delimit-cli 4.1.43 → 4.1.47

package/CHANGELOG.md

@@ -1,5 +1,38 @@
 # Changelog
 
+## [4.1.45] - 2026-04-09
+
+### Fixed
+- **Shim rename-hack removed** — install no longer races with npm reinstalls that clobbered `/usr/bin/claude` back to a symlink, causing `[Delimit] claude not found in PATH` mid-session. Shim now relies purely on `$HOME/.delimit/shims` being first in `PATH` plus a PATH-strip lookup for the real binary. Fixes regressions from the claude-real rename+wrap install mechanism.
+- Shim exit screen parity and CLI lint output parity (LED-078, LED-087).
+
+## [4.20.0] - 2026-04-20
+
+*The highest state of AI governance.*
+
+### Added
+- `delimit doctor` — 14 prescriptive diagnostics with `--ci` JSON, `--fix` auto-repair, health score
+- `delimit status` — visual terminal dashboard with `--json`, `--watch` live refresh
+- `delimit simulate` — policy dry-run (terraform plan for API governance)
+- `delimit report` — governance report with `--since`, `--format md|html|json`
+- Memory hardening — SHA-256 integrity hash + source_model on every `remember`
+- Tag-based publishing — `scripts/release.sh` + GitHub Actions workflow
+- Gateway sync gate — `prepublishOnly` auto-syncs from gateway (drift impossible)
+- YouTube auto-publish pipeline — `scripts/record-and-upload.sh`
+- VS Code extension v0.2.0 — simulate + report commands
+- 17 new tests for v4.20 features (total: 123)
+
+### Fixed
+- Flaky test timeouts (5s → 15s for hook/deliberate tests)
+- PostToolUse hook test updated for tightened spec patterns
+- Dashboard workspace filter now filters data by project (LED-330)
+- Hardcoded usernames scrubbed from gateway (moved to env var)
+
+### Changed
+- README updated with v4.20 features and new quick-start commands
+- Landing page: tool count 176 → 186, doctor + simulate cards, YouTube embed
+- Demo GIF updated with clean mock data (Acme API)
+
 ## [4.1.0] - 2026-04-03
 
 ### Added

package/README.md

@@ -16,13 +16,18 @@ The universal command for the Delimit Swarm. When you say **"Think and Build"**,
 Works across any configuration — from a single model on a budget to an enterprise swarm of 4+ models.
 
 [![npm](https://img.shields.io/npm/v/delimit-cli)](https://www.npmjs.com/package/delimit-cli)
+[![Tests](https://img.shields.io/badge/tests-123%20passing-brightgreen)](https://github.com/delimit-ai/delimit-mcp-server)
+[![MCP Tools](https://img.shields.io/badge/MCP%20tools-186-blue)](https://delimit.ai)
 [![GitHub Action](https://img.shields.io/badge/GitHub%20Action-v1.6.0-blue)](https://github.com/marketplace/actions/delimit-api-governance)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![Glama](https://glama.ai/mcp/servers/delimit-ai/delimit/badge)](https://glama.ai/mcp/servers/delimit-ai/delimit)
-[![API Governance](https://delimit-ai.github.io/badge/pass.svg)](https://github.com/marketplace/actions/delimit-api-governance)
 
 <p align="center">
-  <img src="docs/demo.gif" alt="Delimit detecting breaking API changes" width="700">
+  <img src="docs/demo.gif" alt="Delimit v4.20 — doctor, simulate, status, memory" width="700">
+</p>
+
+<p align="center">
+  <a href="https://youtu.be/8e_6P7rkFxo">Watch the demo</a> · <a href="https://youtu.be/4O1wY4vWmiY">Multi-model deliberation</a> · <a href="https://delimit.ai">Website</a>
 </p>
 
 ---
@@ -30,10 +35,11 @@ Works across any configuration — from a single model on a budget to an enterpr
 ## Try it in 2 minutes
 
 ```bash
+npx delimit-cli doctor            # 14 prescriptive checks — tells you exactly what to fix
+npx delimit-cli status            # Visual dashboard of your entire governance setup
+npx delimit-cli simulate          # Dry-run: see what would be blocked before you commit
 npx delimit-cli scan              # Instant health grade for your API spec
 npx delimit-cli try owner/repo    # Try governance on any GitHub repo
-npx delimit-cli pr owner/repo#123 # Review any GitHub PR for breaking changes
-npx delimit-cli setup && source ~/.bashrc  # Configure AI assistants + activate
 ```
 
 No API keys. No account. No config files.
@@ -64,7 +70,42 @@ npx delimit-cli init        # Sets up governance + drift baseline
 
 ---
 
-## What's New in v4.1
+## What's New in v4.20
+
+*The highest state of AI governance.*
+
+- **`delimit doctor`** -- 14 prescriptive diagnostics. Every failure prints the exact command to fix it. `--ci` for pipelines, `--fix` for auto-repair.
+- **`delimit simulate`** -- policy dry-run. See what would be blocked before you commit. The `terraform plan` for API governance.
+- **`delimit status`** -- visual terminal dashboard. Policy, specs, hooks, CI, MCP, models, memory, ledger, evidence, git branch. `--watch` for live refresh.
+- **`delimit report`** -- governance report. `--since 7d --format md|html|json`. Audit-friendly output for PRs and compliance.
+- **Memory hardening** -- SHA-256 integrity hash + source model tag on every `remember`. Cross-model trust, verified on every `recall`.
+- **Tag-based publishing** -- automated gateway sync, no more version drift between source and npm bundle.
+
+### Multi-Model Deliberation
+
+Run your question through 4 AI models simultaneously. They debate each other until unanimous agreement.
+
+```bash
+delimit deliberate "Should we build rate limiting in-house or use a managed service?"
+```
+
+```
+  Round 1 (independent):
+    Claude:  Build in-house. Redis sliding window is 50 lines.
+    Gemini:  Build. You already have Redis.
+    Codex:   Agree — but add circuit breaker for Redis failures.
+    Grok:    Build. Managed service costs $200/mo for 50 lines of code.
+
+  Round 2 (deliberation):
+    All models: AGREE
+
+  UNANIMOUS CONSENSUS (2 rounds, confidence 94/100)
+  Build rate limiting in-house with Redis + circuit breaker.
+```
+
+3 free deliberations, then BYOK for unlimited. Works with Grok, Gemini, Claude, GPT-4o.
+
+### v4.1
 
 - **TUI** -- terminal-native Ventures panel, real `delimit think` and `delimit build` commands
 - **Security hardening** -- notify.py stubbed in npm, axios pinned against supply chain attacks