Ship Matrix-intake CRM endpoints to the box (v0.1.0:84)

The intake bot's server-side dependencies — GET /api/intake/match (new-vs-
existing lookup) and `source` provenance on log-communication — shipped in
source with 7ad0ee7 but were never packaged. The box ran v83 (pre-7ad0ee7),
so the bot's match calls 404'd: a note on an existing investor would have
created a duplicate, and writes weren't tagged matrix_intake. Bump + build +
install verified live (installed-version 0.1.0:84, clean 83->84 migration,
match endpoint now resolves by name and email). No schema change.

Also log the conversational (LLM-mediated) edit enhancement in ROADMAP.

ROADMAP.md

@@ -102,6 +102,8 @@ Use the **matrix-bridge** repo's pattern to listen on a dedicated ten31-database
 
 **Post-deploy enhancement — fuzzy match + in-thread confirm (Grant, 2026-06-17).** Today `find_intake_match` is **exact-after-normalization** (`_normalize_text` = lowercase+strip), so near-misses — "Charlie" vs "Charles" (same last name), "Acme Capital" vs "Acme Capital LLC", a one-character email typo — return no match and the bot proposes a **new** investor, risking a duplicate the human approves without realizing a near-match exists. The existing in-thread approval gate is useless against this because the human is never *shown* the near-match. Fix: matcher returns **ranked fuzzy candidates** (deterministic pre-filter: normalized name similarity / token overlap + email edit-distance ≤ ~2), surfaced in-thread for the human to confirm or pick, with the **local Spark LLM optionally re-ranking/judging the shortlist** (good at Charlie/Charles + legal-suffix equivalence; fed only the shortlist, never the whole LP list). Keeps the approval gate but makes it effective against duplicates. Land **after** the live smoke — net-new logic + reply grammar + tests; the current exact match is safe and its failure mode (a duplicate) is recoverable via the existing entity-merge subsystem (`backend/entity_*.py`).
 
+**Post-deploy enhancement — conversational (LLM-mediated) edits (Grant, 2026-06-17).** Today an in-thread correction uses a rigid grammar (`edit field=value`). Let a free-form reply that isn't `yes`/`no`/a literal `edit …` be treated as a natural-language revision instruction: send {current proposal + the instruction} back through local Qwen (`spark.py`, the same parse leg — no Claude, no scrub) and re-render the revised proposal card for approval (e.g. "add that we met on June 14" → updated Note). Keeps the draft→human-approve gate (the human still confirms the LLM's revision) and subsumes `edit field=value` as a deterministic fast path. Thread the instruction text into `normalize`'s source so the email-integrity rule still holds (a revised email must appear in the original message or the instruction). Pairs naturally with the fuzzy-match item above — build both as one conversational-UX pass after the smoke. (Parsing of free-form *intake* messages already works today via the Qwen parse leg; this item is specifically about the *edit/refine* turn.)
+
 ### Scoped service-credential auth path for automated CRM writers
 *Surfaced 2026-06-17 while deploying the Matrix intake bot. **Decision: defer — the bot uses a dedicated member username/password for now.** The CRM has no API-key/service-token path; its only auth is username+password → JWT. A dedicated **member** login is appropriately scoped against what matters operationally (no admin: can't manage users, reset data, or change settings) and unblocks the live smoke today.*