chore: Release-As 0.8.0 override

[dfrostar]

Summary

Tiny PR — one empty commit with Release-As: 0.8.0 in the footer.

Why

PR #125 (v0.8 always-on) was merged with merge-commit title "v0.8.0: always-on…" instead of conventional-commit format (feat(serve): …). Release-please reads merge-commit titles for non-squash merges and missed the feat: prefix, so it proposed v0.7.1 (PR #127, now closed) covering only the fix(ci): PAT patch from PR #126 — missing the always-on work entirely.

The always-on code (/healthz, systemd/launchd templates, docs/use-cases/always-on.md, RELEASE_NOTES_v0.8.0.md) is already on main. This commit overrides release-please's version proposal so the next release-please PR proposes v0.8.0 with the correct changelog scope (always-on + PAT fix combined).

Test plan

• No code changes; empty commit only
• Release-As: footer is the documented release-please override mechanism

Order of operations after this merges

1. release-please re-runs on the merge, opens a new PR proposing v0.8.0 (PR chore: Release-As 0.8.0 override #128 or thereabouts)
2. Merge that release-please PR (squash) → cuts the v0.8.0 tag
3. Once RELEASE_PLEASE_TOKEN is set as a repo secret (the PAT setup from fix(ci): use PAT for release-please so tag pushes trigger release.yml #126), release.yml auto-publishes to PyPI on the tag push. Without the secret, gh workflow run release.yml --ref v0.8.0 from your laptop.

Process-fix going forward

Merge commit titles for non-squash merges need conventional-commit format. I'll apply that from now on.

https://claude.ai/code/session_01SH6iHNAqeMJHXdq7ubVcuJ

---

Generated by Claude Code

[Copilot]

Copilot wasn't able to review any files in this pull request.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

NeuralMind self-benchmark

Status: PASS — floor 4×, measured 5.9×.

Phase 1 — Reduction on committed fixture

• Average reduction: 5.9×
• Top-k retrieval hit rate: 71.7%
• Naive baseline: 47,360 tokens (all fixture files concatenated)
• NeuralMind total: 8,149 tokens across 10 queries
• Estimated monthly savings @ 100 queries/day on Claude 3.5 Sonnet: ~$35.30

#	Query	Shape	Naive	NeuralMind	Ratio	Hit
1	auth-flow	cross-file	4,736	815	5.8×	33.3%
2	api-endpoints	focused	4,736	809	5.9×	100.0%
3	billing-flow	cross-file	4,736	846	5.6×	33.3%
4	user-storage	cross-file	4,736	672	7.0×	50.0%
5	jwt-verify	focused	4,736	681	7.0×	100.0%
6	stripe-webhook	focused	4,736	838	5.7×	100.0%
7	create-user	cross-file	4,736	794	6.0×	50.0%
8	refund	focused	4,736	827	5.7×	100.0%
9	db-choice	identity	4,736	899	5.3×	100.0%
10	invoice-send	cross-file	4,736	968	4.9×	50.0%

Phase 2 — Learning uplift

• Memory events logged: 20
• Learned patterns: 20
• Reduction ratio after neuralmind learn: 5.9× (Δ +0.00× vs. cold)
• Top-k hit rate after learning: 71.7% (Δ +0.0 points vs. cold)

Note: uplift numbers on a 500-line fixture are intentionally modest — the point is to
verify the learning mechanism persists and applies. On real production repos the lift
is larger; this test only catches regressions in persistence.

Assumptions

• Baseline: every .py file in tests/fixtures/sample_project/ concatenated.
• Tokenizer: tiktoken GPT-4o encoding (per-model breakdown in multi_model.json if generated).
• Pricing: Claude 3.5 Sonnet input @ $3.0/MTok.
• Regression floor: 4× — well below NeuralMind's typical 40–70× on real repos.

Per-model token reduction

Model	Tokenizer	Naive	NeuralMind	Ratio	Source
GPT-4o / GPT-4o-mini	tiktoken o200k_base	4,739	927	5.1×	measured
GPT-4 / GPT-3.5-turbo	tiktoken cl100k_base	4,710	918	5.1×	measured
Claude 3.5 Sonnet	estimated: GPT-4o × 1.08 — install anthropic for an exact count	5,118	1,001	5.1×	estimated
Llama 3 (70B)	estimated: GPT-4o × 1.22 — Llama tokenizer requires model weights; estimate based on published vocab ratios	5,781	1,130	5.1×	estimated

Rows marked measured use the provider's real tokenizer. Rows marked
estimated apply a published vocab-size correction to the GPT-4o count —
honest approximations, not hardcoded claims.

---

Automated by .github/workflows/ci-benchmark.yml — regenerate locally with python -m tests.benchmark.run.