Apply P20: M5 splits into M5a (local memory), M5b (Honcho) and M5c (the scheduler)

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

docs/milestones.md

@@ -13,8 +13,9 @@ One session per milestone. The design brief is `docs/design.md`.
 | M3b | `brokerd` runner | Rootless container runner, four tools (read file, write file, sandboxed shell, HTTP fetch with host allowlist), egress proxy | A container with no network grant cannot reach the network; fetch refused for hosts outside the grant |
 | M4a | `gatewayd` + Mattermost conversations | Bot connection over TLS, user-ID allowlist, threads as sessions, bursts as one turn, typing while working, catching up after downtime, the secret store, no listening port | A direct message answered on the real server; a non-allowlisted user gets no response |
 | M4b | Approvals over Mattermost | `gateway.sock`, approval posts, answers by `!approve`/`!deny` in the thread, approvers list, long approvals in parts | An `ask` call approved and refused from Mattermost; the audit log names the post |
-| M5 | Scheduler + memory | Heartbeat and cron on their own slot in isolated sessions; core block, `recall` and `remember` with provenance, FTS5 index, flush-then-compact at idle | Scheduled run leaves the main slot's cache intact; a fact from epoch 1 is recalled in epoch 2; a note written after reading untrusted content is marked on recall |
-| M5b | Embedding index (when justified) | Local embedding server, hybrid retrieval behind the `Retriever` trait, rebuild on model change | A paraphrased query finds a note that lexical search misses; no memory text leaves the host |
+| M5a | Local memory | `memoryd` without a network: the three memory files served to `loopd` once per epoch, the `memory` tool (add, replace, remove, `consolidate`) at `ask`, `memory/archive.md`, FTS5 `recall` over session logs and the archive, `recall` hit counts, `bxctl reindex` | A fact from epoch 1 is recalled in epoch 2; an entry moved by `consolidate` is found by `recall`; a memory edit changes the prompt only at the next epoch; the baseline with the owner's files stays under 3,000 tokens |
+| M5b | Honcho | `memoryd` syncs finished turns to its own Honcho workspace through `roncho`, `recall` and `ask_memory` over Honcho, other workspaces read with the owner's trust labels, moved entries written as conclusions | A turn from a tainted session never reaches Honcho; a result from an untrusted workspace taints the session; Honcho's contents are rebuilt from the logs |
+| M5c | Scheduler | Heartbeat and cron on their own slot in isolated sessions; the tiering job, which proposes what stays at which tier | A scheduled run leaves the main slot's cache intact; the tiering job's proposals reach the owner as ordinary approvals and change nothing on their own |
 | M6 | Subagents + cloud consult | Subagents on their slot returning summaries; consult tool gated by data-class grants with full payload log | A tainted session is refused; payload log matches what was sent |
 | M7 | Split deployment | Each role in its own rootless container; `loopd` with no network; socket volume permissions; egress proxy for tools; host ACL policy in `deploy/` | From inside the `loopd` container, requests to the internet, the tailnet and the host all fail; a tool container without a host grant cannot reach the tailnet |