docs: README AG2 section + CHANGELOG v0.3.11 + v0.3.10 entries

- README: Added AG2 Agent Shell section with install/usage examples
- README: Updated Quick Start with agent commands
- README: Updated VS Code Extension features (AG2, catalog, agent tab)
- README: Updated 50+ CLI commands list with agent commands
- CHANGELOG: v0.3.11 entry (AG2 shell, tools, tests, timeout fix)
- CHANGELOG: v0.3.10 entry (no-placeholder-requirements)

Co-Authored-By: Oz <oz-agent@warp.dev>

Author: tbitcs

CHANGELOG.md

@@ -5,6 +5,38 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.3.11] — 2026-04-22
+
+### Added
+- **AG2 agent shell** (`src/specsmith/agents/`) — Planner/Builder/Verifier agents over Ollama.
+  New CLI commands: `specsmith agent run/plan/status/verify/improve/reports`.
+  Uses AG2 v0.12.0 with native Ollama tool calling. Configurable per-project via `scaffold.yml`.
+- **Self-improvement workflow** (`agents/workflows/improve.py`) — `specsmith agent improve <task>`
+  runs Plan→Build→Verify, produces structured ChangeReport at `.specsmith/agent-reports/`.
+- **AG2 tool surface** — 12 typed tools: filesystem (pathlib, no subprocess), shell, git, tests.
+  Replaces the old `operations.py` concept.
+- **Phase 0–3 documentation** — `docs/baseline-audit.md`, `docs/system-proof.md`.
+- **23 new agent tests** (`tests/test_agent.py`) — tool registry, tool handlers, system prompt,
+  AgentRunner init, SessionState, meta-commands, Ollama integration (live).
+- **tests/conftest.py** — WinError 448 pytest cleanup fix for Windows.
+
+### Changed
+- **Ollama timeout** — 120s → 600s for completion, 300s for streaming. Fixes frequent
+  `[Provider error] timed out` in VS Code sessions.
+- **AgentConfig** — `effective_utility_model` (defaults to primary), `effective_max_iterations`
+  (0 = unlimited, maps to 999).
+- **AGENTS.md** — AG2 four-layer architecture, 12 project rules, updated file registry.
+- **pyproject.toml** — `ag2[ollama]` optional dependency added.
+
+---
+
+## [0.3.10] — 2026-04-10
+
+### Fixed
+- No-placeholder-requirements rule added to system prompt (#69).
+
+---
+
 ## [0.3.6] — 2026-04-09
 
 ### Added

README.md

@@ -121,12 +121,45 @@ specsmith epistemic-audit --project-dir ./my-project
 # Start the agentic REPL
 specsmith run --project-dir ./my-project
 
+# AG2 agent shell — Planner/Builder/Verifier over Ollama
+specsmith agent status                    # check agent config + Ollama
+specsmith agent plan "add logging"        # plan only (no execution)
+specsmith agent run "fix lint errors"     # full Plan → Build → Verify
+specsmith agent improve "add tests"       # self-improvement with reports
+specsmith agent verify                    # run Verifier on current state
+specsmith agent reports                   # list improvement reports
+
 # Check current AEE workflow phase
 specsmith phase --project-dir ./my-project
 ```
 
 ---
 
+## AG2 Agent Shell — Local AI Agents over Ollama
+
+specsmith includes an AG2-based agent shell with three specialized agents:
+
+- **Planner** — inspects repo, generates execution plans with acceptance criteria
+- **Builder** — makes code/doc changes following the plan
+- **Verifier** — runs tests, accepts or rejects changes
+
+All agents run locally on Ollama (default: `qwen2.5:14b`). Zero cloud cost.
+
+```bash
+pip install "specsmith[ag2]"              # install AG2 + Ollama support
+specsmith agent status                    # verify config + Ollama running
+specsmith agent run "fix lint errors"     # Plan → Build → Verify pipeline
+specsmith agent improve "add tests for config.py"  # self-improvement with reports
+```
+
+The agent shell stores structured reports at `.specsmith/agent-reports/` with task ID,
+files changed, test results, verdict (ACCEPT/REJECT), and follow-up tasks.
+
+Configurable per-project in `scaffold.yml` under `agents:` or via the VS Code
+Project Settings → Agent tab.
+
+---
+
 ## VS Code Extension
 
 The **specsmith AEE Workbench** VS Code extension is the flagship client:
@@ -146,7 +179,10 @@ The **specsmith AEE Workbench** VS Code extension is the flagship client:
 - **Execution profiles** — safe / standard / open / admin; custom allow/block command lists
 - **AEE phase indicator** — shows current phase with readiness %, Next Phase button, phase selector
 - **AI agent sessions** — independent process per project, JSONL bridge, chat with file injection
+- **AG2 agent shell** — Planner/Builder/Verifier agents over Ollama in Actions tab
+- **Agent tab** — per-project provider/model/context/iteration config (overrides global defaults)
 - **Live model listing** — Anthropic, OpenAI, Gemini, Mistral, local Ollama (GPU-aware)
+- **Ollama model catalog** — 16 models, 4 tiers, GPU-aware recommendations, filter by installed/available
 - **Ollama integration** — model manager (update/remove/update-all), version check, upgrade
 - **FPGA/HDL tool support** — vivado, gtkwave, vsg, ghdl, verilator, yosys, nextpnr, and 15 more
 - **Tool installer** — scan installed tools; one-click install via winget/brew/apt for missing tools
@@ -219,7 +255,7 @@ Supported tools: **Synthesis:** vivado, quartus, radiant, diamond, gowin.
 
 **Workflow:** `phase show/set/next/list` `ledger add/list` `req list/add/gaps/trace`
 
-**Agent:** `run` `agent providers/tools/skills`
+**Agent:** `run` `agent run/plan/status/verify/improve/reports` `agent providers/tools/skills`
 
 **Ollama:** `ollama list/available/gpu/pull/suggest`