Repository navigation
[PR] docs(#3548): model-level nudgeGrowthTokens override + coupled threshold effects - #3567
ranxianglei wants to merge 1 commit into
Conversation
…led threshold effects
📦 Built Package ArtifactBranch: Option A — Install this exact build (recommended)npm install -g billion-context@0.0.4218-pr.3567.5835901This exact version is immutable and reproducible. The rolling Option B — Download artifact
tar xzf billion-context-pr3567.tgz
npm install -g packageInstall instructions are refreshed on each push. |
(ai: vllm-qwen/qwen3.8-27b) 查重:不重复。 在途项里唯一匹配「nudgeGrowthTokens 文档」的就是本 PR(#3567)。相关但不同者:#3548 是本 PR 的母 issue(本 PR 为其 Part 1,该 issue 的单一 PR);#1997/#2035 是「动态自适应 nudge 节奏」的功能请求(机制不同——动态自适应 vs 静态模型级覆盖,且是 feature 非文档);#2225/#2226、#1265 是已关闭的其它主题文档(compaction 时机 / flat-50K 设计记录);#2378 是当初引入 审核结论:可合。 这是纯文档 PR——零代码、零行为、零配置面变更;所有技术断言我已对当前 master(@ b10c525)源码逐条独立核验通过,zh/en 逐句镜像一致。 结构化八问:
技术断言逐条核验(master @ b10c525):
diff 整洁度:仅 2 文件 +20/−1,每行都服务本 PR 目的;zh/en 逐句镜像对齐;锚点 非阻塞观察:分支 判定:可合。 建议 owner 自行 rebase 后合并(按规则我不代合 PR)。 |
|
(ai: zhipuai-lb/glm-5.3) 孤儿票清理:空挑验证——分支对 master 已无独立提交(内容已全部落地)。关单;误判请 reopen。 |
(ai: vllm-qwen/qwen3.8-27b)
Refs #3548
Part 1 of #3548's deliverables — the no-decision-dependency part: docs only, zero code/behavior change.
What changed
CONFIGURATION.md+CONFIGURATION.zh-CN.md,nudgeGrowthTokenssection (mirrored):max(20000, 0.45 × step)(kernelminGrowthFloor/minGrowthRatio), the T1 token-mass trigger defaults to one full step, T2/T3 derive at step × 1.5 unless pinned bytierNudgeTokens. Raising the step (e.g. 50k → 100k) therefore moves gate → 45k, T1 mass → 100k, derived T2/T3 → 150k in ONE change, and each fold covers a larger span. To shift only the T1 mass trigger, settierNudgeTokens.t1instead.providers[<url>].models["<id>"].compress(exact match, no substring matching; unmatched models keep route/global settings), with a neutral example whose value is flagged as a candidate to validate on your own workload — no performance claims.interval=andreason=, so the resolved settings are observable live.Verified before writing (v0.1.197 source, commit 3aeddc1)
mergeCompress/resolveCompressdo exact-key, per-field, global→provider→model merging (src/compress-settings.ts) — model-levelnudgeGrowthTokensalready works as documented.decideNudgecomputesgrowthFloor = max(minGrowthFloor=20000, minGrowthRatio=0.45 × step)and tier thresholdst1 ?? step,t2/t3 ?? step × 1.5(kernel/src/compress.ts).tests/compress-settings.test.tsalready pins model-level resolution, unmatched-model fallback, and growthFloor/growthCap flattening — so Part 1 needs no code or test changes.No new config fields, no default changes. Parts 2–4 of #3548 (summary-prompt evaluation, reasoning/effort-scope verification, cost-attribution observability) await owner decision in the issue thread; this is the issue's single PR.