Skip to content

Release 0.4.0: usage reporting, routing calibration, audit nudge, handoff + dispatch/predup hardening#2

Merged
dropdevrahul merged 1 commit into
mainfrom
review-fixes
Jun 20, 2026
Merged

Release 0.4.0: usage reporting, routing calibration, audit nudge, handoff + dispatch/predup hardening#2
dropdevrahul merged 1 commit into
mainfrom
review-fixes

Conversation

@dropdevrahul

Copy link
Copy Markdown
Owner

Brings main (v0.2.1) up to v0.4.0. Five commits of context + model-cost optimization work for the nexum plugin.

Highlights

0.4.0 features

  • Usage reportingstore.py record-usage CLI; cost_report.py relabels the per-tier breakdown as ESTIMATED (metered session_cost stays authoritative); nx-build.md §6a logs an estimated usage row per dispatch.
  • Per-repo routing calibrationroute_calibration table + record/list helpers and calib-record/calib-list CLI; nx-plan.md nudges weak routes up one tier (advisory only — never down, never moves needs-strong).
  • Audit nudgescripts/audit_nudge.py throttled SessionStart one-liner wired into hooks.json.

Reliability fixes

  • predup freshness guard — a read passes through when its prior tool_calls row is older than predup_max_age_seconds (default 900; 0 = old behavior), so subagent/compaction rows no longer false-deny the parent.
  • dispatch hardeningmax_steps_per_dispatch 6→4 plus size-aware batching (store.partition_steps_by_size + plan_preview.py), bounded by max_dispatch_context_tokens (50k).

Earlier on this branch (0.3.x)

  • Pre-emptive dedup, plan cost preview, resume nudge.
  • Session handoff feature; commands renamed to nx-*; context levers hardened.
  • 100k auto-handoff driven off real transcript context size.
  • /nexum-implement request-cost overhaul + metered cost capture.

Verification

  • python3 -m pytest tests/ -q327 passed
  • python3 tools/check_version.py → version 0.4.0 consistent across manifests
  • CHANGELOG [0.4.0] entry added (Added/Changed/Fixed)

Notes

  • Usage-reporting data capture begins on the next /nx-build (the orchestrator that produced this branch predates §6a).
  • The predup guard mitigates but does not fully resolve cross-context false-denies; a deeper fix (tagging tool_calls rows by originating context) is tracked as follow-up.
  • No v0.3.0/v0.4.0 git tag exists yet — tagging deferred pending release-mechanism decision.

…dispatch + predup

Features:
- Usage reporting: store.py `record-usage` CLI; cost_report.py relabels the
  per-tier breakdown as ESTIMATED (metered session_cost stays authoritative);
  nx-build.md §6a logs an estimated usage row per dispatch.
- Per-repo routing calibration: route_calibration table + record/list helpers
  and calib-record/calib-list CLI; nx-plan.md nudges weak routes up one tier
  (advisory only — never down, never moves needs-strong).
- Audit nudge: scripts/audit_nudge.py throttled SessionStart one-liner, wired
  into hooks.json (audit_nudge_enabled / audit_nudge_throttle_hours).

Reliability fixes:
- predup freshness guard: allow a read through when its prior tool_calls row is
  older than predup_max_age_seconds (default 900; 0 = old behavior), so
  subagent/compaction rows no longer false-deny the parent.
- dispatch hardening: max_steps_per_dispatch 6->4 plus size-aware batching via
  store.partition_steps_by_size and plan_preview.py, bounded by
  max_dispatch_context_tokens (50k) and dispatch_step_base_tokens (1500).

Version bumped 0.3.0->0.4.0 across manifests; CHANGELOG [0.4.0] entry added.
Full suite: 327 passed.
@dropdevrahul
dropdevrahul merged commit 0377553 into main Jun 20, 2026
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant