Commit Graph
6 Commits
Author SHA1 Message Date
kyleandGrok 4.6 09e362690e docs: M5d-2 hold returns Busy, not Result<(), ()>
clippy result_unit_err is denied by the gate. Context::hold uses a Busy
unit struct; the given tests still only expect Ok.

Co-Authored-By: Grok 4.6 <noreply@x.ai>
2026-10-03 01:56:52 -07:00
kyleandGrok 4.6 e697589b98 docs: M5d-2 task 03 updates the main.rs m5c() count
ask_memory_tool pins Registry::m5c() in main.rs at exactly one call.
Heartbeat's check_summarise adds two more; the task now edits that count
to 3 and still forbids m2b/m3a/m5a.

Co-Authored-By: Grok 4.6 <noreply@x.ai>
2026-10-03 01:43:00 -07:00
kyleandGrok 4.6 c4a8f9488d docs: M5d-2 given tests: unused import and leftover-held
scheduler_heartbeat imported scheduler::{self} without using it, which
clippy -D warnings would fail at task 06. The live-previous cron tick now
asserts a held leftover stays started.

Co-Authored-By: Grok 4.6 <noreply@x.ai>
2026-10-03 01:39:50 -07:00
kyleandGrok 4.6 df987c3058 docs: M5d-2 checklist: given-test lifetimes and cron AND
session_slot and the scheduler tests held a temporary JSON Value across
statements (E0716). Cron now pins DOM and DOW as AND, which the given tests
had not. Gate counts from task 04 on move up by one.

Co-Authored-By: Grok 4.6 <noreply@x.ai>
2026-10-03 01:31:07 -07:00
kyleandGrok 4.6 fb2e269a85 docs: M5d-2 gate count 1508 and OpenCode model id
The M5d-1 gate on straylight is 1508, so every M5d-2 expected count moves up by one.
OpenCode 1.15.10 serves Ornith as llama.cpp/ornith-1.5-35b-a3b.

Co-Authored-By: Grok 4.6 <noreply@x.ai>
2026-10-03 01:24:25 -07:00
kyleandGrok 4.6 3726ae585f docs: M5d-1 and M5d-2 implementation plans for Ornith
Eight closed tasks for epochs and compaction, then ten for the scheduler,
ToolSummary, and tiers. Given tests first. Gate 1456 → 1507 → 1572.

Co-Authored-By: Grok 4.6 <noreply@x.ai>
2026-10-02 21:54:37 -07:00