fix(context): teach result handling and avoid accumulation/polling overhead #501
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "fix/context-contract-latency"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Explicit operator request
Minerva is still slow; verify/update the SYSTEM PROMPT so Main/Dispatcher/workers know how to consume retained/excerpted/structured/grouped tool returns. Prior #498 pressure/lifecycle work remains delivered and is not reopened.
Implementation
Evidence
Real SDK tests exercise Main/worker/subagent projection, targeted retained originals, exact errors/uncertainty, repeated-small-result indexing, no extra summary inference/effect replay, disabled/failed storage and discovery. Typecheck/build and independent review PASS; 49 focused tests PASS. Exact-head full local suite PASS: 2636 passed, 1 existing optional skip, 0 failures (2637 total). Exact-head CI required before merge.
Latency honesty
Read-only live evidence shows real requests taking 8–21 minutes plus five-minute timeouts. Main repeatedly attempted host-blocked bash and polled an unchanged ready task, now addressed in guidance. Backend observation separately found a standalone 4-session/131072-token DS4 process, not the documented 2-session resident RDMA runtime; live prefill around50–100t/s and decoding falling near0.7–1t/s while other sessions prefill, with cold-prefix/cache-eviction churn. These backend observations are NOT per-request correlation or a claim that this Core PR solves serving performance. No busy inference backend was restarted or model silently switched.
A separate concurrent editor changed structured-context worktree authority prompts; this PR uses a fresh isolated worktree and excludes those unrelated changes.