Eval bug: reasoning loop guard force-closes legitimate reasoning early (looks like reasoning budget exhausted)

Offen
#202 1 Kommentar 0 Reaktionen 0 zugewiesene Personen Auf GitHub ansehen

Dieses Issue hat noch niemand übernommen.

Bewertung

Schwierigkeit
4/5
Geschätzter Aufwand
3-5 Tage
Anfängerfreundlichkeit
45/100
Issue-Typ
Bug
Klarheit
Größtenteils klar
Aktivitätsstatus
Aktiv
Tech-Stack
cpp
Bereich
ai-infra-agents

Rechercherichtung

Start at the /v1/chat/completions entry point and trace how reasoning_loop_guard, reasoning_loop_min_tokens, and the force-close message interact with reasoning-token accounting. Reproduce the reported early cut with the provided 8000-token budget and compare against guard-off behavior. Done means legitimate restatements do not trigger premature closure, actual budget limits still apply, and reasoning-token usage remains accurate when the guard is off.

Vom Indexierungsmodell aus dem Issue-Text verfasst.

Beschreibung

Name and Version

llama-server version: 0.4.9 (build 12930, commit b46c53e54), Windows x64 CUDA 13.3 release binary, router mode.

Operating systems

Windows 11

GGML backends

CUDA

Hardware

RTX 4090 24 GB

Models

unsloth Qwen3.8-27B-GGUF, UD-Q4_K_XL (both the August upload and Dynamic v3.1). The same thing happens with UD-IQ4_XS. Settings: --spec-type draft-mtp --spec-draft-n-max 3, KV kvarn6, --reasoning-budget 8000, --reasoning-budget-message "... reasoning budget exceeded, need to answer.\n", reasoning_effort: medium.

Problem description & steps to reproduce

With the default --reasoning-loop-guard force-close, hidden reasoning is often force-closed well before the reasoning budget is reached. With a budget of 8000, we saw the budget message injected after only about 1.1K–1.9K reasoning tokens. Because the force-close uses the budget message, it looks like a broken budget counter. Budgets of 500 and 2000 are honoured exactly.

All the early cuts we looked at happen at the same point: the model re-states content it wrote earlier in the same reasoning, on purpose. In our case it re-copies a 3×3 OKLab matrix with 10-digit coefficients to double-check it. That is legitimate verification, not a degenerate loop. It is also a very predictable stretch, where MTP drafts get accepted almost entirely.

Test setup: one coding prompt (implement OKLab colour mixing, stdlib only, with stated edge cases), thinking_budget_tokens: 8000, non-streaming /v1/chat/completions, temp 1.0 / top_p 0.95 / top_k 20.

per-request setting early cut (budget message in reasoning) usage.completion_tokens_details.reasoning_tokens
default 3/6 (at 1100–1930 tokens) reported
"reasoning_loop_guard": "off" 0/6 always 0
"reasoning_loop_window": 2048, "reasoning_loop_min_coverage": 1024, "reasoning_loop_min_tokens": 2048 7/8, six of them at exactly 2060 tokens (the first check after min_tokens) reported
"reasoning_loop_min_tokens": 100000 0/6 (2.8K–5.4K tokens of reasoning, finishing normally) reported

An earlier run with the same prompt (budget 8000, 6 requests per model version) cut 4/6 on the August GGUF and 1/6 on v3.1. In a small coding benchmark, the share of tasks with all tests passing dropped from 97 % to 74 %, and every failure traced back to one of these early cuts.

Observations / possible issues:

  1. False positives on legitimate restatements. A single re-copy of a ~200–300-token block is enough to trigger. A larger window and a higher coverage threshold make it worse (7/8). That suggests the detector counts one repetition of a long span as "coverage", not a repetition that happens many times.
  2. Misleading message. The force-close injects the reasoning-budget message. From the client side, a loop-guard intervention can't be told apart from an exhausted budget. The loop_guard telemetry block did not appear in the OpenAI-compatible chat completion response, so we only found the cause by reading the source.
  3. reasoning_loop_guard: off also turns off reasoning-token accounting (reasoning_tokens = 0 in usage), apparently because reasoning_output_tokens is only updated in the loop-guard accept callback.

Suggestions:

  • Require several repetitions (period × count) before triggering, instead of a single restated span.
  • Use a separate message, or none, for loop-guard force-close, and expose the loop_guard event in chat-completion responses.
  • Keep reasoning-token accounting independent of the guard mode.

Workaround in use: reasoning-loop-min-tokens = 100000 in the preset. The reasoning budget still caps real loops.

First Bad Commit

Not bisected. The behaviour is present in v0.4.9.

Relevant log output

Example tail of reasoning_content at a cut (budget 8000, 1484 reasoning tokens):

r = 4.0767416621f * l - 3.3077115913f * m + 0.2309699292f * s
g = -... reasoning budget exceeded, need to answer.\n
Vorherrschende Sprache
C++
Sterne
1.2k
Forks
80
Ø Merge
4 T. 20 Std.
Gemergte PRs (30 T.)
2

Entwicklungsumgebung

Dieses Projekt bietet weder Dev-Container noch Dockerfile noch Beitragsleitfaden – die Einrichtung liegt bei Ihnen. Beginnen Sie mit der README; die allgemeinen Schritte stehen in unserem Leitfaden für den ersten Beitrag.

Erste Schritte

  1. Lesen Sie das ganze Issue und danach den Beitragsleitfaden des Projekts.
  2. Schreiben Sie ins Issue, dass Sie es übernehmen — das erspart doppelte Arbeit.
  3. Forken Sie das Repository und arbeiten Sie in einem Branch.
  4. Öffnen Sie einen Pull Request, der die Issue-Nummer nennt.

Mehr aus Anbeeld/beellama.cpp

Alle Issues in Anbeeld/beellama.cpp

Ähnliche Issues

Weitere Issues zu C++

Neue Issues direkt in Ihr Postfach

Eine kurze Übersicht über anfängerfreundliche GitHub-Issues.