Skip to content

Releases: azank1/cdv

v1.0.1 — dependency guardrails

Choose a tag to compare

@azank1 azank1 released this 01 Aug 00:24

Fixed

  • Cap mcp dependency at <2 — the unpinned mcp>=1.0.0 let pip resolve the new mcp 2.0 line, which the CDV server isn't validated against yet
  • Pin ruff/mypy in dev extras so CI and local runs use identical lint gates

No functional changes.

v1.0.0 — CDV: the judge for AI coding agents

Choose a tag to compare

@azank1 azank1 released this 31 Jul 22:10

CDV (formerly PromptLoop/loopllm) — full rebrand and 1.0. pip install "cdv[mcp]"

Breaking changes

  • PyPI package loopllmcdv; CLI command loopllmcdv
  • Python imports loopllm.*cdv.* (public API symbols unchanged)
  • All 36 MCP tools loopllm_*cdv_*
  • Env vars LOOPLLM_*CDV_*; state dir ~/.loopllm~/.cdv; audit artifact .loopllm/audit.json.cdv/audit.json
  • VS Code extension: loopllm-prompt-gaugecdv-judge ("CDV — Judge for AI Coding Agents")
  • Repo: azank1/loop-llmazank1/cdv (old URLs redirect)
  • cdv migrate-legacy still imports your old ~/.loopllm/store.db — learned priors and episodes carry over

What CDV is

Your agent said it works. CDV is the receipt. Every step an agent claims is judged through two channels — a deterministic floor plus an LLM critic, stricter score wins — with Bayesian stop/continue logic, a git-stamped audit trail, and a per-project memory that learns how your tasks actually converge. Local-first, model-agnostic, no API key.

309 tests, strict mypy, ruff — all green. Full details: CHANGELOG.md

v0.11.0 — CI audit-gate + install-mcp --rules

Choose a tag to compare

@azank1 azank1 released this 22 Jul 19:54

Added

  • CI verification gate: loopllm audit --export <path> writes the audit trail as a portable JSON artifact you commit alongside the code it verifies; loopllm audit-gate --since <ref> [--min-score X] [--require-verified] checks every commit in a PR against it (report-only by default).
  • Reusable composite action .github/actions/loopllm-gate + workflow wiring the gate into this repo's own PRs.
  • loopllm install-mcp --rules drops project-scoped agent-instruction files (Cursor .mdc, VS Code instructions, CLAUDE.md) so the IDE agent actually consults loopllm instead of merely having the tools registered.

Fixed

  • structlog was never configured and could write to stdout, corrupting the MCP stdio JSON-RPC stream; new logging_config.configure_logging() routes all output to stderr with level filtering.

Full details: CHANGELOG.md

v0.7.0 — Conservative Dual-Verify for agent loops

Choose a tag to compare

@azank1 azank1 released this 21 Jun 21:53

Conservative Dual-Verify (CDV)

Agents submit step_output artifacts; the MCP server scores each step through two independent channels:

  • Channel A: deterministic evaluators (regex, JSON, completeness, composite)
  • Channel B: separate critic via MCP sampling (verifier hat)
  • Final score: min(channel_a, channel_b) — the stricter channel wins

Added

  • step_scorer.py, guards.py, evaluator_factory.py
  • Composable guard stack: timeout, token budget, output-repeat, plateau, threshold, Bayesian ROI
  • Async artifact-primary loopllm_loop_step; legacy score fallback with deprecation warning
  • Verdict JSON exposes channel_a_score, channel_b_score, score_source, deficiencies

Changed

  • AgentLoopController uses GuardStack
  • README restructured around three-layer architecture
  • Internal launch docs pruned; docs/launch/show-hn.md updated for CDV

Full changelog: CHANGELOG.md