148.0] — 2026-08-18

### Added
Expand Down
2 changes: 1 addition & 1 deletion clients/python/pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ build-backend = "hatchling.build"

[project]
name = "agent-eval-rpc"
version = "0.148.0"
version = "0.149.0"
description = "Python RPC client, official optimizer bridge, and DSPy metric adapter for @tangle-network/agent-eval."
readme = "README.md"
requires-python = ">=3.10"
Expand Down
2 changes: 1 addition & 1 deletion clients/python/src/agent_eval_rpc/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@
try:
__version__ = version("agent-eval-rpc")
except PackageNotFoundError:
__version__ = "0.148.0"
__version__ = "0.149.0"

__all__ = [
"Client",
Expand Down
2 changes: 1 addition & 1 deletion clients/python/uv.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion docs/feature-guide.md
Original file line number Diff line number Diff line change
Expand Up @@ -152,7 +152,7 @@ Store as `FeedbackTrajectory`, then derive:
| Area | Key exports | Best for | Notes |
| --- | --- | --- | --- |
| Judging | `llmJudge`, semantic judges, anti-slop, wire rubrics | Content, voice, semantic quality | Pair with objective checks when possible. |
| Verification | `MultiLayerVerifier`, `JudgeRunner`, sandbox harness | Code and multi-step gates | Do not let semantic judges override failed builds. |
| Verification | `MultiLayerVerifier`, sandbox harness | Code and multi-step gates | Do not let semantic judges override failed builds. |
| Control | `runAgentControlLoop`, `objectiveEval`, `subjectiveEval` | Long-running agent tasks | Supports budgets, cost, stop policies, trace spans. |
| Propose/review | `runProposeReview` | Iterative artifact repair | Good for code, docs, plans, briefs. |
| Feedback data | `FeedbackTrajectory`, stores, converters | Human/environment labels | Domain adapters live in downstream repos. |
Expand Down
2 changes: 1 addition & 1 deletion package.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "@tangle-network/agent-eval",
"version": "0.148.0",
"version": "0.149.0",
"description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
"homepage": "https://github.com/tangle-network/agent-eval#readme",
"repository": {
Expand Down
125 changes: 0 additions & 125 deletions src/adapters/langchain.ts

This file was deleted.

2 changes: 1 addition & 1 deletion src/analyst/benchmark-implementation.ts
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ export const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
])

export const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 =
'5c7e5561a2ecaa48aaffc52d8a44f582642ed434a92839ae4741ad5556fd9789'
'3e17b679d34215f636931e6d39cb5215d878cdaa501c38fd6cef513ce844677f'

/** The published benchmark evidence was produced at this package version, by
* the retired one-shot direct runner, before trace analysts moved to the
Expand Down
Loading
Loading