merge: package presence and session memory readiness

CHANGELOG.md

@@ -10,7 +10,20 @@ ______________________________________________________________________
 
 ### Added
 
-- Nothing yet.
+- Tier 3 core session memory implementation:
+  - new `src/tai/session_store.py` persistent ChromaDB store
+  - `--session-memory` option on `tai run`
+  - prior-session retrieval injected into analysis/follow-up prompts
+  - final response indexing at session end
+- Planner enhancements for broader service detection:
+  - generic service candidate extraction from free text
+  - package presence probes in plans (`rpm -q` and `dpkg-query -W`)
+- SSH read-only allowlist expanded to permit package presence commands (`rpm`, `dpkg-query`)
+- Session memory tests in `tests/test_session_store.py`
+
+### Changed
+
+- Documentation alignment updates in README and ROADMAP to reflect implemented session memory and package-presence capabilities.
 
 ______________________________________________________________________
 

README.md

@@ -191,9 +191,8 @@ pytest tests/test_plan.py tests/test_ai.py tests/test_cli.py
 
 ## Known Limits
 
-- Service-specific presence checks currently apply to recognized service/subsystem names.
-- Package-manager-level presence checks are not yet in the default read-only command allowlist.
-- Tier 3 persistent session memory is not implemented yet.
+- Deep service-specific probes (known binary/config/package aliases) are richer for recognized services than generic service names.
+- Session memory is available via `--session-memory`, but dedicated history UX commands (`tai history`, `/history`) are not implemented yet.
 
 ## Changelog and Roadmap
 

ROADMAP.md

@@ -143,7 +143,7 @@ ______________________________________________________________________
 | Hybrid retrieval | Semantic only, BM25 only, hybrid | Hybrid (BM25 keyword + cosine semantic) for best recall | ⬜ Pending |
 | Reranking | None, cross-encoder (`ms-marco-MiniLM`), LLM-as-judge | Cross-encoder rerank pass before prompt injection | ⬜ Pending |
 | Runbook format | Markdown, YAML, JSON | Markdown (human-editable, version-controllable) | ✅ Implemented |
-| Session index storage | Local `~/.tai/`, configurable path | `~/.tai/sessions/` with ChromaDB collection | ⬜ Pending |
+| Session index storage | Local `~/.tai/`, configurable path | `~/.tai/sessions/` with ChromaDB collection | ✅ Implemented (core) |
 
 ______________________________________________________________________
 
@@ -229,28 +229,30 @@ ______________________________________________________________________
 
 ### Tier 3 — Session Memory Index (institutional learning)
 
-Status: ⬜ Pending
+Status: ✅ Implemented (core retrieval/indexing) / ⬜ UX commands pending
 
 **Problem:** Every session starts from zero. Repeat incidents on the same host or
 same issue type get no benefit from past work.
 
-**Approach:**
+**Implemented now:**
 
 - On session end, embed the session summary (issue + root cause + actions) and upsert into a persistent ChromaDB collection (`~/.tai/sessions/`)
 - On session start, query for similar past sessions by issue text + hostname
 - Inject top-2 past sessions as `## Prior Sessions` context
-- Optionally: `/history` command in interactive mode to surface past sessions explicitly
+
+**Pending UX layer:**
+
+- `/history` command in interactive mode to surface past sessions explicitly
 
 **New module:** `src/tai/session_store.py`
 
 - `SessionStore`: wraps ChromaDB collection at `~/.tai/sessions/`
-- `index_session(session_log_path)` — embed and store completed session
-- `query_similar(issue, host, top_k) -> list[PastSession]`
+- `index_session(host, issue, summary, ai)` — embed and store completed session
+- `query(question, host, ai, top_k) -> list[PastSession]`
 
 **Changes to existing code:**
 
-- `session_log.py`: add `summarise() -> str` method (issue + final AI response)
-- `cli.py`: query `SessionStore` at session start, index at session end
+- `cli.py`: query `SessionStore` during analysis turns and index final responses at session end
 
 **Companion features buildable at same time:**
 
@@ -308,14 +310,14 @@ ______________________________________________________________________
 | Date | Decision | Outcome |
 |------|----------|---------|
 | 2026-05-04 | Implementation language | Python — with single distributable binary via Nuitka |
-| — | AI inference backend | vLLM (provisional) |
-| — | Default model | `gemma4:a4b` (provisional) |
+| 2026-05-04 | AI backend API | OpenAI-compatible API endpoint (local Ollama by default) |
+| 2026-05-04 | Default model | `gemma3:4b` |
 | 2026-05-04 | SSH auth methods | Keypair only (ed25519/RSA); auto-accept new hosts; reject on key change (MITM) |
 | 2026-05-04 | Bastion host support | `--jump-host` flag via SSH native ProxyJump |
 | 2026-05-04 | SSH config behavior | Use `~/.ssh/config` by default; allow override via `--ignore-ssh-config` |
 | 2026-05-04 | CLI vs interactive mode | Interactive: REPL for v0.1, `textual` TUI for v0.2+ |
-| 2026-05-04 | RAG embedding model | `nomic-embed-text` via Ollama (local, air-gapped safe) — ⬜ pending confirmation |
+| 2026-05-04 | RAG embedding model | `nomic-embed-text` via Ollama (local, air-gapped safe) |
 | 2026-05-04 | RAG vector store (Tier 1) | In-memory numpy cosine similarity — zero deps, session-scoped |
-| 2026-05-04 | RAG vector store (Tier 2/3) | `chromadb` embedded mode (default) or `qdrant` self-hosted — ⬜ pending confirmation |
+| 2026-05-04 | RAG vector store (Tier 2/3) | `chromadb` embedded mode (default) or `qdrant` self-hosted |
 | 2026-05-04 | RAG chunking unit | Command-boundary splitting — each collected command = one or more chunks |
 | 2026-05-04 | Runbook format | Markdown with YAML frontmatter, version-controlled in `runbooks/` directory |

src/tai/chroma_telemetry.py

@@ -7,6 +7,8 @@ disabled, so tai wires ChromaDB to this no-op client instead.
 
 from __future__ import annotations
 
+from typing import override
+
 from chromadb.config import System
 from chromadb.telemetry.product import ProductTelemetryClient, ProductTelemetryEvent
 
@@ -17,6 +19,7 @@ class NoOpProductTelemetryClient(ProductTelemetryClient):
     def __init__(self, system: System):
         super().__init__(system)
 
+    @override
     def capture(self, event: ProductTelemetryEvent) -> None:
         del event
         return None