Compaction level 2 summarizes every old turn at once, leaving 10–24% of the budget at 96K
I maintainer di solito rispondono entro 1 giorno
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 4/5
- Tempo stimato
- 3-5 giorni
- Idoneità per principianti
- 48/100
- Tipo di issue
- Funzionalità
- Chiarezza
- Abbastanza chiara
- Stato di attività
- Attiva
- Stack tecnologico
- rust
- Ambito
- ai-infra-agents, performance
Direzione di ricerca
Start with level2_summarize_old_turns and compact_messages in src/context.rs, then read docs/evals/compaction-defaults.md and run the compaction_sweep example to establish the baseline. Compare the 96K and 26K rows against the acceptance criteria, and add coverage for partial summaries and byte-for-byte stability before deciding whether the measured tradeoffs meet the target.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Summary
At the default budget (96K effective), a compaction leaves far less history than its own target asks for. Level 2 summarizes every turn older than keep_recent in one pass, whatever the target, so the context drops to 10–24% of the budget while the target sits at 30–70%. The model loses the detail of all older turns at once, with most of the budget unused.
Follow-up to #150 (closed by #393, which fixed the small-budget cliff in level 3). Noted in docs/evals/compaction-defaults.md: "level 2's all-or-nothing summarization is the remaining cliff at 96K."
Numbers
cargo run --release --example compaction_sweep (drives the real compact_messages; floor 0.30, compact_headroom_turns: Some(30), keep_recent: 10, 5 seeds × 240 requests), at 96K:
| profile | growth/turn | effective target | left after a compaction (mean / min) | compactions /100 |
|---|---|---|---|---|
| chat | ~0.7K | 0.70 (cap) | 24.1% / 22.8% | 0.4 |
| records (#150's shape) | ~1.6K | ~0.50 | 10.5% / 9.3% | 1.7 |
| coding | ~3.4K | 0.30 (floor) | 19.7% / 9.9% | 3.8 |
| mixed | varies | — | 23.9% / 7.4% | 2.3 |
The effective target is ContextConfig::effective_target_ratio: (budget − 30 × growth) / budget, capped at compact_target_ratio (0.7) and floored at MIN_HEADROOM_RATIO (0.30). For records it asks to keep ~48K and level 2 leaves ~10K. Level 3 never runs: level 2 already lands under the target.
Why
level2_summarize_old_turns(messages, keep_recent) (src/context.rs) replaces every assistant message before the keep_recent boundary with a [Summary] … one-liner and drops its tool results. The target isn't an input. compact_messages checks the target only afterwards (if total_tokens(&compacted) <= target).
Proposed
Summarize the oldest turns only until the history fits the target, the way level 3 drops the smallest span that reaches it. Turns between that point and the keep_recent boundary stay in full detail.
Things to settle with the sweep before changing it:
- Retention vs compaction count. Keeping more after a compaction means reaching the budget sooner.
records@ 96K should move from ~10% toward ~50% kept; measure how muchcmp/100and the ideal hit rate move. - Prefix-cache stability. Today a second pass re-summarizes from the same boundary. A partial summary moves the boundary each pass, so check the bytes before it stay put. Summaries are deterministic and inherit the turn's timestamp, so this should hold, but it needs a test like
a_second_compaction_keeps_the_front_byte_for_byte. - Small budgets. At 26K, level 3 (with #393) already handles the protected set. Confirm the 26K rows don't regress.
Acceptance
- The sweep's 96K rows: post-compaction size close to the effective target, the compaction count not materially higher, the hit rate not lower.
- The 26K rows unchanged or better on
head-/ask-/mkr. compaction_is_well_formed_within_budget_and_keeps_what_fitsstill passes, plus a level-2 test that a partial summary keeps the turns after its cut in full.
- Lingua principale
- Rust
- Stelle
- 327
- Fork
- 46
- Merge medio
- 2h 36m
- PR unite (30g)
- 107
Preparare l'ambiente
- Nessun Dockerfile né file Docker Compose
- Ha un modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di yologdev/yoagent
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 3/5 1-2 giorni Idoneità per principianti 78/100
I maintainer di solito rispondono entro 1 giorno
-
enhancement
Difficoltà 4/5 3-5 giorni Idoneità per principianti 25/100
I maintainer di solito rispondono entro 1 giorno
-
enhancement P3
Difficoltà 4/5 3-5 giorni Idoneità per principianti 35/100
I maintainer di solito rispondono entro 1 giorno
-
enhancement P3
Difficoltà 5/5 Più di una settimana Idoneità per principianti 35/100
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di yologdev/yoagent
Issue simili
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
I maintainer di solito rispondono entro 5 giorni
-
bug studies ui
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
userFRM/egui-charts#3308 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 74/100
I maintainer di solito rispondono entro 1 giorno
-
marketing
Difficoltà 2/5 1-3 ore Idoneità per principianti 90/100
I maintainer di solito rispondono entro 1 giorno
-
bug
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
meerkat-lang/meerkat#279 ·
I maintainer di solito rispondono entro 1 giorno