hermes-agent/docs
Michael Jordan cac9526d2a feat(agent): token telemetry for micro-compaction
The existing log line reports message counts, which is the least
informative number available here: absorbing one tool-heavy exchange can
drop hundreds of tokens while moving the count by one. There was no way to
answer "is this actually helping?" from a real session.

Emit one content-free JSON line per pass, in the same shape as the batch
compaction telemetry: before/after tokens, the delta, the size of the
absorbed exchange, the rolling summary size, duration, and running
per-session totals so a whole run can be read off the last line. No
transcript content rides along.

Add scripts/micro_compaction_report.py to aggregate those lines into
passes, outcome mix, net tokens saved, mean exchange size and durations,
with an optional per-session breakdown.

Measuring it immediately surfaced something worth documenting: the first
pass in a session normally *costs* tokens. The summary marker carries a
fixed ~400 tokens of scaffolding, paid on pass one against a single
absorbed exchange. From pass two the marker is replaced rather than added,
so the overhead is already paid and each exchange is close to pure saving.
Break-even is typically the second or third pass. Tests cover the
telemetry contract, the cumulative totals, and that first-pass/later-pass
shape so nobody reads a single turn and concludes it made things worse.

The estimator costs ~5 ms at 600 messages and ~20 ms at 1200, taken twice
per pass, post-turn — and only once an exchange is actually in hand, so
turns that no-op early pay nothing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-31 17:44:19 +05:30
..
design docs(profile): update clone-from references 2026-06-13 07:33:58 -07:00
kanban feat(kanban): gate notifier watcher on dispatch_in_gateway 2026-06-01 20:30:24 -07:00
middleware fix(middleware): preserve translated downstream failures 2026-06-06 09:26:18 -07:00
observability Merge remote-tracking branch 'origin/main' into feat/gateway-health-diagnostics-monitoring 2026-07-29 15:37:14 +00:00
plans fix(gateway): recover partial Telegram overflow streams 2026-06-10 15:09:35 -07:00
security docs(security): add network egress isolation guide for Docker deployments (#26385) 2026-05-29 14:09:10 +10:00
billing-lifecycle.md feat(cli): plan catalog on Free + plan= deep link + top-up/auto-refill copy split (#68689) 2026-07-22 08:11:09 +05:30
chronos-managed-cron-contract.md docs(chronos): pin hop-1 auth to the hosted-agent bootstrap token 2026-06-24 20:57:43 +10:00
hermes-kanban-v1-spec.pdf feat(kanban): durable multi-profile collaboration board (#17805) 2026-04-30 13:36:47 -07:00
micro-compaction.md feat(agent): token telemetry for micro-compaction 2026-07-31 17:44:19 +05:30
profile-routing.md fix(gateway): gate profile routing on multiplex_profiles + widen batch-key routing to all adapters 2026-07-15 09:50:05 -07:00
rca-ssl-cacert-post-git-pull.md fix(ssl): align guard docs and escape hatch 2026-06-13 21:14:32 -07:00
relay-connector-contract.md fix(relay): coerce Slack behavior flags exactly as the native adapter does 2026-07-29 12:03:01 -07:00
session-lifecycle.md fix(config): shipped template no longer enables session auto-reset (#67772) 2026-07-19 23:33:53 -07:00
streaming-tts.md feat(tts): Gemini SSE + xAI WebSocket streaming providers, tts.streaming.provider knob, docs + E2E tests 2026-07-28 22:31:40 -07:00