…ry, PalaceContext

Lands the read-side contract so third-party adapter authors (@Perseusxrltd,
@JakobSachs, @adv3nt3, @zendesk-thittesdorf, @mfhens, @roip, @MrDys) have a
stable target matching what RFC 001 §10 landed on the write side in #995.

Scope (this PR):

- mempalace/sources/base.py: BaseSourceAdapter ABC with kwargs-only
  ingest() / describe_schema() and default is_current() / source_summary()
  / close() (§1.1–1.2). Typed records: SourceRef, SourceItemMetadata,
  DrawerRecord, RouteHint, SourceSummary, AdapterSchema, FieldSpec (§1.3,
  §5.2). Error classes: SourceNotFoundError, AuthRequiredError,
  AdapterClosedError, TransformationViolationError, SchemaConformanceError
  (§2.7). Class-level identity contract: name / adapter_version /
  capabilities / supported_modes / declared_transformations /
  default_privacy_class (§2.1, §1.4, §1.5, §6).

- mempalace/sources/transforms.py: reference implementations of the 13
  reserved transformations (§1.4) — utf8_replace_invalid, newline_normalize,
  whitespace_trim, whitespace_collapse_internal, line_trim, line_join_spaces,
  blank_line_drop — as pure functions, plus identity shims for the six
  adapter-specific ones (strip_tool_chrome, tool_result_truncate,
  tool_result_omitted, spellcheck_user, synthesized_marker,
  speaker_role_assignment) that the conversations adapter will override
  when migrated. get_transformation(name) resolves by reserved name.

- mempalace/sources/registry.py: entry-point discovery via
  importlib.metadata.entry_points(group="mempalace.sources") + explicit
  register()/unregister() surface (§3.1–3.2). resolve_adapter_for_source()
  implements the §3.3 priority order; crucially, no auto-detection on the
  read side (§3.3 is explicit about that — user intent never inferred from
  on-disk artifacts).

- mempalace/sources/context.py: PalaceContext facade (§9) bundling the
  drawer/closet collections, knowledge graph, palace path, adapter identity,
  and progress hooks core passes into adapter.ingest(). upsert_drawer()
  applies the spec-mandated adapter_name/adapter_version stamps from §5.1.
  skip_current_item() signals laziness; emit() dispatches to hooks and
  swallows hook exceptions.

- mempalace/knowledge_graph.py: add_triple() gains optional source_drawer_id
  and adapter_name kwargs (§5.5). Backwards-compatible column migration
  auto-adds the new columns on open of a pre-RFC 002 palace (PRAGMA
  table_info then ALTER TABLE ADD COLUMN), matching the pattern used for
  any new palace-side provenance fields.

- pyproject.toml: mempalace.sources entry-point group declared. Empty on
  the first-party side for now — miners migrate in a follow-up; the group
  being present means third-party packages can begin registering today.

Out of scope (explicit follow-ups):

- miner.py → mempalace/sources/filesystem.py. Behavior-preserving rename
  that also moves READABLE_EXTENSIONS, detect_room(), detect_hall() into
  the adapter (§9). Larger refactor; lands separately.
- convo_miner.py + normalize.py → mempalace/sources/conversations.py. The
  format-detection if-chain in normalize.py becomes per-format plugins;
  declared_transformations enumerates what the current pipeline already
  does to source bytes (§1.4 existing-code mapping).
- Closet post-step wired into the conversations adapter (§1.7).
- CLI --source flag + --mode deprecation alias (§3.3).
- MCP mempalace_mine tool source parameter.
- AbstractSourceAdapterContractSuite (§7.1–7.3): byte-preservation round-
  trip and declared-transformation round-trip tests.
- Privacy-class floor enforcement (§6.2); depends on #389 for
  secrets_possible scanning.

Tests: 1018 passed (up from ~990 on develop), +27 targeted tests covering
the ABC instantiation rules, typed records, all reserved transformations,
the registry register/get/unregister surface, PalaceContext upsert + skip +
emit semantics, and both the new KG provenance kwargs and backwards-
compatible legacy-schema migration.

Refs: #989 (RFC 002 tracking), #990 (RFC 002 spec), #995 (RFC 001 §10
cleanup — sibling PR on the write side).

…uard

Merges MemPalace#990 (RFC 002 spec), MemPalace#1014 (BaseSourceAdapter/PalaceContext scaffolding),
MemPalace#1013 (Layer3.search_raw None guard), MemPalace#1012 (docs), MemPalace#1010 (chromadb >=1.5.4),
and MemPalace#998 (sweeper/tandem transcript safety net).

Fork changes preserved:
- quarantine_stale_hnsw() in chroma.py (guards HNSW/sqlite drift segfault)
- get-then-create instead of get_or_create (guards ChromaDB 1.5.x metadata segfault)
- paginated status() loop (guards SQLite variable limit on large palaces)
- searcher hits-loop, BM25 fallback, _count_in_scope
- .jsonl exempt from JUNK_FILE_SIZE cap (Claude Code transcripts can be large)
- _validate_where() + operator constants taken from upstream

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

Version bumps across pyproject.toml, mempalace/version.py, README badge,
uv.lock, and plugin manifests (.claude-plugin/*, .codex-plugin/*).

CHANGELOG aligned with main (post-3.3.1) and a new [3.3.2] section added
covering the 11 PRs merged on develop since v3.3.1 — silent-transcript-drop
fix + tandem sweeper (#998), None-metadata guards (#999, #1013),
chromadb ≥1.5.4 for Py 3.13/3.14 (#1010), Windows Unicode (#681),
HNSW quarantine recovery (#1000), PID stacking guard (#1023), doc-path
cleanup (#996, #1012), and RFC 001/002 internal scaffolding (#995, #1014, #990).

… Cursor, Aider, Gemini CLI, Codex CLI, Warp)

Adds a new "What's next" bullet for first-class support across the AI
coding agent ecosystem. Today's integration is Claude Code-specific
(Stop / PreCompact hooks, ~/.claude/projects/*.jsonl mining); the
roadmap target is the broader set of coding agents.

Path is upstream's RFC 002 source-adapter spec (MemPalace#990): each agent
ships a pip install mempalace-source-<agent> package mapping its
session format onto the canonical drawer shape, with parity on
session_id / agent / wing.

Frames the integration matrix as three cells:
* read — universal (MCP server is already agent-agnostic)
* mine — per-agent via RFC 002 adapters
* hook/event — wherever the host exposes a hook surface, falling
  back to mining-on-cron

Fork unblocks the pattern; adapter PRs land per-agent. Companion
to the agent-shaped-CLI item already in What's next; together they
cover both surfaces of the agent integration story.

https://claude.ai/code/session_01GvwducFnFtN8KYmfbWKMR6

…Code, MemPalace#274/MemPalace#232 Cursor, MemPalace#169 Pi, MemPalace#702 Cursor+factory.ai)

Updates the multi-agent-support bullet to cite the actual upstream
work instead of just gesturing at it. RFC 002 itself is PR MemPalace#990
(tracking issue MemPalace#989). Existing third-party prototypes already
proposed against the spec:

* OpenCode SQLite — PR MemPalace#23
* Cursor SQLite — issue MemPalace#274
* Cursor JSONL (earlier variant) — PR MemPalace#232
* Pi agent JSONL — PR MemPalace#169
* Combined Cursor + factory.ai — PR MemPalace#702

Each becomes a mempalace-source-<agent> package once RFC 002 lands.
Names the path explicitly: fork unblocks the pattern by helping land
RFC 002; per-agent adapter PRs land from their respective authors.

Aider, Gemini CLI, Codex CLI, and Warp are roadmap targets without
existing adapter PRs and are listed as such (no fabricated PR refs).

https://claude.ai/code/session_01GvwducFnFtN8KYmfbWKMR6