mirror of
https://github.com/shareAI-lab/analysis_claude_code.git
synced 2026-09-20 12:13:38 +08:00
feat: refresh context compaction lesson
This commit is contained in:
Haoran
@@ -11,13 +11,13 @@
|
||||
<rect width="720" height="400" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L4: autoCompact — LLM Full Summary</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 4: compact_history, Summarize History</text>
|
||||
|
||||
<!-- Trigger Condition -->
|
||||
<rect x="20" y="54" width="680" height="44" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
<text x="35" y="70" fill="#991b1b" font-size="11" font-weight="600">Trigger Condition</text>
|
||||
<text x="140" y="70" fill="#991b1b" font-size="11">All three preprocessing layers have run, estimated tokens > contextWindow - maxOutputTokens - 13_000.</text>
|
||||
<text x="140" y="86" fill="#991b1b" font-size="10">Tries sessionMemoryCompact first (lightweight summary from existing memory), only calls LLM if insufficient.</text>
|
||||
<text x="140" y="70" fill="#991b1b" font-size="11">After Steps 1–3, estimate_size(messages) > CONTEXT_LIMIT.</text>
|
||||
<text x="140" y="86" fill="#991b1b" font-size="10">The current CONTEXT_LIMIT is 50,000 characters.</text>
|
||||
|
||||
<!-- Steps -->
|
||||
<rect x="20" y="106" width="200" height="110" rx="8" fill="#fff" stroke="#94a3b8" stroke-width="1.5"/>
|
||||
@@ -30,21 +30,21 @@
|
||||
<line x1="225" y1="161" x2="265" y2="161" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="270" y="106" width="200" height="110" rx="8" fill="#fff" stroke="#94a3b8" stroke-width="1.5"/>
|
||||
<text x="370" y="130" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">Step 2: LLM generates summary</text>
|
||||
<text x="290" y="152" fill="#475569" font-size="10">Send conversation history to LLM</text>
|
||||
<text x="290" y="166" fill="#475569" font-size="9">Summary must include 9 sections:</text>
|
||||
<text x="370" y="180" fill="#94a3b8" font-size="8" text-anchor="middle">request · concepts · files · errors</text>
|
||||
<text x="370" y="192" fill="#94a3b8" font-size="8" text-anchor="middle">resolutions · user messages · todos</text>
|
||||
<text x="370" y="204" fill="#94a3b8" font-size="8" text-anchor="middle">current state · next steps</text>
|
||||
<text x="370" y="130" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">Step 2: Factual summary</text>
|
||||
<text x="370" y="152" fill="#475569" font-size="9" text-anchor="middle">Conversation is untrusted data</text>
|
||||
<text x="290" y="166" fill="#475569" font-size="9">Summary preserves 5 categories:</text>
|
||||
<text x="370" y="180" fill="#94a3b8" font-size="8" text-anchor="middle">goal · findings and decisions · files</text>
|
||||
<text x="370" y="192" fill="#94a3b8" font-size="8" text-anchor="middle">remaining work · user constraints</text>
|
||||
<text x="370" y="204" fill="#94a3b8" font-size="8" text-anchor="middle">do not propose or select an action</text>
|
||||
|
||||
<line x1="475" y1="161" x2="515" y2="161" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="520" y="106" width="180" height="110" rx="8" fill="#fef2f2" stroke="#dc2626" stroke-width="2"/>
|
||||
<text x="610" y="130" fill="#991b1b" font-size="12" font-weight="700" text-anchor="middle">Step 3: Replace message list</text>
|
||||
<text x="540" y="152" fill="#991b1b" font-size="10">All old messages → 1 summary</text>
|
||||
<text x="540" y="168" fill="#991b1b" font-size="10">Model continues from summary</text>
|
||||
<text x="540" y="184" fill="#991b1b" font-size="10">Includes recently_read file list</text>
|
||||
<text x="540" y="200" fill="#ef4444" font-size="9">⚠ This is an irreversible operation</text>
|
||||
<text x="610" y="130" fill="#991b1b" font-size="12" font-weight="700" text-anchor="middle">Step 3: Replace history</text>
|
||||
<text x="610" y="152" fill="#991b1b" font-size="9" text-anchor="middle">Old history → 1 message</text>
|
||||
<text x="610" y="168" fill="#991b1b" font-size="9" text-anchor="middle">Request + reference state</text>
|
||||
<text x="610" y="184" fill="#991b1b" font-size="9" text-anchor="middle">System separates instructions/data</text>
|
||||
<text x="610" y="200" fill="#ef4444" font-size="9" text-anchor="middle">Transcript remains on disk</text>
|
||||
|
||||
<!-- Before/After comparison -->
|
||||
<rect x="20" y="234" width="320" height="94" rx="6" fill="#fff" stroke="#94a3b8" stroke-width="1"/>
|
||||
@@ -54,19 +54,19 @@
|
||||
<rect x="149" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="154" y="276" fill="#475569" font-size="8">user</text>
|
||||
<rect x="206" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="211" y="276" fill="#475569" font-size="8">assistant</text>
|
||||
<rect x="263" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="268" y="276" fill="#475569" font-size="8">user</text>
|
||||
<text x="180" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">~180 messages, occupying 62K tokens</text>
|
||||
<text x="180" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">Many messages, estimated size > 50,000</text>
|
||||
|
||||
<line x1="345" y1="281" x2="375" y2="281" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="380" y="234" width="320" height="94" rx="6" fill="#fef2f2" stroke="#dc2626" stroke-width="1"/>
|
||||
<text x="540" y="256" fill="#991b1b" font-size="11" font-weight="600" text-anchor="middle">After messages</text>
|
||||
<rect x="395" y="264" width="290" height="32" rx="4" fill="#fee2e2" stroke="#fca5a5" stroke-width="0.5"/>
|
||||
<text x="540" y="276" fill="#991b1b" font-size="9" text-anchor="middle">[Compacted] Summary: goal → create hello.py ...</text>
|
||||
<text x="540" y="290" fill="#991b1b" font-size="9" text-anchor="middle">Recent files: hello.py, README.md ...</text>
|
||||
<text x="540" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">~1 message, occupying 1K tokens</text>
|
||||
<text x="540" y="276" fill="#991b1b" font-size="9" text-anchor="middle">Authoritative request: captured at input</text>
|
||||
<text x="540" y="290" fill="#991b1b" font-size="9" text-anchor="middle">Reference state: untrusted factual summary</text>
|
||||
<text x="540" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">One summary message, well below the limit</text>
|
||||
|
||||
<!-- Circuit breaker -->
|
||||
<!-- Error recovery -->
|
||||
<rect x="20" y="340" width="680" height="36" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="362" fill="#475569" font-size="11" font-weight="600">Circuit breaker:</text>
|
||||
<text x="130" y="362" fill="#475569" font-size="10">3 consecutive autocompact failures → stop retrying. Prevents wasting API calls when context is unrecoverable.</text>
|
||||
<text x="35" y="362" fill="#475569" font-size="11" font-weight="600">Error recovery:</text>
|
||||
<text x="125" y="362" fill="#475569" font-size="10">If the API still returns prompt_too_long, run reactive_compact and retry only once.</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 5.7 KiB After Width: | Height: | Size: 5.7 KiB |
@@ -11,13 +11,13 @@
|
||||
<rect width="720" height="400" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L4: autoCompact — LLM 完全要約</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 4: compact_history、履歴を要約</text>
|
||||
|
||||
<!-- トリガー条件 -->
|
||||
<rect x="20" y="54" width="680" height="44" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
<text x="35" y="70" fill="#991b1b" font-size="11" font-weight="600">トリガー条件</text>
|
||||
<text x="115" y="70" fill="#991b1b" font-size="11">前 3 層の前処理を全て実行後、推定 token > contextWindow - maxOutputTokens - 13_000。</text>
|
||||
<text x="115" y="86" fill="#991b1b" font-size="10">まず sessionMemoryCompact を試行（既存のメモリで軽量要約）、不足時のみ LLM を呼び出し。</text>
|
||||
<text x="115" y="70" fill="#991b1b" font-size="11">Step 1～3 の後、estimate_size(messages) > CONTEXT_LIMIT。</text>
|
||||
<text x="115" y="86" fill="#991b1b" font-size="10">現在の CONTEXT_LIMIT は 50,000 文字。</text>
|
||||
|
||||
<!-- ステップ -->
|
||||
<rect x="20" y="106" width="200" height="110" rx="8" fill="#fff" stroke="#94a3b8" stroke-width="1.5"/>
|
||||
@@ -30,21 +30,21 @@
|
||||
<line x1="225" y1="161" x2="265" y2="161" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="270" y="106" width="200" height="110" rx="8" fill="#fff" stroke="#94a3b8" stroke-width="1.5"/>
|
||||
<text x="370" y="130" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">ステップ 2：LLM 要約生成</text>
|
||||
<text x="290" y="152" fill="#475569" font-size="10">対話履歴を LLM に送信</text>
|
||||
<text x="290" y="166" fill="#475569" font-size="9">要約は 9 つのセクションを含む：</text>
|
||||
<text x="290" y="180" fill="#94a3b8" font-size="8">リクエスト・概念・ファイル・エラー・解決</text>
|
||||
<text x="290" y="192" fill="#94a3b8" font-size="8">ユーザーメッセージ・TODO・現在・次ステップ</text>
|
||||
<text x="290" y="206" fill="#94a3b8" font-size="9">1 回のみ生成</text>
|
||||
<text x="370" y="130" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">ステップ 2：事実要約</text>
|
||||
<text x="370" y="152" fill="#475569" font-size="9" text-anchor="middle">元の対話は信頼しないデータ</text>
|
||||
<text x="290" y="166" fill="#475569" font-size="9">要約は 5 種類の情報を保持：</text>
|
||||
<text x="290" y="180" fill="#94a3b8" font-size="8">目標・発見と判断・関連ファイル</text>
|
||||
<text x="290" y="192" fill="#94a3b8" font-size="8">残作業・ユーザー制約</text>
|
||||
<text x="290" y="206" fill="#94a3b8" font-size="9">行動を提案・選択しない</text>
|
||||
|
||||
<line x1="475" y1="161" x2="515" y2="161" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="520" y="106" width="180" height="110" rx="8" fill="#fef2f2" stroke="#dc2626" stroke-width="2"/>
|
||||
<text x="610" y="130" fill="#991b1b" font-size="12" font-weight="700" text-anchor="middle">ステップ 3：要約に置換</text>
|
||||
<text x="540" y="152" fill="#991b1b" font-size="10">全旧メッセージ → 1 件の要約に</text>
|
||||
<text x="540" y="168" fill="#991b1b" font-size="10">モデルは要約から作業を継続</text>
|
||||
<text x="540" y="184" fill="#991b1b" font-size="10">recently_read を添付</text>
|
||||
<text x="540" y="200" fill="#ef4444" font-size="9">⚠ これは復元不可能な操作</text>
|
||||
<text x="610" y="130" fill="#991b1b" font-size="12" font-weight="700" text-anchor="middle">ステップ 3：履歴置換</text>
|
||||
<text x="610" y="152" fill="#991b1b" font-size="9" text-anchor="middle">旧履歴 → 1 件の圧縮</text>
|
||||
<text x="610" y="168" fill="#991b1b" font-size="9" text-anchor="middle">要求と参照状態を分離</text>
|
||||
<text x="610" y="184" fill="#991b1b" font-size="8" text-anchor="middle">system が指示とデータを区別</text>
|
||||
<text x="610" y="200" fill="#ef4444" font-size="9" text-anchor="middle">transcript はディスクに保持</text>
|
||||
|
||||
<!-- 圧縮前/後 比較 -->
|
||||
<rect x="20" y="234" width="320" height="94" rx="6" fill="#fff" stroke="#94a3b8" stroke-width="1"/>
|
||||
@@ -54,19 +54,19 @@
|
||||
<rect x="149" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="154" y="276" fill="#475569" font-size="8">user</text>
|
||||
<rect x="206" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="211" y="276" fill="#475569" font-size="8">assistant</text>
|
||||
<rect x="263" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="268" y="276" fill="#475569" font-size="8">user</text>
|
||||
<text x="180" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">~180 件のメッセージ、62K トークンを占有</text>
|
||||
<text x="180" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">多数のメッセージ、推定 size > 50,000</text>
|
||||
|
||||
<line x1="345" y1="281" x2="375" y2="281" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="380" y="234" width="320" height="94" rx="6" fill="#fef2f2" stroke="#dc2626" stroke-width="1"/>
|
||||
<text x="540" y="256" fill="#991b1b" font-size="11" font-weight="600" text-anchor="middle">圧縮後 messages</text>
|
||||
<rect x="395" y="264" width="290" height="32" rx="4" fill="#fee2e2" stroke="#fca5a5" stroke-width="0.5"/>
|
||||
<text x="540" y="276" fill="#991b1b" font-size="9" text-anchor="middle">[Compacted] 要約：目標 → hello.py を作成 ...</text>
|
||||
<text x="540" y="290" fill="#991b1b" font-size="9" text-anchor="middle">最近のファイル：hello.py, README.md ...</text>
|
||||
<text x="540" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">~1 件のメッセージ、1K トークンを占有</text>
|
||||
<text x="540" y="276" fill="#991b1b" font-size="9" text-anchor="middle">Authoritative request：入力時に取得した要求</text>
|
||||
<text x="540" y="290" fill="#991b1b" font-size="9" text-anchor="middle">Reference state：信頼しない事実要約</text>
|
||||
<text x="540" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">1 件の要約メッセージ、上限を下回る</text>
|
||||
|
||||
<!-- サーキットブレーカー -->
|
||||
<!-- エラー回復 -->
|
||||
<rect x="20" y="340" width="680" height="36" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="362" fill="#475569" font-size="11" font-weight="600">サーキットブレーカー：</text>
|
||||
<text x="145" y="362" fill="#475569" font-size="10">autocompact が連続 3 回失敗 → リトライ停止。コンテキストが復元不可能な場合の API 呼び出しの無駄な反復を防止。</text>
|
||||
<text x="35" y="362" fill="#475569" font-size="11" font-weight="600">エラー回復：</text>
|
||||
<text x="115" y="362" fill="#475569" font-size="10">API が prompt_too_long を返したら reactive_compact を実行し、1 回だけ再試行。</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 5.9 KiB After Width: | Height: | Size: 5.7 KiB |
@@ -11,40 +11,40 @@
|
||||
<rect width="720" height="400" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L4: autoCompact — LLM 全量摘要</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 4: compact_history，生成历史摘要</text>
|
||||
|
||||
<!-- 触发条件 -->
|
||||
<rect x="20" y="54" width="680" height="44" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
<text x="35" y="70" fill="#991b1b" font-size="11" font-weight="600">触发条件</text>
|
||||
<text x="105" y="70" fill="#991b1b" font-size="11">前三层预处理全跑完，估算 token > contextWindow - maxOutputTokens - 13_000。</text>
|
||||
<text x="105" y="86" fill="#991b1b" font-size="10">先尝试 sessionMemoryCompact（用已有记忆做轻量摘要），不足才调 LLM。</text>
|
||||
<text x="105" y="70" fill="#991b1b" font-size="11">前三步执行后，estimate_size(messages) > CONTEXT_LIMIT。</text>
|
||||
<text x="105" y="86" fill="#991b1b" font-size="10">当前实现的 CONTEXT_LIMIT 为 50,000 个字符。</text>
|
||||
|
||||
<!-- 步骤 -->
|
||||
<rect x="20" y="106" width="200" height="110" rx="8" fill="#fff" stroke="#94a3b8" stroke-width="1.5"/>
|
||||
<text x="120" y="130" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">步骤 1：保存 transcript</text>
|
||||
<text x="40" y="152" fill="#475569" font-size="10">完整对话写入 .transcripts/</text>
|
||||
<text x="40" y="168" fill="#475569" font-size="10">JSONL 格式，一行一条消息</text>
|
||||
<text x="40" y="184" fill="#475569" font-size="10">文件名：transcript_{timestamp}.jsonl</text>
|
||||
<text x="40" y="184" fill="#475569" font-size="10">文件名：transcript_{time}.jsonl</text>
|
||||
<text x="40" y="200" fill="#94a3b8" font-size="9">信息没有丢失，只是移出活跃区</text>
|
||||
|
||||
<line x1="225" y1="161" x2="265" y2="161" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="270" y="106" width="200" height="110" rx="8" fill="#fff" stroke="#94a3b8" stroke-width="1.5"/>
|
||||
<text x="370" y="130" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">步骤 2：LLM 生成摘要</text>
|
||||
<text x="290" y="152" fill="#475569" font-size="10">把对话历史发给 LLM</text>
|
||||
<text x="290" y="166" fill="#475569" font-size="9">摘要需包含 9 个部分：</text>
|
||||
<text x="290" y="180" fill="#94a3b8" font-size="8">请求·概念·文件·错误·解决</text>
|
||||
<text x="290" y="192" fill="#94a3b8" font-size="8">用户消息·待办·当前·下一步</text>
|
||||
<text x="290" y="206" fill="#94a3b8" font-size="9">只生成一次</text>
|
||||
<text x="370" y="130" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">步骤 2：生成事实摘要</text>
|
||||
<text x="370" y="152" fill="#475569" font-size="9" text-anchor="middle">原对话是不可信数据</text>
|
||||
<text x="290" y="166" fill="#475569" font-size="9">摘要保留 5 类信息：</text>
|
||||
<text x="290" y="180" fill="#94a3b8" font-size="8">目标·发现与决定·相关文件</text>
|
||||
<text x="290" y="192" fill="#94a3b8" font-size="8">剩余工作·用户约束</text>
|
||||
<text x="290" y="206" fill="#94a3b8" font-size="9">不提出或选择后续动作</text>
|
||||
|
||||
<line x1="475" y1="161" x2="515" y2="161" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="520" y="106" width="180" height="110" rx="8" fill="#fef2f2" stroke="#dc2626" stroke-width="2"/>
|
||||
<text x="610" y="130" fill="#991b1b" font-size="12" font-weight="700" text-anchor="middle">步骤 3：替换消息列表</text>
|
||||
<text x="540" y="152" fill="#991b1b" font-size="10">所有旧消息 → 1 条摘要</text>
|
||||
<text x="540" y="168" fill="#991b1b" font-size="10">模型从摘要继续工作</text>
|
||||
<text x="540" y="184" fill="#991b1b" font-size="10">附带 recently_read 文件列表</text>
|
||||
<text x="540" y="200" fill="#ef4444" font-size="9">⚠ 这是无法恢复的操作</text>
|
||||
<text x="610" y="130" fill="#991b1b" font-size="12" font-weight="700" text-anchor="middle">步骤 3：替换历史</text>
|
||||
<text x="610" y="152" fill="#991b1b" font-size="9" text-anchor="middle">旧历史 → 1 条压缩消息</text>
|
||||
<text x="610" y="168" fill="#991b1b" font-size="9" text-anchor="middle">用户要求与参考状态分开</text>
|
||||
<text x="610" y="184" fill="#991b1b" font-size="9" text-anchor="middle">system 区分指令与数据</text>
|
||||
<text x="610" y="200" fill="#ef4444" font-size="9" text-anchor="middle">完整 transcript 保留在磁盘</text>
|
||||
|
||||
<!-- Before/After 对比 -->
|
||||
<rect x="20" y="234" width="320" height="94" rx="6" fill="#fff" stroke="#94a3b8" stroke-width="1"/>
|
||||
@@ -54,19 +54,19 @@
|
||||
<rect x="149" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="154" y="276" fill="#475569" font-size="8">user</text>
|
||||
<rect x="206" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="211" y="276" fill="#475569" font-size="8">assistant</text>
|
||||
<rect x="263" y="264" width="52" height="16" rx="3" fill="#e2e8f0"/><text x="268" y="276" fill="#475569" font-size="8">user</text>
|
||||
<text x="180" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">~180 条消息，占 62K token</text>
|
||||
<text x="180" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">多条消息，估算 size > 50,000</text>
|
||||
|
||||
<line x1="345" y1="281" x2="375" y2="281" stroke="#dc2626" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
|
||||
<rect x="380" y="234" width="320" height="94" rx="6" fill="#fef2f2" stroke="#dc2626" stroke-width="1"/>
|
||||
<text x="540" y="256" fill="#991b1b" font-size="11" font-weight="600" text-anchor="middle">压缩后 messages</text>
|
||||
<rect x="395" y="264" width="290" height="32" rx="4" fill="#fee2e2" stroke="#fca5a5" stroke-width="0.5"/>
|
||||
<text x="540" y="276" fill="#991b1b" font-size="9" text-anchor="middle">[Compacted] 摘要：目标 → 创建 hello.py ...</text>
|
||||
<text x="540" y="290" fill="#991b1b" font-size="9" text-anchor="middle">最近文件：hello.py, README.md ...</text>
|
||||
<text x="540" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">~1 条消息，占 1K token</text>
|
||||
<text x="540" y="276" fill="#991b1b" font-size="9" text-anchor="middle">Authoritative request：入口捕获的用户要求</text>
|
||||
<text x="540" y="290" fill="#991b1b" font-size="9" text-anchor="middle">Reference state：不可信的事实摘要</text>
|
||||
<text x="540" y="318" fill="#94a3b8" font-size="9" text-anchor="middle">1 条摘要消息，显著低于阈值</text>
|
||||
|
||||
<!-- 熔断器 -->
|
||||
<!-- 错误后补救 -->
|
||||
<rect x="20" y="340" width="680" height="36" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="362" fill="#475569" font-size="11" font-weight="600">熔断器：</text>
|
||||
<text x="95" y="362" fill="#475569" font-size="10">连续 autocompact 失败 3 次 → 停止重试。防止上下文不可恢复时反复浪费 API 调用。</text>
|
||||
<text x="35" y="362" fill="#475569" font-size="11" font-weight="600">错误后补救：</text>
|
||||
<text x="115" y="362" fill="#475569" font-size="10">API 仍返回 prompt_too_long 时执行 reactive_compact，并且只重试 1 次。</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 5.6 KiB After Width: | Height: | Size: 5.6 KiB |
@@ -27,7 +27,7 @@
|
||||
<!-- Title -->
|
||||
<rect x="0" y="0" width="820" height="48" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="40" width="820" height="8" fill="url(#header)"/>
|
||||
<text x="410" y="31" fill="#fff" font-size="16" font-weight="700" text-anchor="middle">Context Compact — Compression Before LLM Call, Three Trigger Modes</text>
|
||||
<text x="410" y="31" fill="#fff" font-size="16" font-weight="700" text-anchor="middle">Context Compact: Compression Before LLM Calls, Three Triggers</text>
|
||||
|
||||
<!-- Labels -->
|
||||
<text x="50" y="74" fill="#94a3b8" font-size="11" font-weight="600">s07 Preserved</text>
|
||||
@@ -50,13 +50,13 @@
|
||||
<text x="270" y="122" fill="#92400e" font-size="8" font-weight="700" text-anchor="middle">① Every Turn · Unconditional · 0 API</text>
|
||||
|
||||
<rect x="186" y="130" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="146" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L3 tool_result_budget</text>
|
||||
<text x="270" y="146" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 1 tool_result_budget</text>
|
||||
|
||||
<rect x="186" y="158" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="174" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L1 snip_compact</text>
|
||||
<text x="270" y="174" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 2 snip_compact</text>
|
||||
|
||||
<rect x="186" y="186" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="202" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L2 micro_compact</text>
|
||||
<text x="270" y="202" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 3 micro_compact</text>
|
||||
|
||||
<!-- ↓ → ◇ -->
|
||||
<line x1="270" y1="210" x2="270" y2="222" stroke="#555" stroke-width="1.2" marker-end="url(#arrow)"/>
|
||||
@@ -74,10 +74,10 @@
|
||||
|
||||
<!-- ── ② Conditional Trigger ── -->
|
||||
<rect x="186" y="268" width="168" height="16" rx="3" fill="#fed7aa" stroke="#ea580c" stroke-width="0.8"/>
|
||||
<text x="270" y="280" fill="#9a3412" font-size="8" font-weight="700" text-anchor="middle">② Conditional · Token Over Threshold · 1 API</text>
|
||||
<text x="270" y="280" fill="#9a3412" font-size="8" font-weight="700" text-anchor="middle">② Conditional · Size Over Limit · 1 API</text>
|
||||
|
||||
<rect x="186" y="288" width="168" height="24" rx="4" fill="#fed7aa" stroke="#ea580c" stroke-width="1"/>
|
||||
<text x="270" y="304" fill="#9a3412" font-size="10" font-weight="600" text-anchor="middle">L4 compact_history</text>
|
||||
<text x="270" y="304" fill="#9a3412" font-size="10" font-weight="600" text-anchor="middle">Step 4 compact_history</text>
|
||||
|
||||
<!-- Pipeline exit → LLM -->
|
||||
<line x1="370" y1="158" x2="438" y2="158" stroke="#2563eb" stroke-width="2" marker-end="url(#arrow-blue)"/>
|
||||
@@ -113,7 +113,7 @@
|
||||
<rect x="580" y="210" width="170" height="56" rx="6" fill="#fef2f2" stroke="#dc2626" stroke-width="1" stroke-dasharray="4,2"/>
|
||||
<text x="665" y="228" fill="#991b1b" font-size="9" font-weight="700" text-anchor="middle">③ Emergency Trigger</text>
|
||||
<text x="665" y="242" fill="#991b1b" font-size="8" text-anchor="middle">API returns prompt_too_long</text>
|
||||
<text x="665" y="256" fill="#991b1b" font-size="8" text-anchor="middle">→ reactive_compact → retry</text>
|
||||
<text x="665" y="256" fill="#991b1b" font-size="8" text-anchor="middle">→ reactive_compact → retry once</text>
|
||||
|
||||
<!-- ===== Loop Back ===== -->
|
||||
<path d="M 710 158 L 760 158 L 760 348 L 90 348 L 90 184" fill="none" stroke="#555" stroke-width="2" marker-end="url(#arrow)" stroke-dasharray="6,3"/>
|
||||
@@ -126,13 +126,13 @@
|
||||
<text x="94" y="414" fill="#334155" font-size="10">s07 Preserved: loop, hooks, skill loading, sub-agents</text>
|
||||
|
||||
<rect x="70" y="426" width="16" height="12" rx="3" fill="#fde68a" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="94" y="436" fill="#334155" font-size="10">① Every Turn Auto: L3→L1→L2 run unconditionally before each LLM call, 0 API</text>
|
||||
<text x="94" y="436" fill="#334155" font-size="10">① Every Turn: Steps 1→2→3 run before each LLM call, 0 API</text>
|
||||
|
||||
<rect x="70" y="448" width="16" height="12" rx="3" fill="#fed7aa" stroke="#ea580c" stroke-width="1"/>
|
||||
<text x="94" y="458" fill="#334155" font-size="10">② Conditional: after L3/L1/L2, tokens still over threshold → compact_history, 1 API</text>
|
||||
<text x="94" y="458" fill="#334155" font-size="10">② Conditional: size remains over the limit after Step 3 → compact_history, 1 API</text>
|
||||
|
||||
<rect x="70" y="470" width="16" height="12" rx="3" fill="#fef2f2" stroke="#dc2626" stroke-width="1" stroke-dasharray="3,2"/>
|
||||
<text x="94" y="480" fill="#334155" font-size="10">③ Emergency: API returns prompt_too_long → reactive_compact → retry</text>
|
||||
<text x="94" y="480" fill="#334155" font-size="10">③ Recovery: API returns prompt_too_long → reactive_compact → retry once</text>
|
||||
|
||||
<text x="70" y="498" fill="#94a3b8" font-size="9">Three modes with increasing cost: 0 API → 1 API → 1 API + more aggressive trimming</text>
|
||||
<text x="70" y="498" fill="#94a3b8" font-size="9">Increasing cost: 0 API → one summary call → one summary call and retry</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 9.0 KiB After Width: | Height: | Size: 9.0 KiB |
@@ -27,7 +27,7 @@
|
||||
<!-- タイトル -->
|
||||
<rect x="0" y="0" width="820" height="48" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="40" width="820" height="8" fill="url(#header)"/>
|
||||
<text x="410" y="31" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Context Compact — LLM 呼び出し前に圧縮、3 つのトリガーモード</text>
|
||||
<text x="410" y="31" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Context Compact：LLM 呼び出し前の圧縮と 3 つのトリガー</text>
|
||||
|
||||
<!-- ラベル -->
|
||||
<text x="50" y="74" fill="#94a3b8" font-size="11" font-weight="600">s07 保持</text>
|
||||
@@ -50,20 +50,20 @@
|
||||
<text x="270" y="122" fill="#92400e" font-size="8" font-weight="700" text-anchor="middle">① 毎ターン自動 · 無条件 · 0 API</text>
|
||||
|
||||
<rect x="186" y="130" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="146" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L3 tool_result_budget</text>
|
||||
<text x="270" y="146" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 1 tool_result_budget</text>
|
||||
|
||||
<rect x="186" y="158" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="174" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L1 snip_compact</text>
|
||||
<text x="270" y="174" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 2 snip_compact</text>
|
||||
|
||||
<rect x="186" y="186" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="202" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L2 micro_compact</text>
|
||||
<text x="270" y="202" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 3 micro_compact</text>
|
||||
|
||||
<!-- ↓ → ◇ -->
|
||||
<line x1="270" y1="210" x2="270" y2="222" stroke="#555" stroke-width="1.2" marker-end="url(#arrow)"/>
|
||||
|
||||
<!-- ◇ 判定ダイヤモンド -->
|
||||
<polygon points="270,226 300,244 270,262 240,244" fill="#f0f4ff" stroke="#ea580c" stroke-width="1.5"/>
|
||||
<text x="270" y="247" fill="#9a3412" font-size="7" font-weight="600" text-anchor="middle">閾値超過?</text>
|
||||
<text x="270" y="247" fill="#9a3412" font-size="7" font-weight="600" text-anchor="middle">推定値超過?</text>
|
||||
|
||||
<!-- いいえ：右側注釈 -->
|
||||
<text x="306" y="240" fill="#16a34a" font-size="9" font-weight="700">No → 通過</text>
|
||||
@@ -74,10 +74,10 @@
|
||||
|
||||
<!-- ── ② 条件トリガー ── -->
|
||||
<rect x="186" y="268" width="168" height="16" rx="3" fill="#fed7aa" stroke="#ea580c" stroke-width="0.8"/>
|
||||
<text x="270" y="280" fill="#9a3412" font-size="8" font-weight="700" text-anchor="middle">② 条件 · トークン閾値超過 · 1 API</text>
|
||||
<text x="270" y="280" fill="#9a3412" font-size="8" font-weight="700" text-anchor="middle">② 条件 · サイズ上限超過 · 1 API</text>
|
||||
|
||||
<rect x="186" y="288" width="168" height="24" rx="4" fill="#fed7aa" stroke="#ea580c" stroke-width="1"/>
|
||||
<text x="270" y="304" fill="#9a3412" font-size="10" font-weight="600" text-anchor="middle">L4 compact_history</text>
|
||||
<text x="270" y="304" fill="#9a3412" font-size="10" font-weight="600" text-anchor="middle">Step 4 compact_history</text>
|
||||
|
||||
<!-- パイプライン出口 → LLM -->
|
||||
<line x1="370" y1="158" x2="438" y2="158" stroke="#2563eb" stroke-width="2" marker-end="url(#arrow-blue)"/>
|
||||
@@ -113,7 +113,7 @@
|
||||
<rect x="580" y="210" width="170" height="56" rx="6" fill="#fef2f2" stroke="#dc2626" stroke-width="1" stroke-dasharray="4,2"/>
|
||||
<text x="665" y="228" fill="#991b1b" font-size="9" font-weight="700" text-anchor="middle">③ 緊急トリガー</text>
|
||||
<text x="665" y="242" fill="#991b1b" font-size="8" text-anchor="middle">API が prompt_too_long を返す</text>
|
||||
<text x="665" y="256" fill="#991b1b" font-size="8" text-anchor="middle">→ reactive_compact → リトライ</text>
|
||||
<text x="665" y="256" fill="#991b1b" font-size="8" text-anchor="middle">→ reactive_compact → 1 回リトライ</text>
|
||||
|
||||
<!-- ===== ループバック ===== -->
|
||||
<path d="M 710 158 L 760 158 L 760 348 L 90 348 L 90 184" fill="none" stroke="#555" stroke-width="2" marker-end="url(#arrow)" stroke-dasharray="6,3"/>
|
||||
@@ -126,13 +126,13 @@
|
||||
<text x="94" y="414" fill="#334155" font-size="10">s07 保持：ループ、フック、スキルロード、サブエージェント</text>
|
||||
|
||||
<rect x="70" y="426" width="16" height="12" rx="3" fill="#fde68a" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="94" y="436" fill="#334155" font-size="10">① 毎ターン自動：L3→L1→L2 が各 LLM 呼び出し前に無条件実行、0 API</text>
|
||||
<text x="94" y="436" fill="#334155" font-size="10">① 毎ターン：Step 1→2→3 を各 LLM 呼び出し前に実行、0 API</text>
|
||||
|
||||
<rect x="70" y="448" width="16" height="12" rx="3" fill="#fed7aa" stroke="#ea580c" stroke-width="1"/>
|
||||
<text x="94" y="458" fill="#334155" font-size="10">② 条件トリガー：L3/L1/L2 後もトークン超過 → compact_history、1 API</text>
|
||||
<text x="94" y="458" fill="#334155" font-size="10">② 条件：Step 3 後もサイズ上限超過 → compact_history、1 API</text>
|
||||
|
||||
<rect x="70" y="470" width="16" height="12" rx="3" fill="#fef2f2" stroke="#dc2626" stroke-width="1" stroke-dasharray="3,2"/>
|
||||
<text x="94" y="480" fill="#334155" font-size="10">③ 緊急トリガー：API が prompt_too_long を返す → reactive_compact → リトライ</text>
|
||||
<text x="94" y="480" fill="#334155" font-size="10">③ 回復：API が prompt_too_long を返す → reactive_compact → 1 回リトライ</text>
|
||||
|
||||
<text x="70" y="498" fill="#94a3b8" font-size="9">3 つのモードはコスト増加：0 API → 1 API → 1 API + より積極的なトリム</text>
|
||||
<text x="70" y="498" fill="#94a3b8" font-size="9">コストは順に増加：0 API → 1 回の要約 → 1 回の要約とリトライ</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 9.2 KiB After Width: | Height: | Size: 9.1 KiB |
@@ -27,7 +27,7 @@
|
||||
<!-- 标题 -->
|
||||
<rect x="0" y="0" width="820" height="48" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="40" width="820" height="8" fill="url(#header)"/>
|
||||
<text x="410" y="31" fill="#fff" font-size="16" font-weight="700" text-anchor="middle">Context Compact — 压缩插在 LLM 调用前，三种触发模式</text>
|
||||
<text x="410" y="31" fill="#fff" font-size="16" font-weight="700" text-anchor="middle">Context Compact：LLM 调用前压缩，三种触发方式</text>
|
||||
|
||||
<!-- 标签 -->
|
||||
<text x="50" y="74" fill="#94a3b8" font-size="11" font-weight="600">s07 保留</text>
|
||||
@@ -50,20 +50,20 @@
|
||||
<text x="270" y="122" fill="#92400e" font-size="8" font-weight="700" text-anchor="middle">① 每轮自动 · 无条件 · 0 API</text>
|
||||
|
||||
<rect x="186" y="130" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="146" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L3 tool_result_budget</text>
|
||||
<text x="270" y="146" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 1 tool_result_budget</text>
|
||||
|
||||
<rect x="186" y="158" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="174" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L1 snip_compact</text>
|
||||
<text x="270" y="174" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 2 snip_compact</text>
|
||||
|
||||
<rect x="186" y="186" width="168" height="24" rx="4" fill="#fef3c7" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="270" y="202" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">L2 micro_compact</text>
|
||||
<text x="270" y="202" fill="#92400e" font-size="10" font-weight="600" text-anchor="middle">Step 3 micro_compact</text>
|
||||
|
||||
<!-- ↓ → ◇ -->
|
||||
<line x1="270" y1="210" x2="270" y2="222" stroke="#555" stroke-width="1.2" marker-end="url(#arrow)"/>
|
||||
|
||||
<!-- ◇ 判断菱形（紧凑） -->
|
||||
<polygon points="270,226 300,244 270,262 240,244" fill="#f0f4ff" stroke="#ea580c" stroke-width="1.5"/>
|
||||
<text x="270" y="247" fill="#9a3412" font-size="7" font-weight="600" text-anchor="middle">超阈值?</text>
|
||||
<text x="270" y="247" fill="#9a3412" font-size="7" font-weight="600" text-anchor="middle">估算超限?</text>
|
||||
|
||||
<!-- 否：右侧文字标注 -->
|
||||
<text x="306" y="240" fill="#16a34a" font-size="9" font-weight="700">否 → 通过</text>
|
||||
@@ -74,10 +74,10 @@
|
||||
|
||||
<!-- ── ② 条件触发 ── -->
|
||||
<rect x="186" y="268" width="168" height="16" rx="3" fill="#fed7aa" stroke="#ea580c" stroke-width="0.8"/>
|
||||
<text x="270" y="280" fill="#9a3412" font-size="8" font-weight="700" text-anchor="middle">② 条件触发 · token 超阈值 · 1 API</text>
|
||||
<text x="270" y="280" fill="#9a3412" font-size="8" font-weight="700" text-anchor="middle">② 条件触发 · size 超阈值 · 1 API</text>
|
||||
|
||||
<rect x="186" y="288" width="168" height="24" rx="4" fill="#fed7aa" stroke="#ea580c" stroke-width="1"/>
|
||||
<text x="270" y="304" fill="#9a3412" font-size="10" font-weight="600" text-anchor="middle">L4 compact_history</text>
|
||||
<text x="270" y="304" fill="#9a3412" font-size="10" font-weight="600" text-anchor="middle">Step 4 compact_history</text>
|
||||
|
||||
<!-- 管线出口 → LLM -->
|
||||
<line x1="370" y1="158" x2="438" y2="158" stroke="#2563eb" stroke-width="2" marker-end="url(#arrow-blue)"/>
|
||||
@@ -113,7 +113,7 @@
|
||||
<rect x="580" y="210" width="170" height="56" rx="6" fill="#fef2f2" stroke="#dc2626" stroke-width="1" stroke-dasharray="4,2"/>
|
||||
<text x="665" y="228" fill="#991b1b" font-size="9" font-weight="700" text-anchor="middle">③ 异常触发</text>
|
||||
<text x="665" y="242" fill="#991b1b" font-size="8" text-anchor="middle">API 返回 prompt_too_long</text>
|
||||
<text x="665" y="256" fill="#991b1b" font-size="8" text-anchor="middle">→ reactive_compact → 重试</text>
|
||||
<text x="665" y="256" fill="#991b1b" font-size="8" text-anchor="middle">→ reactive_compact → 重试一次</text>
|
||||
|
||||
<!-- ===== 回环（y=348 在管线框底 y=334 下方，完全不穿过） ===== -->
|
||||
<path d="M 710 158 L 760 158 L 760 348 L 90 348 L 90 184" fill="none" stroke="#555" stroke-width="2" marker-end="url(#arrow)" stroke-dasharray="6,3"/>
|
||||
@@ -126,13 +126,13 @@
|
||||
<text x="94" y="414" fill="#334155" font-size="10">s07 保留：循环、hook、技能加载、子 Agent</text>
|
||||
|
||||
<rect x="70" y="426" width="16" height="12" rx="3" fill="#fde68a" stroke="#d97706" stroke-width="1"/>
|
||||
<text x="94" y="436" fill="#334155" font-size="10">① 每轮自动：L3→L1→L2 在每次 LLM 调用前无条件执行，0 API</text>
|
||||
<text x="94" y="436" fill="#334155" font-size="10">① 每轮自动：Step 1→2→3 在每次 LLM 调用前执行，0 API</text>
|
||||
|
||||
<rect x="70" y="448" width="16" height="12" rx="3" fill="#fed7aa" stroke="#ea580c" stroke-width="1"/>
|
||||
<text x="94" y="458" fill="#334155" font-size="10">② 条件触发：L3/L1/L2 跑完 token 仍超阈值 → compact_history，1 API</text>
|
||||
<text x="94" y="458" fill="#334155" font-size="10">② 条件触发：前三步后 size 仍超阈值 → compact_history，1 API</text>
|
||||
|
||||
<rect x="70" y="470" width="16" height="12" rx="3" fill="#fef2f2" stroke="#dc2626" stroke-width="1" stroke-dasharray="3,2"/>
|
||||
<text x="94" y="480" fill="#334155" font-size="10">③ 异常触发：API 返回 prompt_too_long → reactive_compact → 重试</text>
|
||||
<text x="94" y="480" fill="#334155" font-size="10">③ 异常触发：API 返回 prompt_too_long → reactive_compact → 重试一次</text>
|
||||
|
||||
<text x="70" y="498" fill="#94a3b8" font-size="9">三种模式的代价递增：0 API → 1 API → 1 API + 更激进的裁剪</text>
|
||||
<text x="70" y="498" fill="#94a3b8" font-size="9">三种方式逐步增加成本：0 API → 1 次摘要 → 1 次摘要与重试</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 9.0 KiB After Width: | Height: | Size: 9.1 KiB |
@@ -22,77 +22,77 @@
|
||||
<!-- Title bar -->
|
||||
<rect x="0" y="0" width="760" height="44" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="36" width="760" height="8" fill="url(#header)"/>
|
||||
<text x="380" y="28" fill="#fff" font-size="15" font-weight="700" text-anchor="middle">Context Compaction — Pre-processing Pipeline + Auto-compact + Emergency Fallback</text>
|
||||
<text x="380" y="28" fill="#fff" font-size="15" font-weight="700" text-anchor="middle">Context Compaction: Four Steps and API Error Recovery</text>
|
||||
|
||||
<!-- Design principles (left) -->
|
||||
<rect x="20" y="62" width="220" height="80" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="130" y="82" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">Design Principles</text>
|
||||
<text x="130" y="100" fill="#475569" font-size="10" text-anchor="middle">Cheap operations first, expensive later</text>
|
||||
<text x="130" y="116" fill="#475569" font-size="10" text-anchor="middle">Trim text before dropping messages</text>
|
||||
<text x="130" y="132" fill="#475569" font-size="10" text-anchor="middle">Drop messages before calling LLM</text>
|
||||
<text x="130" y="100" fill="#475569" font-size="10" text-anchor="middle">Run lower-cost operations first</text>
|
||||
<text x="130" y="116" fill="#475569" font-size="10" text-anchor="middle">Preserve recoverable information</text>
|
||||
<text x="130" y="132" fill="#475569" font-size="10" text-anchor="middle">Summarize only above the limit</text>
|
||||
|
||||
<!-- Cost escalation (right) -->
|
||||
<rect x="530" y="62" width="210" height="80" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="635" y="82" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">Increasing Cost</text>
|
||||
<text x="635" y="104" fill="#475569" font-size="10" text-anchor="middle">Text ops → LLM summary → Emergency trim</text>
|
||||
<text x="635" y="124" fill="#94a3b8" font-size="9" text-anchor="middle">0 API · 0 API · 0 API · 1 API · 1 API</text>
|
||||
<text x="635" y="104" fill="#475569" font-size="10" text-anchor="middle">Structure → Summary → Recovery</text>
|
||||
<text x="635" y="124" fill="#94a3b8" font-size="9" text-anchor="middle">0 API × 3 · 1 API · at most 1 more</text>
|
||||
|
||||
<!-- ===== Pre-processing pipeline title ===== -->
|
||||
<rect x="20" y="146" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="55" y="163" fill="#64748b" font-size="11" font-weight="600">Pre-processing Pipeline (execution order: L3 → L1 → L2, before every LLM call, 0 API)</text>
|
||||
<text x="55" y="163" fill="#64748b" font-size="11" font-weight="600">Pre-processing (Step 1 → Step 2 → Step 3 before every LLM call, 0 API)</text>
|
||||
|
||||
<!-- L3: toolResultBudget -->
|
||||
<!-- Step 1: tool_result_budget -->
|
||||
<rect x="80" y="180" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="200" fill="#1e40af" font-size="12" font-weight="600">L3</text>
|
||||
<text x="135" y="200" fill="#1e40af" font-size="13" font-weight="700">toolResultBudget</text>
|
||||
<text x="260" y="200" fill="#1e40af" font-size="11">tool_result total > 200KB → spill largest item</text>
|
||||
<text x="100" y="200" fill="#1e40af" font-size="12" font-weight="600">Step 1</text>
|
||||
<text x="155" y="200" fill="#1e40af" font-size="13" font-weight="700">tool_result_budget</text>
|
||||
<text x="315" y="200" fill="#1e40af" font-size="11">total > 200,000 chars → persist largest</text>
|
||||
<text x="650" y="200" fill="#1e40af" font-size="10" text-anchor="end">keep full content</text>
|
||||
<text x="135" y="218" fill="#2563eb" font-size="9">Trigger: every turn, before microCompact can replace full content</text>
|
||||
<text x="155" y="218" fill="#2563eb" font-size="9">Runs every turn before micro_compact can replace content</text>
|
||||
|
||||
<!-- Arrow L3→L1 -->
|
||||
<!-- Step 1 to Step 2 -->
|
||||
<line x1="380" y1="226" x2="380" y2="238" stroke="#94a3b8" stroke-width="1" marker-end="url(#arrow-d)"/>
|
||||
|
||||
<!-- L1: snipCompact -->
|
||||
<!-- Step 2: snip_compact -->
|
||||
<rect x="80" y="240" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="260" fill="#1e40af" font-size="12" font-weight="600">L1</text>
|
||||
<text x="135" y="260" fill="#1e40af" font-size="13" font-weight="700">snipCompact</text>
|
||||
<text x="100" y="260" fill="#1e40af" font-size="12" font-weight="600">Step 2</text>
|
||||
<text x="155" y="260" fill="#1e40af" font-size="13" font-weight="700">snip_compact</text>
|
||||
<text x="260" y="260" fill="#1e40af" font-size="11">messages > 50 → trim middle</text>
|
||||
<text x="650" y="260" fill="#1e40af" font-size="10" text-anchor="end">keep head/tail</text>
|
||||
<text x="135" y="278" fill="#2563eb" font-size="9">Trigger: message count exceeds threshold</text>
|
||||
<text x="155" y="278" fill="#2563eb" font-size="9">Trims above 50 messages and preserves tool pairs</text>
|
||||
|
||||
<!-- Arrow L1→L2 -->
|
||||
<!-- Step 2 to Step 3 -->
|
||||
<line x1="380" y1="286" x2="380" y2="298" stroke="#94a3b8" stroke-width="1" marker-end="url(#arrow-d)"/>
|
||||
|
||||
<!-- L2: microCompact -->
|
||||
<!-- Step 3: micro_compact -->
|
||||
<rect x="80" y="300" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="320" fill="#1e40af" font-size="12" font-weight="600">L2</text>
|
||||
<text x="135" y="320" fill="#1e40af" font-size="13" font-weight="700">microCompact</text>
|
||||
<text x="100" y="320" fill="#1e40af" font-size="12" font-weight="600">Step 3</text>
|
||||
<text x="155" y="320" fill="#1e40af" font-size="13" font-weight="700">micro_compact</text>
|
||||
<text x="260" y="320" fill="#1e40af" font-size="11">old tool_result → placeholder (keep latest 3)</text>
|
||||
<text x="650" y="320" fill="#1e40af" font-size="10" text-anchor="end">compact old</text>
|
||||
<text x="135" y="338" fill="#2563eb" font-size="9">Trigger: every turn; replace older results with text placeholders</text>
|
||||
<text x="155" y="338" fill="#2563eb" font-size="9">Runs every turn and keeps the latest 3 results complete</text>
|
||||
|
||||
<!-- ===== Auto-compact title ===== -->
|
||||
<rect x="20" y="358" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="70" y="375" fill="#64748b" font-size="11" font-weight="600">Auto-compact Decision (triggered when pre-processing is insufficient, 1 API call)</text>
|
||||
|
||||
<!-- L4: autoCompact -->
|
||||
<!-- Step 4: compact_history -->
|
||||
<rect x="80" y="390" width="600" height="58" rx="7" fill="url(#auto)" stroke="#dc2626" stroke-width="2"/>
|
||||
<text x="100" y="412" fill="#991b1b" font-size="12" font-weight="600">L4</text>
|
||||
<text x="135" y="412" fill="#991b1b" font-size="13" font-weight="700">autoCompact</text>
|
||||
<text x="260" y="412" fill="#991b1b" font-size="11">tokens over threshold → LLM summary</text>
|
||||
<text x="100" y="412" fill="#991b1b" font-size="12" font-weight="600">Step 4</text>
|
||||
<text x="155" y="412" fill="#991b1b" font-size="13" font-weight="700">compact_history</text>
|
||||
<text x="305" y="412" fill="#991b1b" font-size="11">size above 50,000 → LLM summary</text>
|
||||
<text x="650" y="412" fill="#991b1b" font-size="10" text-anchor="end">1 API call</text>
|
||||
<text x="135" y="428" fill="#dc2626" font-size="9">Threshold: contextWindow - maxOutputTokens - 13,000 · Try sessionMemoryCompact first, then LLM</text>
|
||||
<text x="135" y="442" fill="#dc2626" font-size="9">Circuit breaker: stop retrying after 3 consecutive failures</text>
|
||||
<text x="155" y="428" fill="#dc2626" font-size="9">Condition: estimate_size(messages) > CONTEXT_LIMIT</text>
|
||||
<text x="155" y="442" fill="#dc2626" font-size="9">Save a transcript, then replace active history with one summary</text>
|
||||
|
||||
<!-- ===== Emergency fallback title ===== -->
|
||||
<rect x="20" y="460" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="55" y="477" fill="#64748b" font-size="11" font-weight="600">Emergency Fallback (triggered when API still returns prompt_too_long)</text>
|
||||
<text x="55" y="477" fill="#64748b" font-size="11" font-weight="600">Error Recovery (when the API returns prompt_too_long, at most once)</text>
|
||||
|
||||
<!-- Emergency: reactiveCompact -->
|
||||
<!-- Fallback: reactive_compact -->
|
||||
<rect x="80" y="492" width="600" height="62" rx="7" fill="url(#emergency)" stroke="#c2410c" stroke-width="1.5"/>
|
||||
<text x="100" y="512" fill="#9a3412" font-size="12" font-weight="600">Emrg</text>
|
||||
<text x="135" y="512" fill="#9a3412" font-size="13" font-weight="700">reactiveCompact</text>
|
||||
<text x="135" y="528" fill="#9a3412" font-size="10">API returns 413 / prompt_too_long → byte-level trim</text>
|
||||
<text x="135" y="544" fill="#c2410c" font-size="9">Keep last 5 + summary; more aggressive than autoCompact</text>
|
||||
<text x="100" y="512" fill="#9a3412" font-size="12" font-weight="600">Retry</text>
|
||||
<text x="155" y="512" fill="#9a3412" font-size="13" font-weight="700">reactive_compact</text>
|
||||
<text x="155" y="528" fill="#9a3412" font-size="10">Summarize older history and keep the latest 5 messages</text>
|
||||
<text x="155" y="544" fill="#c2410c" font-size="9">Preserve tool pairs, then retry once</text>
|
||||
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 6.7 KiB After Width: | Height: | Size: 6.6 KiB |
@@ -22,77 +22,77 @@
|
||||
<!-- タイトルバー -->
|
||||
<rect x="0" y="0" width="760" height="44" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="36" width="760" height="8" fill="url(#header)"/>
|
||||
<text x="380" y="28" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">コンテキスト圧縮 — 前処理パイプライン + 自動圧縮 + 緊急フォールバック</text>
|
||||
<text x="380" y="28" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">コンテキスト圧縮：4 ステップと API エラー後の回復</text>
|
||||
|
||||
<!-- 設計原則（左側） -->
|
||||
<rect x="20" y="62" width="220" height="80" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="130" y="82" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">設計原則</text>
|
||||
<text x="130" y="100" fill="#475569" font-size="10" text-anchor="middle">安価な処理を先に、高価な処理を後に</text>
|
||||
<text x="130" y="116" fill="#475569" font-size="10" text-anchor="middle">テキスト修正 → メッセージ削除の順</text>
|
||||
<text x="130" y="132" fill="#475569" font-size="10" text-anchor="middle">メッセージ削除 → LLM 呼び出しの順</text>
|
||||
<text x="130" y="100" fill="#475569" font-size="10" text-anchor="middle">低コストな処理を先に実行</text>
|
||||
<text x="130" y="116" fill="#475569" font-size="10" text-anchor="middle">再取得できる情報を保持</text>
|
||||
<text x="130" y="132" fill="#475569" font-size="10" text-anchor="middle">上限超過時だけ履歴を要約</text>
|
||||
|
||||
<!-- コスト増加（右側） -->
|
||||
<rect x="530" y="62" width="210" height="80" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="635" y="82" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">コスト増加</text>
|
||||
<text x="635" y="104" fill="#475569" font-size="10" text-anchor="middle">テキスト操作 → LLM 要約 → 緊急トリム</text>
|
||||
<text x="635" y="124" fill="#94a3b8" font-size="9" text-anchor="middle">0 API · 0 API · 0 API · 1 API · 1 API</text>
|
||||
<text x="635" y="104" fill="#475569" font-size="10" text-anchor="middle">構造整理 → 履歴要約 → エラー回復</text>
|
||||
<text x="635" y="124" fill="#94a3b8" font-size="9" text-anchor="middle">0 API × 3 · 1 API · 最大 1 API 追加</text>
|
||||
|
||||
<!-- ===== 前処理パイプラインタイトル ===== -->
|
||||
<rect x="20" y="146" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="55" y="163" fill="#64748b" font-size="11" font-weight="600">前処理パイプライン（実行順：L3 → L1 → L2、各 LLM 呼び出し前に自動実行、0 API）</text>
|
||||
<text x="55" y="163" fill="#64748b" font-size="11" font-weight="600">前処理（Step 1 → Step 2 → Step 3、各 LLM 呼び出し前、0 API）</text>
|
||||
|
||||
<!-- L3: toolResultBudget -->
|
||||
<!-- Step 1: tool_result_budget -->
|
||||
<rect x="80" y="180" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="200" fill="#1e40af" font-size="12" font-weight="600">L3</text>
|
||||
<text x="135" y="200" fill="#1e40af" font-size="13" font-weight="700">toolResultBudget</text>
|
||||
<text x="260" y="200" fill="#1e40af" font-size="11">tool_result 合計 > 200KB → 最大項目を退避</text>
|
||||
<text x="100" y="200" fill="#1e40af" font-size="12" font-weight="600">Step 1</text>
|
||||
<text x="155" y="200" fill="#1e40af" font-size="13" font-weight="700">tool_result_budget</text>
|
||||
<text x="315" y="200" fill="#1e40af" font-size="11">合計 > 200,000 文字 → 最大項目を保存</text>
|
||||
<text x="650" y="200" fill="#1e40af" font-size="10" text-anchor="end">完全内容を保持</text>
|
||||
<text x="135" y="218" fill="#2563eb" font-size="9">トリガー：毎ターン、microCompact が完全内容を置換する前に実行</text>
|
||||
<text x="155" y="218" fill="#2563eb" font-size="9">毎ターン実行し、micro_compact より先に内容を保存</text>
|
||||
|
||||
<!-- 矢印 L3→L1 -->
|
||||
<!-- Step 1 to Step 2 -->
|
||||
<line x1="380" y1="226" x2="380" y2="238" stroke="#94a3b8" stroke-width="1" marker-end="url(#arrow-d)"/>
|
||||
|
||||
<!-- L1: snipCompact -->
|
||||
<!-- Step 2: snip_compact -->
|
||||
<rect x="80" y="240" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="260" fill="#1e40af" font-size="12" font-weight="600">L1</text>
|
||||
<text x="135" y="260" fill="#1e40af" font-size="13" font-weight="700">snipCompact</text>
|
||||
<text x="100" y="260" fill="#1e40af" font-size="12" font-weight="600">Step 2</text>
|
||||
<text x="155" y="260" fill="#1e40af" font-size="13" font-weight="700">snip_compact</text>
|
||||
<text x="260" y="260" fill="#1e40af" font-size="11">メッセージ > 50 → 中間をトリム</text>
|
||||
<text x="650" y="260" fill="#1e40af" font-size="10" text-anchor="end">先頭/末尾保持</text>
|
||||
<text x="135" y="278" fill="#2563eb" font-size="9">トリガー：メッセージ数が閾値を超過</text>
|
||||
<text x="155" y="278" fill="#2563eb" font-size="9">50 件を超えたら中間を省略し、ツールの組を保持</text>
|
||||
|
||||
<!-- 矢印 L1→L2 -->
|
||||
<!-- Step 2 to Step 3 -->
|
||||
<line x1="380" y1="286" x2="380" y2="298" stroke="#94a3b8" stroke-width="1" marker-end="url(#arrow-d)"/>
|
||||
|
||||
<!-- L2: microCompact -->
|
||||
<!-- Step 3: micro_compact -->
|
||||
<rect x="80" y="300" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="320" fill="#1e40af" font-size="12" font-weight="600">L2</text>
|
||||
<text x="135" y="320" fill="#1e40af" font-size="13" font-weight="700">microCompact</text>
|
||||
<text x="100" y="320" fill="#1e40af" font-size="12" font-weight="600">Step 3</text>
|
||||
<text x="155" y="320" fill="#1e40af" font-size="13" font-weight="700">micro_compact</text>
|
||||
<text x="260" y="320" fill="#1e40af" font-size="11">古い tool_result → プレースホルダー（最新 3 件保持）</text>
|
||||
<text x="650" y="320" fill="#1e40af" font-size="10" text-anchor="end">旧結果を圧縮</text>
|
||||
<text x="135" y="338" fill="#2563eb" font-size="9">トリガー：毎ターン、古い結果をテキストプレースホルダーに置換</text>
|
||||
<text x="155" y="338" fill="#2563eb" font-size="9">毎ターン実行し、最新 3 件は完全に保持</text>
|
||||
|
||||
<!-- ===== 自動圧縮タイトル ===== -->
|
||||
<rect x="20" y="358" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="70" y="375" fill="#64748b" font-size="11" font-weight="600">自動圧縮判定（前処理で不足時にトリガー、1 API 呼び出し）</text>
|
||||
|
||||
<!-- L4: autoCompact -->
|
||||
<!-- Step 4: compact_history -->
|
||||
<rect x="80" y="390" width="600" height="58" rx="7" fill="url(#auto)" stroke="#dc2626" stroke-width="2"/>
|
||||
<text x="100" y="412" fill="#991b1b" font-size="12" font-weight="600">L4</text>
|
||||
<text x="135" y="412" fill="#991b1b" font-size="13" font-weight="700">autoCompact</text>
|
||||
<text x="260" y="412" fill="#991b1b" font-size="11">トークンが閾値超過 → LLM 全量要約</text>
|
||||
<text x="100" y="412" fill="#991b1b" font-size="12" font-weight="600">Step 4</text>
|
||||
<text x="155" y="412" fill="#991b1b" font-size="13" font-weight="700">compact_history</text>
|
||||
<text x="305" y="412" fill="#991b1b" font-size="11">サイズが 50,000 超 → LLM 要約</text>
|
||||
<text x="590" y="412" fill="#991b1b" font-size="10" text-anchor="end">1 API 呼び出し</text>
|
||||
<text x="135" y="428" fill="#dc2626" font-size="9">閾値: contextWindow - maxOutputTokens - 13,000 · sessionMemoryCompact を先に試行、不足時のみ LLM 呼び出し</text>
|
||||
<text x="135" y="442" fill="#dc2626" font-size="9">サーキットブレーカー：連続 3 回失敗後にリトライ停止</text>
|
||||
<text x="155" y="428" fill="#dc2626" font-size="9">条件：estimate_size(messages) > CONTEXT_LIMIT</text>
|
||||
<text x="155" y="442" fill="#dc2626" font-size="9">transcript 保存後、現在の履歴を 1 件の要約に置換</text>
|
||||
|
||||
<!-- ===== 緊急フォールバックタイトル ===== -->
|
||||
<rect x="20" y="460" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="55" y="477" fill="#64748b" font-size="11" font-weight="600">緊急フォールバック（API が引き続き prompt_too_long を返す場合にトリガー）</text>
|
||||
<text x="55" y="477" fill="#64748b" font-size="11" font-weight="600">エラー回復（API が prompt_too_long を返した場合、最大 1 回）</text>
|
||||
|
||||
<!-- 緊急: reactiveCompact -->
|
||||
<!-- Fallback: reactive_compact -->
|
||||
<rect x="80" y="492" width="600" height="62" rx="7" fill="url(#emergency)" stroke="#c2410c" stroke-width="1.5"/>
|
||||
<text x="100" y="512" fill="#9a3412" font-size="12" font-weight="600">緊急</text>
|
||||
<text x="135" y="512" fill="#9a3412" font-size="13" font-weight="700">reactiveCompact</text>
|
||||
<text x="135" y="528" fill="#9a3412" font-size="10">API が 413 / prompt_too_long を返す → バイト単位でトリム</text>
|
||||
<text x="135" y="544" fill="#c2410c" font-size="9">最後の 5 件 + 要約を保持、autoCompact より積極的</text>
|
||||
<text x="100" y="512" fill="#9a3412" font-size="12" font-weight="600">回復</text>
|
||||
<text x="155" y="512" fill="#9a3412" font-size="13" font-weight="700">reactive_compact</text>
|
||||
<text x="155" y="528" fill="#9a3412" font-size="10">古い履歴を要約し、最新 5 メッセージを保持</text>
|
||||
<text x="155" y="544" fill="#c2410c" font-size="9">ツールの組を維持して 1 回だけリトライ</text>
|
||||
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 7.1 KiB After Width: | Height: | Size: 6.8 KiB |
@@ -22,77 +22,77 @@
|
||||
<!-- 标题栏 -->
|
||||
<rect x="0" y="0" width="760" height="44" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="36" width="760" height="8" fill="url(#header)"/>
|
||||
<text x="380" y="28" fill="#fff" font-size="15" font-weight="700" text-anchor="middle">上下文压缩 — 预处理管线 + 自动压缩 + 应急兜底</text>
|
||||
<text x="380" y="28" fill="#fff" font-size="15" font-weight="700" text-anchor="middle">上下文压缩：四步管线与 API 拒绝后的补救</text>
|
||||
|
||||
<!-- 左侧说明 -->
|
||||
<rect x="20" y="62" width="220" height="80" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="130" y="82" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">设计原则</text>
|
||||
<text x="130" y="100" fill="#475569" font-size="10" text-anchor="middle">便宜的先跑，贵的后跑</text>
|
||||
<text x="130" y="116" fill="#475569" font-size="10" text-anchor="middle">能改文本 → 不删整条</text>
|
||||
<text x="130" y="132" fill="#475569" font-size="10" text-anchor="middle">能删整条 → 不调 LLM</text>
|
||||
<text x="130" y="100" fill="#475569" font-size="10" text-anchor="middle">低成本的处理优先执行</text>
|
||||
<text x="130" y="116" fill="#475569" font-size="10" text-anchor="middle">可恢复的信息优先保留</text>
|
||||
<text x="130" y="132" fill="#475569" font-size="10" text-anchor="middle">整理后仍超限才生成摘要</text>
|
||||
|
||||
<!-- 右侧代价箭头 -->
|
||||
<rect x="530" y="62" width="210" height="80" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="635" y="82" fill="#1e3a5f" font-size="12" font-weight="700" text-anchor="middle">代价递增</text>
|
||||
<text x="635" y="104" fill="#475569" font-size="10" text-anchor="middle">文本操作 → LLM 摘要 → 应急裁剪</text>
|
||||
<text x="635" y="124" fill="#94a3b8" font-size="9" text-anchor="middle">0 API · 0 API · 0 API · 1 API · 1 API</text>
|
||||
<text x="635" y="104" fill="#475569" font-size="10" text-anchor="middle">结构整理 → 历史摘要 → 错误后补救</text>
|
||||
<text x="635" y="124" fill="#94a3b8" font-size="9" text-anchor="middle">0 API × 3 · 1 API · 最多再 1 API</text>
|
||||
|
||||
<!-- ===== 预处理管线标题 ===== -->
|
||||
<rect x="20" y="146" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="55" y="163" fill="#64748b" font-size="11" font-weight="600">预处理管线（执行顺序：L3 → L1 → L2，每轮 LLM 调用前自动执行，0 API）</text>
|
||||
<text x="55" y="163" fill="#64748b" font-size="11" font-weight="600">预处理管线（执行顺序：Step 1 → Step 2 → Step 3，每轮调用前执行，0 API）</text>
|
||||
|
||||
<!-- L3: toolResultBudget -->
|
||||
<!-- Step 1: tool_result_budget -->
|
||||
<rect x="80" y="180" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="200" fill="#1e40af" font-size="12" font-weight="600">L3</text>
|
||||
<text x="135" y="200" fill="#1e40af" font-size="13" font-weight="700">toolResultBudget</text>
|
||||
<text x="260" y="200" fill="#1e40af" font-size="11">tool_result 总和 > 200KB → 最大项落盘</text>
|
||||
<text x="100" y="200" fill="#1e40af" font-size="12" font-weight="600">Step 1</text>
|
||||
<text x="155" y="200" fill="#1e40af" font-size="13" font-weight="700">tool_result_budget</text>
|
||||
<text x="315" y="200" fill="#1e40af" font-size="11">总和 > 200,000 字符 → 最大项落盘</text>
|
||||
<text x="650" y="200" fill="#1e40af" font-size="10" text-anchor="end">保留完整内容</text>
|
||||
<text x="135" y="218" fill="#2563eb" font-size="9">触发：每轮自动，必须在 microCompact 之前保留完整内容</text>
|
||||
<text x="155" y="218" fill="#2563eb" font-size="9">每轮执行，在 micro_compact 前保留超大结果</text>
|
||||
|
||||
<!-- 箭头 L3→L1 -->
|
||||
<!-- Step 1 to Step 2 -->
|
||||
<line x1="380" y1="226" x2="380" y2="238" stroke="#94a3b8" stroke-width="1" marker-end="url(#arrow-d)"/>
|
||||
|
||||
<!-- L1: snipCompact -->
|
||||
<!-- Step 2: snip_compact -->
|
||||
<rect x="80" y="240" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="260" fill="#1e40af" font-size="12" font-weight="600">L1</text>
|
||||
<text x="135" y="260" fill="#1e40af" font-size="13" font-weight="700">snipCompact</text>
|
||||
<text x="100" y="260" fill="#1e40af" font-size="12" font-weight="600">Step 2</text>
|
||||
<text x="155" y="260" fill="#1e40af" font-size="13" font-weight="700">snip_compact</text>
|
||||
<text x="260" y="260" fill="#1e40af" font-size="11">消息 > 50 条 → 裁掉中间</text>
|
||||
<text x="650" y="260" fill="#1e40af" font-size="10" text-anchor="end">保留头尾</text>
|
||||
<text x="135" y="278" fill="#2563eb" font-size="9">触发：消息数超过阈值</text>
|
||||
<text x="155" y="278" fill="#2563eb" font-size="9">消息超过 50 条时裁剪，并保护工具调用与结果的配对</text>
|
||||
|
||||
<!-- 箭头 L1→L2 -->
|
||||
<!-- Step 2 to Step 3 -->
|
||||
<line x1="380" y1="286" x2="380" y2="298" stroke="#94a3b8" stroke-width="1" marker-end="url(#arrow-d)"/>
|
||||
|
||||
<!-- L2: microCompact -->
|
||||
<!-- Step 3: micro_compact -->
|
||||
<rect x="80" y="300" width="600" height="46" rx="7" fill="url(#pre)" stroke="#2563eb" stroke-width="1.5"/>
|
||||
<text x="100" y="320" fill="#1e40af" font-size="12" font-weight="600">L2</text>
|
||||
<text x="135" y="320" fill="#1e40af" font-size="13" font-weight="700">microCompact</text>
|
||||
<text x="100" y="320" fill="#1e40af" font-size="12" font-weight="600">Step 3</text>
|
||||
<text x="155" y="320" fill="#1e40af" font-size="13" font-weight="700">micro_compact</text>
|
||||
<text x="260" y="320" fill="#1e40af" font-size="11">旧 tool_result → 占位符（保留最近 3 条）</text>
|
||||
<text x="650" y="320" fill="#1e40af" font-size="10" text-anchor="end">压旧结果</text>
|
||||
<text x="135" y="338" fill="#2563eb" font-size="9">触发：每轮自动，把较旧结果替换为文本占位符</text>
|
||||
<text x="155" y="338" fill="#2563eb" font-size="9">每轮执行，最近 3 条结果保持完整</text>
|
||||
|
||||
<!-- ===== 自动压缩标题 ===== -->
|
||||
<rect x="20" y="358" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="70" y="375" fill="#64748b" font-size="11" font-weight="600">自动压缩决策（预处理不够时触发，1 API 调用）</text>
|
||||
|
||||
<!-- L4: autoCompact -->
|
||||
<!-- Step 4: compact_history -->
|
||||
<rect x="80" y="390" width="600" height="58" rx="7" fill="url(#auto)" stroke="#dc2626" stroke-width="2"/>
|
||||
<text x="100" y="412" fill="#991b1b" font-size="12" font-weight="600">L4</text>
|
||||
<text x="135" y="412" fill="#991b1b" font-size="13" font-weight="700">autoCompact</text>
|
||||
<text x="260" y="412" fill="#991b1b" font-size="11">token 超阈值 → LLM 全量摘要</text>
|
||||
<text x="100" y="412" fill="#991b1b" font-size="12" font-weight="600">Step 4</text>
|
||||
<text x="155" y="412" fill="#991b1b" font-size="13" font-weight="700">compact_history</text>
|
||||
<text x="305" y="412" fill="#991b1b" font-size="11">size 超过 50,000 → LLM 摘要</text>
|
||||
<text x="590" y="412" fill="#991b1b" font-size="10" text-anchor="end">1 API 调用</text>
|
||||
<text x="135" y="428" fill="#dc2626" font-size="9">阈值: contextWindow - maxOutputTokens - 13,000 · 先尝试 sessionMemoryCompact，不够才调 LLM</text>
|
||||
<text x="135" y="442" fill="#dc2626" font-size="9">熔断：连续失败 3 次后停止重试</text>
|
||||
<text x="155" y="428" fill="#dc2626" font-size="9">条件：estimate_size(messages) > CONTEXT_LIMIT</text>
|
||||
<text x="155" y="442" fill="#dc2626" font-size="9">先保存 transcript，再用一条摘要替换当前历史</text>
|
||||
|
||||
<!-- ===== 应急兜底标题 ===== -->
|
||||
<rect x="20" y="460" width="720" height="24" rx="4" fill="#f1f5f9"/>
|
||||
<text x="55" y="477" fill="#64748b" font-size="11" font-weight="600">应急兜底（API 仍然返回 prompt_too_long 时触发）</text>
|
||||
<text x="55" y="477" fill="#64748b" font-size="11" font-weight="600">错误后补救（API 返回 prompt_too_long 时触发，最多一次）</text>
|
||||
|
||||
<!-- 应急: reactiveCompact -->
|
||||
<!-- Fallback: reactive_compact -->
|
||||
<rect x="80" y="492" width="600" height="62" rx="7" fill="url(#emergency)" stroke="#c2410c" stroke-width="1.5"/>
|
||||
<text x="100" y="512" fill="#9a3412" font-size="12" font-weight="600">应急</text>
|
||||
<text x="135" y="512" fill="#9a3412" font-size="13" font-weight="700">reactiveCompact</text>
|
||||
<text x="135" y="528" fill="#9a3412" font-size="10">API 返回 413 / prompt_too_long → 字节级裁剪</text>
|
||||
<text x="135" y="544" fill="#c2410c" font-size="9">保留最后 5 条 + 摘要，比 autoCompact 更激进</text>
|
||||
<text x="100" y="512" fill="#9a3412" font-size="12" font-weight="600">补救</text>
|
||||
<text x="155" y="512" fill="#9a3412" font-size="13" font-weight="700">reactive_compact</text>
|
||||
<text x="155" y="528" fill="#9a3412" font-size="10">总结较早历史，保留最近 5 条消息</text>
|
||||
<text x="155" y="544" fill="#c2410c" font-size="9">保持工具调用与结果配对，随后重试一次</text>
|
||||
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 6.6 KiB After Width: | Height: | Size: 6.6 KiB |
@@ -11,20 +11,20 @@
|
||||
<rect width="720" height="356" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L3: toolResultBudget — Large Result Persistence</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 1: tool_result_budget, Persist Large Results</text>
|
||||
|
||||
<!-- Pain Point -->
|
||||
<rect x="20" y="54" width="680" height="42" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
<text x="35" y="72" fill="#991b1b" font-size="11" font-weight="600">Pain Point</text>
|
||||
<text x="105" y="72" fill="#991b1b" font-size="11">Model read 30 files in one turn; total tool_result adds up to 500KB, filling the entire context window</text>
|
||||
<text x="105" y="72" fill="#991b1b" font-size="11">The model read 30 files in one turn; tool_result content totals about 500,000 characters</text>
|
||||
|
||||
<!-- Before -->
|
||||
<text x="155" y="118" fill="#64748b" font-size="12" font-weight="600" text-anchor="middle">Before</text>
|
||||
<rect x="20" y="128" width="270" height="82" rx="6" fill="#fff" stroke="#94a3b8" stroke-width="1"/>
|
||||
<text x="35" y="148" fill="#475569" font-size="10" font-family="monospace">tool_result: (78KB) ...</text>
|
||||
<text x="35" y="164" fill="#475569" font-size="10" font-family="monospace">tool_result: (142KB) ...</text>
|
||||
<text x="35" y="180" fill="#475569" font-size="10" font-family="monospace">tool_result: (290KB) ...</text>
|
||||
<text x="155" y="202" fill="#ef4444" font-size="9" font-weight="600" text-anchor="middle">Total 510KB → over budget</text>
|
||||
<text x="35" y="148" fill="#475569" font-size="10" font-family="monospace">tool_result: (78K chars) ...</text>
|
||||
<text x="35" y="164" fill="#475569" font-size="10" font-family="monospace">tool_result: (142K chars) ...</text>
|
||||
<text x="35" y="180" fill="#475569" font-size="10" font-family="monospace">tool_result: (290K chars) ...</text>
|
||||
<text x="155" y="202" fill="#ef4444" font-size="9" font-weight="600" text-anchor="middle">Total 510K chars → over budget</text>
|
||||
|
||||
<!-- Arrow -->
|
||||
<line x1="295" y1="163" x2="360" y2="163" stroke="#16a34a" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
@@ -33,18 +33,18 @@
|
||||
<text x="485" y="118" fill="#16a34a" font-size="12" font-weight="600" text-anchor="middle">After</text>
|
||||
<rect x="365" y="128" width="335" height="82" rx="6" fill="#f0fdf4" stroke="#16a34a" stroke-width="1"/>
|
||||
<text x="380" y="148" fill="#166534" font-size="10" font-family="monospace">tool_result: <persisted-output></text>
|
||||
<text x="395" y="164" fill="#166534" font-size="9">Full output: .task_outputs/t1.txt</text>
|
||||
<text x="395" y="164" fill="#166534" font-size="9">Full output: .task_outputs/tool-results/t1.txt</text>
|
||||
<text x="395" y="178" fill="#166534" font-size="9">Preview: (first 2000 chars) ...</text>
|
||||
<text x="532" y="202" fill="#16a34a" font-size="9" font-weight="600" text-anchor="middle">Total 18KB → normal</text>
|
||||
<text x="532" y="202" fill="#16a34a" font-size="9" font-weight="600" text-anchor="middle">About 18K chars → within budget</text>
|
||||
|
||||
<!-- How it works -->
|
||||
<rect x="20" y="214" width="680" height="64" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="234" fill="#1e3a5f" font-size="11" font-weight="600">How</text>
|
||||
<text x="70" y="234" fill="#475569" font-size="10">1. Sum the size of all tool_result in the latest turn</text>
|
||||
<text x="70" y="250" fill="#475569" font-size="10">2. Over 200KB → sort by size, persist the largest to .task_outputs/tool-results/</text>
|
||||
<text x="70" y="250" fill="#475569" font-size="10">2. Above 200,000 chars → persist largest results to .task_outputs/tool-results/</text>
|
||||
<text x="70" y="266" fill="#475569" font-size="10">3. Keep only <persisted-output> marker + first 2000 chars preview in context</text>
|
||||
|
||||
<!-- Result summary -->
|
||||
<rect x="20" y="290" width="680" height="36" rx="6" fill="#f0fdf4" stroke="#16a34a" stroke-width="1"/>
|
||||
<text x="35" y="312" fill="#166534" font-size="11">Result: No data lost (full data on disk), context drops from 510KB to ~18KB, 0 API calls</text>
|
||||
<text x="35" y="312" fill="#166534" font-size="11">Result: full data remains on disk; context drops from 510K to about 18K chars, 0 API calls</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 3.5 KiB After Width: | Height: | Size: 3.5 KiB |
@@ -11,20 +11,20 @@
|
||||
<rect width="720" height="356" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L3: toolResultBudget — 大結果の永続化</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 1: tool_result_budget、大きな結果を保存</text>
|
||||
|
||||
<!-- ペインポイント -->
|
||||
<rect x="20" y="54" width="680" height="42" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
<text x="35" y="72" fill="#991b1b" font-size="11" font-weight="600">ペインポイント</text>
|
||||
<text x="100" y="72" fill="#991b1b" font-size="11">モデルが一度に 30 ファイルを読み込み、単一ターンの tool_result が合計 500KB に達し、コンテキストウィンドウを圧迫</text>
|
||||
<text x="100" y="72" fill="#991b1b" font-size="11">モデルが一度に 30 ファイルを読み、tool_result の合計が約 500,000 文字に到達</text>
|
||||
|
||||
<!-- 圧縮前 -->
|
||||
<text x="155" y="118" fill="#64748b" font-size="12" font-weight="600" text-anchor="middle">圧縮前</text>
|
||||
<rect x="20" y="128" width="270" height="82" rx="6" fill="#fff" stroke="#94a3b8" stroke-width="1"/>
|
||||
<text x="35" y="148" fill="#475569" font-size="10" font-family="monospace">tool_result: (78KB) ...</text>
|
||||
<text x="35" y="164" fill="#475569" font-size="10" font-family="monospace">tool_result: (142KB) ...</text>
|
||||
<text x="35" y="180" fill="#475569" font-size="10" font-family="monospace">tool_result: (290KB) ...</text>
|
||||
<text x="155" y="202" fill="#ef4444" font-size="9" font-weight="600" text-anchor="middle">合計 510KB → 予算超過</text>
|
||||
<text x="35" y="148" fill="#475569" font-size="10" font-family="monospace">tool_result: (78K chars) ...</text>
|
||||
<text x="35" y="164" fill="#475569" font-size="10" font-family="monospace">tool_result: (142K chars) ...</text>
|
||||
<text x="35" y="180" fill="#475569" font-size="10" font-family="monospace">tool_result: (290K chars) ...</text>
|
||||
<text x="155" y="202" fill="#ef4444" font-size="9" font-weight="600" text-anchor="middle">合計 510K 文字 → 予算超過</text>
|
||||
|
||||
<!-- 矢印 -->
|
||||
<line x1="295" y1="163" x2="360" y2="163" stroke="#16a34a" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
@@ -33,18 +33,18 @@
|
||||
<text x="485" y="118" fill="#16a34a" font-size="12" font-weight="600" text-anchor="middle">圧縮後</text>
|
||||
<rect x="365" y="128" width="335" height="82" rx="6" fill="#f0fdf4" stroke="#16a34a" stroke-width="1"/>
|
||||
<text x="380" y="148" fill="#166534" font-size="10" font-family="monospace">tool_result: <persisted-output></text>
|
||||
<text x="395" y="164" fill="#166534" font-size="9">Full output: .task_outputs/t1.txt</text>
|
||||
<text x="395" y="164" fill="#166534" font-size="9">Full output: .task_outputs/tool-results/t1.txt</text>
|
||||
<text x="395" y="178" fill="#166534" font-size="9">Preview: (先頭 2000 文字) ...</text>
|
||||
<text x="532" y="202" fill="#16a34a" font-size="9" font-weight="600" text-anchor="middle">合計 18KB → 正常</text>
|
||||
<text x="532" y="202" fill="#16a34a" font-size="9" font-weight="600" text-anchor="middle">約 18K 文字 → 予算内</text>
|
||||
|
||||
<!-- 原理説明 -->
|
||||
<rect x="20" y="214" width="680" height="64" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="234" fill="#1e3a5f" font-size="11" font-weight="600">方法</text>
|
||||
<text x="70" y="234" fill="#475569" font-size="10">1. 最終ターンの全 tool_result の合計サイズを集計</text>
|
||||
<text x="70" y="250" fill="#475569" font-size="10">2. 200KB 超過 → サイズ順にソートし、最大のものから .task_outputs/tool-results/ に永続化</text>
|
||||
<text x="70" y="250" fill="#475569" font-size="10">2. 200,000 文字超過 → 大きな結果から .task_outputs/tool-results/ に保存</text>
|
||||
<text x="70" y="266" fill="#475569" font-size="10">3. コンテキストには <persisted-output> マーカー + 先頭 2000 文字のプレビューのみ残す</text>
|
||||
|
||||
<!-- 変更サマリー -->
|
||||
<rect x="20" y="290" width="680" height="36" rx="6" fill="#f0fdf4" stroke="#16a34a" stroke-width="1"/>
|
||||
<text x="35" y="312" fill="#166534" font-size="11">結果：情報は失われていない（ディスクに完全なデータあり）、コンテキストは 510KB → ~18KB に削減、0 回 API 呼び出し</text>
|
||||
<text x="35" y="312" fill="#166534" font-size="11">結果：完全データはディスクに残り、コンテキストは 510K から約 18K 文字へ縮小、0 API</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 3.7 KiB After Width: | Height: | Size: 3.7 KiB |
@@ -11,20 +11,20 @@
|
||||
<rect width="720" height="356" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L3: toolResultBudget — 大结果落盘</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 1: tool_result_budget，大结果落盘</text>
|
||||
|
||||
<!-- 痛点 -->
|
||||
<rect x="20" y="54" width="680" height="42" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
<text x="35" y="72" fill="#991b1b" font-size="11" font-weight="600">痛点</text>
|
||||
<text x="75" y="72" fill="#991b1b" font-size="11">模型一次读了 30 个文件，单轮 tool_result 加起来 500KB，直接把上下文窗口打满</text>
|
||||
<text x="75" y="72" fill="#991b1b" font-size="11">模型一次读了 30 个文件，单轮 tool_result 合计约 500,000 字符</text>
|
||||
|
||||
<!-- Before -->
|
||||
<text x="155" y="118" fill="#64748b" font-size="12" font-weight="600" text-anchor="middle">压缩前</text>
|
||||
<rect x="20" y="128" width="270" height="82" rx="6" fill="#fff" stroke="#94a3b8" stroke-width="1"/>
|
||||
<text x="35" y="148" fill="#475569" font-size="10" font-family="monospace">tool_result: (78KB) ...</text>
|
||||
<text x="35" y="164" fill="#475569" font-size="10" font-family="monospace">tool_result: (142KB) ...</text>
|
||||
<text x="35" y="180" fill="#475569" font-size="10" font-family="monospace">tool_result: (290KB) ...</text>
|
||||
<text x="155" y="202" fill="#ef4444" font-size="9" font-weight="600" text-anchor="middle">合计 510KB → 超预算</text>
|
||||
<text x="35" y="148" fill="#475569" font-size="10" font-family="monospace">tool_result: (78K chars) ...</text>
|
||||
<text x="35" y="164" fill="#475569" font-size="10" font-family="monospace">tool_result: (142K chars) ...</text>
|
||||
<text x="35" y="180" fill="#475569" font-size="10" font-family="monospace">tool_result: (290K chars) ...</text>
|
||||
<text x="155" y="202" fill="#ef4444" font-size="9" font-weight="600" text-anchor="middle">合计 510K 字符 → 超预算</text>
|
||||
|
||||
<!-- Arrow -->
|
||||
<line x1="295" y1="163" x2="360" y2="163" stroke="#16a34a" stroke-width="2" marker-end="url(#arrow)"/>
|
||||
@@ -33,18 +33,18 @@
|
||||
<text x="485" y="118" fill="#16a34a" font-size="12" font-weight="600" text-anchor="middle">压缩后</text>
|
||||
<rect x="365" y="128" width="335" height="82" rx="6" fill="#f0fdf4" stroke="#16a34a" stroke-width="1"/>
|
||||
<text x="380" y="148" fill="#166534" font-size="10" font-family="monospace">tool_result: <persisted-output></text>
|
||||
<text x="395" y="164" fill="#166534" font-size="9">Full output: .task_outputs/t1.txt</text>
|
||||
<text x="395" y="164" fill="#166534" font-size="9">Full output: .task_outputs/tool-results/t1.txt</text>
|
||||
<text x="395" y="178" fill="#166534" font-size="9">Preview: (前 2000 字符) ...</text>
|
||||
<text x="532" y="202" fill="#16a34a" font-size="9" font-weight="600" text-anchor="middle">合计 18KB → 正常</text>
|
||||
<text x="532" y="202" fill="#16a34a" font-size="9" font-weight="600" text-anchor="middle">合计约 18K 字符 → 正常</text>
|
||||
|
||||
<!-- 原理说明 -->
|
||||
<rect x="20" y="214" width="680" height="64" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="234" fill="#1e3a5f" font-size="11" font-weight="600">怎么做</text>
|
||||
<text x="85" y="234" fill="#475569" font-size="10">1. 统计最后一轮所有 tool_result 的总大小</text>
|
||||
<text x="85" y="250" fill="#475569" font-size="10">2. 超过 200KB → 按大小排序，从最大的开始落盘到 .task_outputs/tool-results/</text>
|
||||
<text x="85" y="250" fill="#475569" font-size="10">2. 超过 200,000 字符 → 从最大的开始落盘到 .task_outputs/tool-results/</text>
|
||||
<text x="85" y="266" fill="#475569" font-size="10">3. 上下文里只留 <persisted-output> 标记 + 前 2000 字符预览</text>
|
||||
|
||||
<!-- 变化摘要 -->
|
||||
<rect x="20" y="290" width="680" height="36" rx="6" fill="#f0fdf4" stroke="#16a34a" stroke-width="1"/>
|
||||
<text x="35" y="312" fill="#166534" font-size="11">结果：信息没丢（磁盘有完整数据），上下文从 510KB 降到 ~18KB，0 次 API 调用</text>
|
||||
<text x="35" y="312" fill="#166534" font-size="11">结果：完整数据保留在磁盘，上下文从 510K 降到约 18K 字符，0 次 API 调用</text>
|
||||
</svg>
|
||||
|
||||
|
Before Width: | Height: | Size: 3.5 KiB After Width: | Height: | Size: 3.5 KiB |
@@ -11,7 +11,7 @@
|
||||
<rect width="720" height="300" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L2: microCompact — Old Result Placeholder Replacement</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 3: micro_compact, Replace Older Results</text>
|
||||
|
||||
<!-- Pain Point -->
|
||||
<rect x="20" y="54" width="680" height="36" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
@@ -39,11 +39,11 @@
|
||||
<text x="535" y="114" fill="#ca8a04" font-size="12" font-weight="600" text-anchor="middle">After (keep only latest 3 complete)</text>
|
||||
<rect x="390" y="122" width="310" height="95" rx="6" fill="#fefce8" stroke="#ca8a04" stroke-width="1"/>
|
||||
<rect x="400" y="130" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="138" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="138" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="145" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="153" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="153" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="160" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="168" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="168" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="175" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="183" fill="#92400e" font-size="8" font-family="monospace">Read file J: (full content, 2800 chars)</text>
|
||||
<text x="545" y="212" fill="#ca8a04" font-size="9" font-weight="600" text-anchor="middle">Keep latest 3; first 7 become placeholders</text>
|
||||
@@ -51,7 +51,7 @@
|
||||
<!-- How -->
|
||||
<rect x="20" y="228" width="680" height="62" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="248" fill="#1e3a5f" font-size="11" font-weight="600">Rule</text>
|
||||
<text x="75" y="248" fill="#475569" font-size="10">Keep the latest 3 tool results complete and replace older results with placeholders.</text>
|
||||
<text x="75" y="248" fill="#475569" font-size="10">Keep the latest 3; replace older results above 120 characters with placeholders.</text>
|
||||
<text x="35" y="264" fill="#1e3a5f" font-size="11" font-weight="600">Placeholder</text>
|
||||
<text x="105" y="264" fill="#475569" font-size="10">Explain that the result was compacted and that the tool can be run again if needed.</text>
|
||||
<text x="105" y="280" fill="#94a3b8" font-size="9">The message structure remains valid for the next loop iteration.</text>
|
||||
|
||||
|
Before Width: | Height: | Size: 4.4 KiB After Width: | Height: | Size: 4.4 KiB |
@@ -11,7 +11,7 @@
|
||||
<rect width="720" height="300" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L2: microCompact — 旧結果のプレースホルダー置換</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 3: micro_compact、古い結果を置換</text>
|
||||
|
||||
<!-- ペインポイント -->
|
||||
<rect x="20" y="54" width="680" height="36" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
@@ -39,11 +39,11 @@
|
||||
<text x="535" y="114" fill="#ca8a04" font-size="12" font-weight="600" text-anchor="middle">圧縮後（最新 3 件のみ完全保持）</text>
|
||||
<rect x="390" y="122" width="310" height="95" rx="6" fill="#fefce8" stroke="#ca8a04" stroke-width="1"/>
|
||||
<rect x="400" y="130" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="138" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="138" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="145" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="153" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="153" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="160" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="168" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="168" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="175" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="183" fill="#92400e" font-size="8" font-family="monospace">Read file J: (完全な内容, 2800 文字)</text>
|
||||
<text x="545" y="212" fill="#ca8a04" font-size="9" font-weight="600" text-anchor="middle">最新 3 件を保持、前 7 件は置換</text>
|
||||
@@ -51,7 +51,7 @@
|
||||
<!-- 原理 -->
|
||||
<rect x="20" y="228" width="680" height="62" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="248" fill="#1e3a5f" font-size="11" font-weight="600">処理規則</text>
|
||||
<text x="95" y="248" fill="#475569" font-size="10">最新 3 件の tool_result を完全保持し、古い結果をプレースホルダーに置換する。</text>
|
||||
<text x="95" y="248" fill="#475569" font-size="10">最新 3 件を保持し、120 文字超の古い結果をプレースホルダーに置換。</text>
|
||||
<text x="35" y="264" fill="#1e3a5f" font-size="11" font-weight="600">プレースホルダー</text>
|
||||
<text x="125" y="264" fill="#475569" font-size="10">結果が圧縮済みで、必要ならツールを再実行できることを示す。</text>
|
||||
<text x="125" y="280" fill="#94a3b8" font-size="9">メッセージ構造を保ったまま次のループへ進める。</text>
|
||||
|
||||
|
Before Width: | Height: | Size: 4.6 KiB After Width: | Height: | Size: 4.5 KiB |
@@ -11,7 +11,7 @@
|
||||
<rect width="720" height="300" fill="#fafbfc" rx="8"/>
|
||||
<rect x="0" y="0" width="720" height="38" fill="url(#header)" rx="8"/>
|
||||
<rect x="0" y="30" width="720" height="8" fill="url(#header)"/>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">L2: microCompact — 旧结果占位替换</text>
|
||||
<text x="360" y="25" fill="#fff" font-size="14" font-weight="700" text-anchor="middle">Step 3: micro_compact，旧结果占位替换</text>
|
||||
|
||||
<!-- 痛点 -->
|
||||
<rect x="20" y="54" width="680" height="36" rx="6" fill="#fef2f2" stroke="#fca5a5" stroke-width="1"/>
|
||||
@@ -38,11 +38,11 @@
|
||||
<text x="535" y="114" fill="#ca8a04" font-size="12" font-weight="600" text-anchor="middle">压缩后（只保留最近 3 条完整）</text>
|
||||
<rect x="390" y="122" width="310" height="95" rx="6" fill="#fefce8" stroke="#ca8a04" stroke-width="1"/>
|
||||
<rect x="400" y="130" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="138" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="138" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="145" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="153" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="153" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="160" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="168" fill="#92400e" font-size="8" font-family="monospace">[Earlier result compacted. Re-run if needed.]</text>
|
||||
<text x="408" y="168" fill="#92400e" font-size="8" font-family="monospace">[Earlier tool result compacted. Re-run if needed.]</text>
|
||||
<rect x="400" y="175" width="290" height="10" rx="2" fill="#fef3c7"/>
|
||||
<text x="408" y="183" fill="#92400e" font-size="8" font-family="monospace">Read file J: (完整内容, 2800 字符)</text>
|
||||
<text x="545" y="212" fill="#ca8a04" font-size="9" font-weight="600">只保留最近 3 条，前 7 条变占位</text>
|
||||
@@ -50,7 +50,7 @@
|
||||
<!-- 原理 -->
|
||||
<rect x="20" y="228" width="680" height="62" rx="6" fill="#f8fafc" stroke="#cbd5e1" stroke-width="1"/>
|
||||
<text x="35" y="248" fill="#1e3a5f" font-size="11" font-weight="600">处理规则</text>
|
||||
<text x="95" y="248" fill="#475569" font-size="10">遍历 tool_result，只保留最近 3 条完整，更旧的替换为占位符。</text>
|
||||
<text x="95" y="248" fill="#475569" font-size="10">最近 3 条保持完整，更早且超过 120 字符的结果替换为占位符。</text>
|
||||
<text x="35" y="264" fill="#1e3a5f" font-size="11" font-weight="600">占位内容</text>
|
||||
<text x="95" y="264" fill="#475569" font-size="10">说明原结果已压缩，并提示需要时重新运行对应工具。</text>
|
||||
<text x="95" y="280" fill="#94a3b8" font-size="9">消息结构保持不变，后续循环仍可继续处理。</text>
|
||||
|
||||
|
Before Width: | Height: | Size: 4.3 KiB After Width: | Height: | Size: 4.3 KiB |
Reference in New Issue
Block a user