@praneeth_54/agentdoctor 2.0.1 → 3.0.0

package/CHANGELOG.md

@@ -7,6 +7,126 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [3.0.0] — 2026-09-26
+
+Public release of the **AgentDoctor 3.0 local core**: project intelligence, doctors,
+student/agent workflows, MCP, dashboard, evidence/proof, and honest EXTERNAL
+boundaries. AI providers remain **opt-in**. Correctness is never claimed.
+
+Limitations: [docs/LIMITATIONS.md](docs/LIMITATIONS.md).
+Release prep: [docs/FINAL_PRE_RELEASE_CHECK.md](docs/FINAL_PRE_RELEASE_CHECK.md).
+
+### Highlights
+
+- **Project intelligence** — discovery, DNA, Brain, software map, hybrid search,
+  dependency/lockfile analysis, architecture contracts, git/change impact.
+- **Project Chat** — deterministic `ask` / `chat` with truth labels
+  (`VERIFIED` | `INFERRED` | `UNKNOWN` | `EXTERNAL`); optional AI when configured.
+- **Coding agent** — plan → human approval → path-safe tools → verify; no
+  unrestricted shell; `ENGINEERING_CORRECTNESS_NOT_CLAIMED` preserved.
+- **Student workflows** — `learn`, viva, docs, Build With Me (explain → plan →
+  approve → apply → verify).
+- **Security & approval** — Security Doctor (static), secret redaction, forensic
+  read-only mode, MCP approval tokens + planHash (bare `approved:true` rejected).
+- **Evidence & verification** — change analysis, evidence bundles, change proof
+  (hash integrity; engineering correctness not claimed).
+- **MCP** — combined server with **38** tools (project, intelligence, agent,
+  assurance); path/workspace escape blocked.
+- **Dashboard** — embedded local UI + APIs (status, DNA, graph, search, security,
+  twin, what-if, forensic, chat).
+- **Digital Twin / What-If** — local refreshable twin snapshot; graph-derived
+  impact with uncertainty (not certainty).
+- **Doctors** — API, Database, Event, Security, Privacy, Incident, Deployment
+  (file/static evidence); live runtime / IdP / brokers remain **EXTERNAL**.
+- **Evaluation Lab** — fixture-driven eval including prompt-injection detect-only.
+- **Self-diagnosis** — product self-check surfaces.
+
+### Providers (local)
+
+- Implemented: `none` | `mock` | `openai-compatible` | `ollama`.
+- Native Anthropic / Gemini SDKs: **not implemented** (fail closed via `none`).
+
+### Limitations (not unfinished stubs)
+
+- Live cloud/DB/K8s/APM runtime intelligence: **EXTERNAL**.
+- Neural embeddings / enterprise IdP-SSO: **EXTERNAL**.
+- Full compiler-grade AST/call binding for every language: not claimed.
+- Not an OS sandbox / EDR; not a replacement for commercial SAST/SCA.
+- Proof asserts hash integrity — not absolute engineering correctness.
+
+### Docs / packaging
+
+- Rebuilt public README; public docs under `docs/`; audits in `docs/internal/`.
+- npm package contents: `dist`, `README.md`, `LICENSE`, `CHANGELOG.md`.
+- GitHub Action default package pin: **3.0.0**.
+
+## [2.1.0] — 2026-09-23
+
+Optional Project AI Agent line on top of 2.0.1 assurance. AI remains **opt-in**.
+Historical notes: [docs/internal/RELEASE_2_1_0.md](docs/internal/RELEASE_2_1_0.md).
+Checklist: [docs/internal/RELEASE_CHECKLIST_2_1_0.md](docs/internal/RELEASE_CHECKLIST_2_1_0.md).
+
+#### Project Intelligence
+
+- Project-aware context retrieval (Brain / graph / planContext orchestration).
+- Project Chat CLI (`agentdoctor chat` / `ask`) with evidence-backed answers.
+- Truth labels: `VERIFIED` | `INFERRED` | `UNKNOWN` | `EXTERNAL`.
+
+#### AI Agent
+
+- Provider abstraction (`ModelProvider`): `none` | `mock` | `openai-compatible` | `ollama`.
+- Optional AI architecture: model reasons; AgentDoctor provides context, controls tools, verifies results.
+- Native Anthropic / Gemini SDKs remain **NOT IMPLEMENTED** (fail closed via `none`).
+
+#### Agent Tools
+
+- Read / search tools (path-safe).
+- Create / edit / delete with diffs (approval required).
+- Controlled command and test execution via `runControlledCommand` (`shell=false`).
+- Coding loop: PLAN → APPROVAL → TOOLS → OBSERVE → VERIFY.
+
+#### Safety
+
+- Path safety and symlink-dir escape rejection on writes.
+- Workspace isolation when `WorkspaceModel` is provided; otherwise repo-root binding.
+- Mode `allowWrites` enforcement (LEARN hard-blocks writes).
+- Approval gates (`--approve` / `approvedByHuman`); model cannot self-approve.
+- Dangerous command blocking; prompt-injection data separation (`PROJECT_DATA` / `TOOL_OUTPUT_UNTRUSTED`).
+- Secret redaction (reuses existing redaction infrastructure).
+- Hard agent limits: tool calls, iterations, wall time, files modified, context chars.
+
+#### Verification
+
+- Post-change analysis / evidence / proof / architecture (where applicable).
+- Optional controlled test run (`--run-tests`).
+- Always preserves `ENGINEERING_CORRECTNESS_NOT_CLAIMED`.
+
+#### Student
+
+- `agentdoctor learn` — project explain, viva, docs.
+- Default student experience: **BUILD_WITH_ME** (explain → plan → teach → approve → `runCodingLoop` → verify).
+- Rich interactive student UI remains **PARTIAL**.
+
+#### MCP
+
+- Agent tools: `project_context`, `project_ask`, `code_search`, `file_read`, `file_create`, `file_edit`, `agent_plan`, `change_verify`.
+- No unrestricted shell.
+- `project_ask` fail-closed when provider is `none`.
+- MCP `approved=true` is **trusted-caller input**, not cryptographic human identity; MCP does not carry `AgentMode`.
+
+#### Dashboard
+
+- Project Chat via `POST /api/chat` (ask-only; no file writes).
+- Fail-closed when AI provider resolves to `none` (no silent mock fallback).
+
+#### Known limitations
+
+- Not an OS sandbox / EDR (**EXTERNAL LIMITATION**).
+- Native Anthropic / Gemini SDKs **NOT IMPLEMENTED**.
+- Correctness is never guaranteed.
+- MCP approval is trusted-caller input (not cryptographic human identity); MCP does not carry AgentMode.
+- Rich interactive student UI remains **PARTIAL**.
+
 ## [2.0.1] — 2026-09-23
 
 Hardening and change-assurance cut on top of 2.0.0, plus a deepening pass that
@@ -453,7 +573,9 @@ First public beta.
 - Not a complete secret scanner
 - Git “tracked secret” detection deferred
 
-[Unreleased]: https://github.com/pranee54/AgentDoctor/compare/v2.0.1...HEAD
+[Unreleased]: https://github.com/pranee54/AgentDoctor/compare/v3.0.0...HEAD
+[3.0.0]: https://github.com/pranee54/AgentDoctor/compare/v2.1.0...v3.0.0
+[2.1.0]: https://github.com/pranee54/AgentDoctor/compare/v2.0.1...v2.1.0
 [2.0.1]: https://github.com/pranee54/AgentDoctor/compare/v2.0.0...v2.0.1
 [2.0.0]: https://github.com/pranee54/AgentDoctor/compare/v1.1.1...v2.0.0
 [1.1.1]: https://github.com/pranee54/AgentDoctor/releases/tag/v1.1.1