Harness engineering beginner tutorial, from 0 to 1
TypeScript agentagenticagentic-aiaiai-agentai-agentsdshdsh-pluginharnessharness-engineeringharness-frameworkllm
fix: repair 298 broken relative links across all markdown files
yuzhiquan3bc70096725e
diff --git a/README.md b/README.mdindex e53371f..e8e59fe 100644--- a/README.md+++ b/README.md@@ -324,29 +324,29 @@ Each phase takes about a week if you're going part-time. If you want to go faste| Session | Question | Core Idea ||---------|----------|-----------|-| [L01](./docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Why do strong models still fail on real tasks? | The capability gap between benchmarks and real engineering |-| [L02](./docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | What does "harness" actually mean? | Five subsystems: instructions, state, verification, scope, lifecycle |-| [L03](./docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Why must the repo be the single source of truth? | If the agent can't see it, it doesn't exist |-| [L04](./docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Why does one giant instruction file fail? | Progressive disclosure: give a map, not an encyclopedia |-| [L05](./docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Why do long-running tasks lose continuity? | Persist progress to disk; pick up where you left off |-| [L06](./docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Why does initialization need its own phase? | Verify the environment is healthy before the agent starts work |-| [L07](./docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Why do agents overreach and under-finish? | One feature at a time; explicit definition of done |-| [L08](./docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Why are feature lists harness primitives? | Machine-readable scope boundaries the agent can't ignore |-| [L09](./docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Why do agents declare victory too early? | Verification gaps: confidence ≠ correctness |-| [L10](./docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Why does end-to-end testing change results? | Only a full-pipeline run counts as real verification |-| [L11](./docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Why does observability belong inside the harness? | If you can't see what the agent did, you can't fix what it broke |-| [L12](./docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Why must every session leave a clean state? | The next session's success depends on this session's cleanup |+| [L01](./docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Why do strong models still fail on real tasks? | The capability gap between benchmarks and real engineering |+| [L02](./docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | What does "harness" actually mean? | Five subsystems: instructions, state, verification, scope, lifecycle |+| [L03](./docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Why must the repo be the single source of truth? | If the agent can't see it, it doesn't exist |+| [L04](./docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Why does one giant instruction file fail? | Progressive disclosure: give a map, not an encyclopedia |+| [L05](./docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Why do long-running tasks lose continuity? | Persist progress to disk; pick up where you left off |+| [L06](./docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Why does initialization need its own phase? | Verify the environment is healthy before the agent starts work |+| [L07](./docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Why do agents overreach and under-finish? | One feature at a time; explicit definition of done |+| [L08](./docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Why are feature lists harness primitives? | Machine-readable scope boundaries the agent can't ignore |+| [L09](./docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Why do agents declare victory too early? | Verification gaps: confidence ≠ correctness |+| [L10](./docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Why does end-to-end testing change results? | Only a full-pipeline run counts as real verification |+| [L11](./docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Why does observability belong inside the harness? | If you can't see what the agent did, you can't fix what it broke |+| [L12](./docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Why must every session leave a clean state? | The next session's success depends on this session's cleanup |### Projects — 6 hands-on projects applying lecture methods to the same Electron app| Project | What You Do | Harness Mechanism ||---------|------------|-------------------|-| [P01](./docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Run the same task twice: prompt-only vs. rules-first | Minimal harness: AGENTS.md + init.sh + feature_list.json |-| [P02](./docs/projects/project-02-agent-readable-workspace/index.md) | Restructure the repo so the agent can read it | Agent-readable workspace + persistent state files |-| [P03](./docs/projects/project-03-multi-session-continuity/index.md) | Make the agent pick up from where it left off | Progress log + session handoff + multi-session continuity |-| [P04](./docs/projects/project-04-incremental-indexing/index.md) | Stop the agent from doing too much or too little | Runtime feedback + scope control + incremental indexing |-| [P05](./docs/projects/project-05-grounded-qa-verification/index.md) | Make the agent verify its own work | Self-verification + grounded Q&A + evidence-based completion |-| [P06](./docs/projects/project-06-runtime-observability-and-debugging/index.md) | Build a complete harness from scratch (capstone) | Full harness: all mechanisms + observability + ablation study |+| [P01](./docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Run the same task twice: prompt-only vs. rules-first | Minimal harness: AGENTS.md + init.sh + feature_list.json |+| [P02](./docs/en/projects/project-02-agent-readable-workspace/index.md) | Restructure the repo so the agent can read it | Agent-readable workspace + persistent state files |+| [P03](./docs/en/projects/project-03-multi-session-continuity/index.md) | Make the agent pick up from where it left off | Progress log + session handoff + multi-session continuity |+| [P04](./docs/en/projects/project-04-incremental-indexing/index.md) | Stop the agent from doing too much or too little | Runtime feedback + scope control + incremental indexing |+| [P05](./docs/en/projects/project-05-grounded-qa-verification/index.md) | Make the agent verify its own work | Self-verification + grounded Q&A + evidence-based completion |+| [P06](./docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Build a complete harness from scratch (capstone) | Full harness: all mechanisms + observability + ablation study |```textPROJECT EVOLUTIONdiff --git a/docs-readme/ar-SA/README.md b/docs-readme/ar-SA/README.mdindex 5383934..ff3c293 100644--- a/docs-readme/ar-SA/README.md+++ b/docs-readme/ar-SA/README.md@@ -316,29 +316,29 @@| الجلسة | السؤال | الفكرة الأساسية ||---------|--------|-----------------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | لماذا تفشل النماذج القوية في المهام الحقيقية؟ | الفجوة في القدرة بين المعايير القياسية والهندسة الحقيقية |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | ماذا يعني "الحزام" فعلياً؟ | خمسة أنظمة فرعية: التعليمات، الحالة، التحقق، النطاق، دورة الحياة |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | لماذا يجب أن يكون المستودع هو المصدر الوحيد للحقيقة؟ | إذا لم يستطع الوكيل رؤيته، فهو غير موجود |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | لماذا يفشل ملف التعليمات الضخم الواحد؟ | الإفصاح التدريجي: أعط خريطة، لا موسوعة |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | لماذا تفقد المهام طويلة التشغيل الاستمرارية؟ | احفظ التقدم على القرص؛ التقط من حيث توقفت |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | لماذا تحتاج التهيئة إلى مرحلة خاصة بها؟ | تحقق من صحة البيئة قبل أن يبدأ الوكيل العمل |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | لماذا يتجاوز الوكلاء الحدود وينهون أعمالاً بشكل ناقص؟ | ميزة واحدة في كل مرة؛ تعريف صريح للإتمام |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | لماذا تُعد قوائم الميزات عناصر أساسية للحزام؟ | حدود نطاق قابلة للقراءة آلياً لا يمكن للوكيل تجاهلها |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | لماذا يعلن الوكلاء النصر مبكراً جداً؟ | فجوات التحقق: الثقة ≠ الصحة |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | لماذا يغيّر الاختبار من طرف إلى طرف النتائج؟ | تشغيل خط أنابيب كامل فقط يُحسب كتحقق حقيقي |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | لماذا تنتمي قابلية الملاحظة داخل الحزام؟ | إذا لم تستطع رؤية ما فعله الوكيل، لا يمكنك إصلاح ما أفسده |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | لماذا يجب أن تترك كل جلسة حالة نظيفة؟ | نجاح الجلسة التالية يعتمد على تنظيف هذه الجلسة |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | لماذا تفشل النماذج القوية في المهام الحقيقية؟ | الفجوة في القدرة بين المعايير القياسية والهندسة الحقيقية |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | ماذا يعني "الحزام" فعلياً؟ | خمسة أنظمة فرعية: التعليمات، الحالة، التحقق، النطاق، دورة الحياة |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | لماذا يجب أن يكون المستودع هو المصدر الوحيد للحقيقة؟ | إذا لم يستطع الوكيل رؤيته، فهو غير موجود |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | لماذا يفشل ملف التعليمات الضخم الواحد؟ | الإفصاح التدريجي: أعط خريطة، لا موسوعة |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | لماذا تفقد المهام طويلة التشغيل الاستمرارية؟ | احفظ التقدم على القرص؛ التقط من حيث توقفت |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | لماذا تحتاج التهيئة إلى مرحلة خاصة بها؟ | تحقق من صحة البيئة قبل أن يبدأ الوكيل العمل |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | لماذا يتجاوز الوكلاء الحدود وينهون أعمالاً بشكل ناقص؟ | ميزة واحدة في كل مرة؛ تعريف صريح للإتمام |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | لماذا تُعد قوائم الميزات عناصر أساسية للحزام؟ | حدود نطاق قابلة للقراءة آلياً لا يمكن للوكيل تجاهلها |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | لماذا يعلن الوكلاء النصر مبكراً جداً؟ | فجوات التحقق: الثقة ≠ الصحة |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | لماذا يغيّر الاختبار من طرف إلى طرف النتائج؟ | تشغيل خط أنابيب كامل فقط يُحسب كتحقق حقيقي |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | لماذا تنتمي قابلية الملاحظة داخل الحزام؟ | إذا لم تستطع رؤية ما فعله الوكيل، لا يمكنك إصلاح ما أفسده |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | لماذا يجب أن تترك كل جلسة حالة نظيفة؟ | نجاح الجلسة التالية يعتمد على تنظيف هذه الجلسة |### المشاريع — 6 مشاريع عملية تطبق طرق المحاضرات على نفس تطبيق Electron| المشروع | ماذا تفعل | آلية الحزام ||---------|-----------|-------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | شغّل نفس المهمة مرتين: بالموجهات فقط مقابل القواعد أولاً | حزام أدنى: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | أعد هيكلة المستودع ليتمكن الوكيل من قراءته | مساحة عمل قابلة للقراءة بواسطة الوكيل + ملفات حالة مستمرة |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | اجعل الوكيل يلتقط من حيث توقف | سجل التقدم + تسليم الجلسة + استمرارية متعددة الجلسات |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | أوقف الوكيل عن القيام بالكثير جداً أو القليل جداً | ملاحظات وقت التشغيل + التحكم في النطاق + الفهرسة التدريجية |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | اجعل الوكيل يتحقق من عمله بنفسه | التحقق الذاتي + أسئلة وأجوبة مبنية على أدلة + إكمال قائم على الأدلة |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | ابنِ حزاماً كاملاً من الصفر (مشروع التخرج) | حزام كامل: جميع الآليات + قابلية الملاحظة + دراسة الاستئصال |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | شغّل نفس المهمة مرتين: بالموجهات فقط مقابل القواعد أولاً | حزام أدنى: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | أعد هيكلة المستودع ليتمكن الوكيل من قراءته | مساحة عمل قابلة للقراءة بواسطة الوكيل + ملفات حالة مستمرة |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | اجعل الوكيل يلتقط من حيث توقف | سجل التقدم + تسليم الجلسة + استمرارية متعددة الجلسات |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | أوقف الوكيل عن القيام بالكثير جداً أو القليل جداً | ملاحظات وقت التشغيل + التحكم في النطاق + الفهرسة التدريجية |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | اجعل الوكيل يتحقق من عمله بنفسه | التحقق الذاتي + أسئلة وأجوبة مبنية على أدلة + إكمال قائم على الأدلة |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | ابنِ حزاماً كاملاً من الصفر (مشروع التخرج) | حزام كامل: جميع الآليات + قابلية الملاحظة + دراسة الاستئصال |```textتطور المشاريعdiff --git a/docs-readme/de-DE/README.md b/docs-readme/de-DE/README.mdindex 8d932e8..ce4cabb 100644--- a/docs-readme/de-DE/README.md+++ b/docs-readme/de-DE/README.md@@ -315,29 +315,29 @@ Jede Phase dauert etwa eine Woche, wenn Sie nebenbei lernen. Wenn Sie schneller| Session | Frage | Kernidee ||---------|-------|----------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Warum scheitern starke Modelle dennoch bei echten Aufgaben? | Die Lücke zwischen Benchmarks und echtem Engineering |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | Was bedeutet „Harness" eigentlich? | Fünf Subsysteme: Instructions, State, Verification, Scope, Lifecycle |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Warum muss das Repo die einzige Quelle der Wahrheit sein? | Wenn der Agent es nicht sehen kann, existiert es nicht |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Warum scheitert eine einzige riesige Instruktionsdatei? | Progressive Enthüllung: eine Karte geben, keine Enzyklopädie |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Warum verlieren langlaufende Aufgaben ihre Kontinuität? | Fortschritt auf der Festplatte speichern; dort fortfahren, wo man aufgehört hat |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Warum braucht die Initialisierung eine eigene Phase? | Die Umgebung auf Funktionsfähigkeit prüfen, bevor der Agent mit der Arbeit beginnt |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Warum greifen Agenten über und schließen unvollständig ab? | Ein Feature gleichzeitig; explizite Definition von „Fertig" |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Warum sind Feature-Listen Harness-Primitiven? | Maschinenlesbare Scope-Grenzen, die der Agent nicht ignorieren kann |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Warum melden Agenten zu früh den Erfolg? | Verifizierungslücken: Vertrauen ≠ Korrektheit |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Warum ändert End-to-End-Testing die Ergebnisse? | Nur ein vollständiger Pipeline-Lauf gilt als echte Verifizierung |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Warum gehört Observability in das Harness? | Wenn Sie nicht sehen können, was der Agent getan hat, können Sie nicht reparieren, was er zerstört hat |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Warum muss jede Session einen sauberen Zustand hinterlassen? | Der Erfolg der nächsten Session hängt vom Aufräumen dieser Session ab |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Warum scheitern starke Modelle dennoch bei echten Aufgaben? | Die Lücke zwischen Benchmarks und echtem Engineering |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | Was bedeutet „Harness" eigentlich? | Fünf Subsysteme: Instructions, State, Verification, Scope, Lifecycle |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Warum muss das Repo die einzige Quelle der Wahrheit sein? | Wenn der Agent es nicht sehen kann, existiert es nicht |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Warum scheitert eine einzige riesige Instruktionsdatei? | Progressive Enthüllung: eine Karte geben, keine Enzyklopädie |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Warum verlieren langlaufende Aufgaben ihre Kontinuität? | Fortschritt auf der Festplatte speichern; dort fortfahren, wo man aufgehört hat |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Warum braucht die Initialisierung eine eigene Phase? | Die Umgebung auf Funktionsfähigkeit prüfen, bevor der Agent mit der Arbeit beginnt |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Warum greifen Agenten über und schließen unvollständig ab? | Ein Feature gleichzeitig; explizite Definition von „Fertig" |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Warum sind Feature-Listen Harness-Primitiven? | Maschinenlesbare Scope-Grenzen, die der Agent nicht ignorieren kann |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Warum melden Agenten zu früh den Erfolg? | Verifizierungslücken: Vertrauen ≠ Korrektheit |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Warum ändert End-to-End-Testing die Ergebnisse? | Nur ein vollständiger Pipeline-Lauf gilt als echte Verifizierung |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Warum gehört Observability in das Harness? | Wenn Sie nicht sehen können, was der Agent getan hat, können Sie nicht reparieren, was er zerstört hat |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Warum muss jede Session einen sauberen Zustand hinterlassen? | Der Erfolg der nächsten Session hängt vom Aufräumen dieser Session ab |### Projekte — 6 praktische Projekte, die Vorlesungsmethoden auf dieselbe Electron-App anwenden| Projekt | Was Sie tun | Harness-Mechanismus ||---------|-------------|---------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Dieselbe Aufgabe zweimal ausführen: nur Prompt vs. regelnbasiert | Minimales Harness: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | Das Repo umstrukturieren, damit der Agent es lesen kann | Agentenlesbarer Arbeitsbereich + persistente Zustandsdateien |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | Den Agenten dort fortfahren lassen, wo er aufgehört hat | Fortschrittsprotokoll + Session-Übergabe + Multi-Session-Kontinuität |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | Den Agenten davon abhalten, zu viel oder zu wenig zu tun | Laufzeit-Feedback + Scope-Kontrolle + inkrementelle Indizierung |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | Den Agenten seine eigene Arbeit verifizieren lassen | Selbstverifizierung + fundierte Q&A + evidenzbasierter Abschluss |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | Ein vollständiges Harness von Grund auf neu aufbauen (Abschlussprojekt) | Vollständiges Harness: alle Mechanismen + Observability + Ablationsstudie |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Dieselbe Aufgabe zweimal ausführen: nur Prompt vs. regelnbasiert | Minimales Harness: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | Das Repo umstrukturieren, damit der Agent es lesen kann | Agentenlesbarer Arbeitsbereich + persistente Zustandsdateien |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | Den Agenten dort fortfahren lassen, wo er aufgehört hat | Fortschrittsprotokoll + Session-Übergabe + Multi-Session-Kontinuität |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | Den Agenten davon abhalten, zu viel oder zu wenig zu tun | Laufzeit-Feedback + Scope-Kontrolle + inkrementelle Indizierung |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | Den Agenten seine eigene Arbeit verifizieren lassen | Selbstverifizierung + fundierte Q&A + evidenzbasierter Abschluss |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Ein vollständiges Harness von Grund auf neu aufbauen (Abschlussprojekt) | Vollständiges Harness: alle Mechanismen + Observability + Ablationsstudie |```textPROJEKTENTWICKLUNGdiff --git a/docs-readme/es-ES/README.md b/docs-readme/es-ES/README.mdindex 4dea43d..a96d67d 100644--- a/docs-readme/es-ES/README.md+++ b/docs-readme/es-ES/README.md@@ -317,29 +317,29 @@ Cada fase toma aproximadamente una semana si lo haces a tiempo parcial. Si quier| Sesión | Pregunta | Idea Central ||---------|----------|--------------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Por qué los modelos potentes siguen fallando en tareas reales? | La brecha de capacidad entre benchmarks e ingeniería real |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | Qué significa realmente "harness"? | Cinco subsistemas: instrucciones, estado, verificación, alcance, ciclo de vida |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Por qué el repositorio debe ser la única fuente de verdad? | Si el agente no puede verlo, no existe |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Por qué falla un único archivo de instrucciones gigante? | Divulgación progresiva: da un mapa, no una enciclopedia |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Por qué las tareas de larga duración pierden continuidad? | Persistir el progreso en disco; continuar donde lo dejaste |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Por qué la inicialización necesita su propia fase? | Verificar que el entorno está saludable antes de que el agente comience a trabajar |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Por qué los agentes se exceden y no terminan? | Una funcionalidad a la vez; definición explícita de "hecho" |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Por qué las listas de funcionalidades son primitivas del harness? | Límites de alcance legibles por máquina que el agente no puede ignorar |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Por qué los agentes declaran victoria demasiado pronto? | Brechas de verificación: confianza ≠ corrección |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Por qué las pruebas de extremo a extremo cambian los resultados? | Solo una ejecución completa del pipeline cuenta como verificación real |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Por qué la observabilidad pertenece dentro del harness? | Si no puedes ver lo que el agente hizo, no puedes arreglar lo que rompió |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Por qué cada sesión debe dejar un estado limpio? | El éxito de la siguiente sesión depende de la limpieza de esta sesión |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Por qué los modelos potentes siguen fallando en tareas reales? | La brecha de capacidad entre benchmarks e ingeniería real |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | Qué significa realmente "harness"? | Cinco subsistemas: instrucciones, estado, verificación, alcance, ciclo de vida |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Por qué el repositorio debe ser la única fuente de verdad? | Si el agente no puede verlo, no existe |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Por qué falla un único archivo de instrucciones gigante? | Divulgación progresiva: da un mapa, no una enciclopedia |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Por qué las tareas de larga duración pierden continuidad? | Persistir el progreso en disco; continuar donde lo dejaste |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Por qué la inicialización necesita su propia fase? | Verificar que el entorno está saludable antes de que el agente comience a trabajar |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Por qué los agentes se exceden y no terminan? | Una funcionalidad a la vez; definición explícita de "hecho" |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Por qué las listas de funcionalidades son primitivas del harness? | Límites de alcance legibles por máquina que el agente no puede ignorar |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Por qué los agentes declaran victoria demasiado pronto? | Brechas de verificación: confianza ≠ corrección |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Por qué las pruebas de extremo a extremo cambian los resultados? | Solo una ejecución completa del pipeline cuenta como verificación real |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Por qué la observabilidad pertenece dentro del harness? | Si no puedes ver lo que el agente hizo, no puedes arreglar lo que rompió |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Por qué cada sesión debe dejar un estado limpio? | El éxito de la siguiente sesión depende de la limpieza de esta sesión |### Proyectos — 6 proyectos prácticos aplicando los métodos de las clases a la misma aplicación Electron| Proyecto | Lo que haces | Mecanismo del Harness ||----------|--------------|----------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Ejecutar la misma tarea dos veces: solo con prompts vs. con reglas primero | Harness mínimo: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | Reestructurar el repositorio para que el agente pueda leerlo | Espacio de trabajo legible por el agente + archivos de estado persistentes |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | Hacer que el agente continúe desde donde se quedó | Registro de progreso + transferencia de sesión + continuidad multi-sesión |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | Evitar que el agente haga demasiado o muy poco | Retroalimentación en tiempo de ejecución + control de alcance + indexación incremental |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | Hacer que el agente verifique su propio trabajo | Auto-verificación + Q&A fundamentado + completación basada en evidencia |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | Construir un harness completo desde cero (proyecto final) | Harness completo: todos los mecanismos + observabilidad + estudio de ablación |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Ejecutar la misma tarea dos veces: solo con prompts vs. con reglas primero | Harness mínimo: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | Reestructurar el repositorio para que el agente pueda leerlo | Espacio de trabajo legible por el agente + archivos de estado persistentes |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | Hacer que el agente continúe desde donde se quedó | Registro de progreso + transferencia de sesión + continuidad multi-sesión |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | Evitar que el agente haga demasiado o muy poco | Retroalimentación en tiempo de ejecución + control de alcance + indexación incremental |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | Hacer que el agente verifique su propio trabajo | Auto-verificación + Q&A fundamentado + completación basada en evidencia |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Construir un harness completo desde cero (proyecto final) | Harness completo: todos los mecanismos + observabilidad + estudio de ablación |```textEVOLUCIÓN DEL PROYECTOdiff --git a/docs-readme/fr-FR/README.md b/docs-readme/fr-FR/README.mdindex bf57553..7a542aa 100644--- a/docs-readme/fr-FR/README.md+++ b/docs-readme/fr-FR/README.md@@ -315,29 +315,29 @@ Chaque phase prend environ une semaine si vous suivez le cours à temps partiel.| Session | Question | Idée Centrale ||---------|----------|---------------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Pourquoi les modèles performants échouent-ils encore sur des tâches réelles ? | L'écart de capacité entre les benchmarks et l'ingénierie réelle |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | Que signifie réellement « harness » ? | Cinq sous-systèmes : instructions, état, vérification, portée, cycle de vie |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Pourquoi le dépôt doit-il être l'unique source de vérité ? | Si l'agent ne peut pas le voir, ça n'existe pas |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Pourquoi un seul fichier d'instructions géant échoue-t-il ? | Divulgation progressive : donnez une carte, pas une encyclopédie |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Pourquoi les tâches de longue durée perdent-elles leur continuité ? | Persister le progrès sur disque ; reprendre là où vous vous êtes arrêté |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Pourquoi l'initialisation nécessite-t-elle sa propre phase ? | Vérifier que l'environnement est sain avant que l'agent ne commence à travailler |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Pourquoi les agents vont-ils trop loin et n'en font-ils pas assez ? | Une seule fonctionnalité à la fois ; définition explicite de « terminé » |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Pourquoi les listes de fonctionnalités sont-elles des primitives du harness ? | Des limites de portée lisibles par machine que l'agent ne peut pas ignorer |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Pourquoi les agents déclarent-ils victoire trop tôt ? | Lacunes de vérification : confiance ≠ correction |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Pourquoi les tests de bout en bout changent-ils les résultats ? | Seule une exécution complète du pipeline compte comme véritable vérification |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Pourquoi l'observabilité appartient-elle au harness ? | Si vous ne pouvez pas voir ce que l'agent a fait, vous ne pouvez pas corriger ce qu'il a cassé |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Pourquoi chaque session doit-elle laisser un état propre ? | Le succès de la prochaine session dépend du nettoyage de celle-ci |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Pourquoi les modèles performants échouent-ils encore sur des tâches réelles ? | L'écart de capacité entre les benchmarks et l'ingénierie réelle |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | Que signifie réellement « harness » ? | Cinq sous-systèmes : instructions, état, vérification, portée, cycle de vie |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Pourquoi le dépôt doit-il être l'unique source de vérité ? | Si l'agent ne peut pas le voir, ça n'existe pas |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Pourquoi un seul fichier d'instructions géant échoue-t-il ? | Divulgation progressive : donnez une carte, pas une encyclopédie |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Pourquoi les tâches de longue durée perdent-elles leur continuité ? | Persister le progrès sur disque ; reprendre là où vous vous êtes arrêté |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Pourquoi l'initialisation nécessite-t-elle sa propre phase ? | Vérifier que l'environnement est sain avant que l'agent ne commence à travailler |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Pourquoi les agents vont-ils trop loin et n'en font-ils pas assez ? | Une seule fonctionnalité à la fois ; définition explicite de « terminé » |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Pourquoi les listes de fonctionnalités sont-elles des primitives du harness ? | Des limites de portée lisibles par machine que l'agent ne peut pas ignorer |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Pourquoi les agents déclarent-ils victoire trop tôt ? | Lacunes de vérification : confiance ≠ correction |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Pourquoi les tests de bout en bout changent-ils les résultats ? | Seule une exécution complète du pipeline compte comme véritable vérification |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Pourquoi l'observabilité appartient-elle au harness ? | Si vous ne pouvez pas voir ce que l'agent a fait, vous ne pouvez pas corriger ce qu'il a cassé |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Pourquoi chaque session doit-elle laisser un état propre ? | Le succès de la prochaine session dépend du nettoyage de celle-ci |### Projets -- 6 projets pratiques appliquant les méthodes des cours à la même application Electron| Projet | Ce que vous faites | Mécanisme du Harness ||--------|--------------------|----------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Exécuter la même tâche deux fois : avec prompts seuls vs. avec règles d'abord | Harness minimal : AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | Restructurer le dépôt pour que l'agent puisse le lire | Espace de travail lisible par l'agent + fichiers d'état persistants |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | Faire en sorte que l'agent reprenne là où il s'est arrêté | Journal de progression + transfert de session + continuité multi-sessions |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | Empêcher l'agent d'en faire trop ou pas assez | Retour d'exécution + contrôle de portée + indexation incrémentale |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | Faire en sorte que l'agent vérifie son propre travail | Auto-vérification + Q&A fondé + achèvement basé sur les preuves |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | Construire un harness complet à partir de zéro (projet final) | Harness complet : tous les mécanismes + observabilité + étude d'ablation |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Exécuter la même tâche deux fois : avec prompts seuls vs. avec règles d'abord | Harness minimal : AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | Restructurer le dépôt pour que l'agent puisse le lire | Espace de travail lisible par l'agent + fichiers d'état persistants |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | Faire en sorte que l'agent reprenne là où il s'est arrêté | Journal de progression + transfert de session + continuité multi-sessions |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | Empêcher l'agent d'en faire trop ou pas assez | Retour d'exécution + contrôle de portée + indexation incrémentale |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | Faire en sorte que l'agent vérifie son propre travail | Auto-vérification + Q&A fondé + achèvement basé sur les preuves |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Construire un harness complet à partir de zéro (projet final) | Harness complet : tous les mécanismes + observabilité + étude d'ablation |```textÉVOLUTION DES PROJETSdiff --git a/docs-readme/ja-JP/README.md b/docs-readme/ja-JP/README.mdindex 633e66e..07e22dd 100644--- a/docs-readme/ja-JP/README.md+++ b/docs-readme/ja-JP/README.md@@ -315,29 +315,29 @@ Harness Engineering は、モデルの周囲に完全な作業環境を構築し| セッション | 問い | コアアイデア ||---------|----------|-----------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | なぜ強力なモデルでも実際のタスクで失敗するのか? | ベンチマークと実際のエンジニアリングの能力格差 |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | 「ハーネス」とは実際何を意味するのか? | 5つのサブシステム:インストラクション、状態、検証、スコープ、ライフサイクル |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | なぜリポジトリが唯一の信頼できる情報源でなければならないのか? | エージェントが見られないものは存在しない |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | なぜ一つの巨大な指示ファイルは失敗するのか? | 段階的開示:百科事典ではなく地図を与える |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | なぜ長時間実行タスクは連続性を失うのか? | 進捗をディスクに永続化し、前回の続きから再開する |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | なぜ初期化に独自のフェーズが必要なのか? | エージェントが作業を開始する前に環境が健全であることを確認する |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | なぜエージェントは過剰に手を出し、不足して終わるのか? | 一度に一つの機能、明確な完了の定義 |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | なぜ機能リストはハーネスのプリミティブなのか? | エージェントが無視できない機械可読なスコープ境界 |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | なぜエージェントは早すぎる完了を宣言するのか? | 検証のギャップ:確信 ≠ 正確性 |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | なぜエンドツーエンドテストが結果を変えるのか? | 完全なパイプライン実行のみが本当の検証として認められる |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | なぜオブザーバビリティはハーネス内にあるべきなのか? | エージェントが何をしたか見えなければ、何を壊したか修正できない |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | なぜすべてのセッションがクリーンな状態を残さなければならないのか? | 次のセッションの成功は、このセッションのクリーンアップに依存する |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | なぜ強力なモデルでも実際のタスクで失敗するのか? | ベンチマークと実際のエンジニアリングの能力格差 |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | 「ハーネス」とは実際何を意味するのか? | 5つのサブシステム:インストラクション、状態、検証、スコープ、ライフサイクル |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | なぜリポジトリが唯一の信頼できる情報源でなければならないのか? | エージェントが見られないものは存在しない |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | なぜ一つの巨大な指示ファイルは失敗するのか? | 段階的開示:百科事典ではなく地図を与える |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | なぜ長時間実行タスクは連続性を失うのか? | 進捗をディスクに永続化し、前回の続きから再開する |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | なぜ初期化に独自のフェーズが必要なのか? | エージェントが作業を開始する前に環境が健全であることを確認する |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | なぜエージェントは過剰に手を出し、不足して終わるのか? | 一度に一つの機能、明確な完了の定義 |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | なぜ機能リストはハーネスのプリミティブなのか? | エージェントが無視できない機械可読なスコープ境界 |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | なぜエージェントは早すぎる完了を宣言するのか? | 検証のギャップ:確信 ≠ 正確性 |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | なぜエンドツーエンドテストが結果を変えるのか? | 完全なパイプライン実行のみが本当の検証として認められる |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | なぜオブザーバビリティはハーネス内にあるべきなのか? | エージェントが何をしたか見えなければ、何を壊したか修正できない |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | なぜすべてのセッションがクリーンな状態を残さなければならないのか? | 次のセッションの成功は、このセッションのクリーンアップに依存する |### プロジェクト — レクチャーの手法を同じ Electron アプリに適用する6つのハンズオンプロジェクト| プロジェクト | やること | ハーネスメカニズム ||---------|------------|-------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | 同じタスクを2回実行:プロンプトのみ vs. ルール優先 | 最小ハーネス:AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | エージェントが読めるようにリポジトリを再構築する | エージェント可読ワークスペース + 永続状態ファイル |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | エージェントが前回の続きから再開できるようにする | 進捗ログ + セションハンドオフ + マルチセッション連続性 |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | エージェントがやりすぎたり、やらなすぎたりするのを防ぐ | ランタイムフィードバック + スコープ制御 + インクリメンタルインデキシング |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | エージェントが自分の作業を検証するようにする | 自己検証 + グラウンデッドQ&A + 証拠ベースの完了 |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | ゼロから完全なハーネスを構築する(カプロジェクト) | フルハーネス:全メカニズム + オブザーバビリティ + アブレーションスタディ |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | 同じタスクを2回実行:プロンプトのみ vs. ルール優先 | 最小ハーネス:AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | エージェントが読めるようにリポジトリを再構築する | エージェント可読ワークスペース + 永続状態ファイル |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | エージェントが前回の続きから再開できるようにする | 進捗ログ + セションハンドオフ + マルチセッション連続性 |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | エージェントがやりすぎたり、やらなすぎたりするのを防ぐ | ランタイムフィードバック + スコープ制御 + インクリメンタルインデキシング |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | エージェントが自分の作業を検証するようにする | 自己検証 + グラウンデッドQ&A + 証拠ベースの完了 |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | ゼロから完全なハーネスを構築する(カプロジェクト) | フルハーネス:全メカニズム + オブザーバビリティ + アブレーションスタディ |```textプロジェクトの進化diff --git a/docs-readme/ko-KR/README.md b/docs-readme/ko-KR/README.mdindex 0b8ad4b..9c75058 100644--- a/docs-readme/ko-KR/README.md+++ b/docs-readme/ko-KR/README.md@@ -313,29 +313,29 @@ Harness engineering은 모델 주변에 안정적인 결과를 생성하는 완| 세션 | 질문 | 핵심 아이디어 ||---------|----------|-----------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | 왜 강력한 모델도 실제 작업에서 여전히 실패하는가? | 벤치마크와 실제 엔지니어링 사이의 역량 격차 |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | "하니스"는 실제로 무엇을 의미하는가? | 다섯 가지 하위 시스템: 지시 사항, 상태, 검증, 범위, 수명 주기 |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | 왜 저장소가 단일 진실 공급원이어야 하는가? | 에이전트가 볼 수 없다면 존재하지 않는 것과 같다 |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | 왜 거대한 단일 지시 파일은 실패하는가? | 점진적 공개: 백과사전이 아닌 지도를 제공하라 |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | 왜 장기 실행 작업은 연속성을 잃는가? | 진행 상황을 디스크에 영속화; 중단된 지점에서 이어하기 |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | 왜 초기화에 전용 단계가 필요한가? | 에이전트가 작업을 시작하기 전에 환경이 정상인지 확인 |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | 왜 에이전트는 과도하게 작업하고 불완전하게 마무리하는가? | 한 번에 하나의 기능; 명시적인 완료 정의 |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | 왜 기능 목록이 하니스 프리미티브인가? | 에이전트가 무시할 수 없는 기계 판독 가능 범위 경계 |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | 왜 에이전트는 너무 일찍 완료를 선언하는가? | 검증 격차: 자신감 ≠ 정확성 |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | 왜 엔드투엔드 테스트가 결과를 바꾸는가? | 전체 파이프라인 실행만이 진정한 검증으로 인정된다 |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | 왜 관측 가능성이 하니스 내에 있어야 하는가? | 에이전트가 무엇을 했는지 볼 수 없으면, 무엇을 망가뜨렸는지 고칠 수 없다 |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | 왜 모든 세션은 깔끔한 상태를 남겨야 하는가? | 다음 세션의 성공은 이번 세션의 정리에 달려 있다 |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | 왜 강력한 모델도 실제 작업에서 여전히 실패하는가? | 벤치마크와 실제 엔지니어링 사이의 역량 격차 |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | "하니스"는 실제로 무엇을 의미하는가? | 다섯 가지 하위 시스템: 지시 사항, 상태, 검증, 범위, 수명 주기 |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | 왜 저장소가 단일 진실 공급원이어야 하는가? | 에이전트가 볼 수 없다면 존재하지 않는 것과 같다 |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | 왜 거대한 단일 지시 파일은 실패하는가? | 점진적 공개: 백과사전이 아닌 지도를 제공하라 |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | 왜 장기 실행 작업은 연속성을 잃는가? | 진행 상황을 디스크에 영속화; 중단된 지점에서 이어하기 |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | 왜 초기화에 전용 단계가 필요한가? | 에이전트가 작업을 시작하기 전에 환경이 정상인지 확인 |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | 왜 에이전트는 과도하게 작업하고 불완전하게 마무리하는가? | 한 번에 하나의 기능; 명시적인 완료 정의 |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | 왜 기능 목록이 하니스 프리미티브인가? | 에이전트가 무시할 수 없는 기계 판독 가능 범위 경계 |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | 왜 에이전트는 너무 일찍 완료를 선언하는가? | 검증 격차: 자신감 ≠ 정확성 |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | 왜 엔드투엔드 테스트가 결과를 바꾸는가? | 전체 파이프라인 실행만이 진정한 검증으로 인정된다 |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | 왜 관측 가능성이 하니스 내에 있어야 하는가? | 에이전트가 무엇을 했는지 볼 수 없으면, 무엇을 망가뜨렸는지 고칠 수 없다 |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | 왜 모든 세션은 깔끔한 상태를 남겨야 하는가? | 다음 세션의 성공은 이번 세션의 정리에 달려 있다 |### 프로젝트 — 동일한 Electron 앱에 강의 방법론을 적용하는 6개의 실습 프로젝트| 프로젝트 | 수행 내용 | 하니스 메커니즘 ||---------|------------|-------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | 동일한 작업을 두 번 실행: 프롬프트만 vs. 규칙 우선 | 최소 하니스: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | 에이전트가 읽을 수 있도록 저장소 재구성 | 에이전트 판독 가능 작업 공간 + 영속적 상태 파일 |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | 에이전트가 중단된 지점에서 이어가도록 만들기 | 진행 로그 + 세션 인계 + 다중 세션 연속성 |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | 에이전트가 너무 많거나 너무 적게 작업하지 않도록 방지 | 런타임 피드백 + 범위 제어 + 점진적 인덱싱 |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | 에이전트가 자신의 작업을 검증하도록 만들기 | 자체 검증 + 근거 기반 Q&A + 증거 기반 완료 |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | 처음부터 완전한 하니스 구축 (캡스톤) | 전체 하니스: 모든 메커니즘 + 관측 가능성 + 어블레이션 스터디 |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | 동일한 작업을 두 번 실행: 프롬프트만 vs. 규칙 우선 | 최소 하니스: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | 에이전트가 읽을 수 있도록 저장소 재구성 | 에이전트 판독 가능 작업 공간 + 영속적 상태 파일 |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | 에이전트가 중단된 지점에서 이어가도록 만들기 | 진행 로그 + 세션 인계 + 다중 세션 연속성 |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | 에이전트가 너무 많거나 너무 적게 작업하지 않도록 방지 | 런타임 피드백 + 범위 제어 + 점진적 인덱싱 |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | 에이전트가 자신의 작업을 검증하도록 만들기 | 자체 검증 + 근거 기반 Q&A + 증거 기반 완료 |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | 처음부터 완전한 하니스 구축 (캡스톤) | 전체 하니스: 모든 메커니즘 + 관측 가능성 + 어블레이션 스터디 |```text프로젝트 발전 과정diff --git a/docs-readme/ru-RU/README.md b/docs-readme/ru-RU/README.mdindex 8ab4664..f07e58e 100644--- a/docs-readme/ru-RU/README.md+++ b/docs-readme/ru-RU/README.md@@ -325,29 +325,29 @@ Harness состоит из пяти подсистем:| Занятие | Вопрос | Ключевая идея ||---------|--------|---------------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Почему сильные модели всё равно ошибаются на реальных задачах? | Разрыв между бенчмарками и реальным инжинирингом |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | Что на самом деле означает «harness"? | Пять подсистем: Instructions, State, Verification, Scope, Lifecycle |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Почему репозиторий должен быть единственным источником истины? | Если агент не может это увидеть — этого не существует |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Почему одна гигантская инструкция обречена на провал? | Прогрессивное раскрытие: дать карту, а не энциклопедию |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Почему длительные задачи теряют связность? | Сохранять прогресс на диске; продолжать с того места, где остановились |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Почему инициализация требует отдельной фазы? | Проверить работоспособность окружения до того, как агент начнёт работу |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Почему агенты выходят за рамки и не доделывают? | Одна фича за раз; явное определение «готово" |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Почему feature-списки — это примитивы harness? | Машинно-читаемые границы scope, которые агент не может проигнорировать |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Почему агенты объявляют успех слишком рано? | Пробелы в верификации: доверие ≠ корректность |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Почему end-to-end-тестирование меняет результаты? | Только полный прогон pipeline считается настоящей верификацией |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Почему observability должна быть внутри harness? | Если вы не видите, что сделал агент, вы не сможете починить то, что он сломал |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Почему каждая сессия должна оставлять чистое состояние? | Успех следующей сессии зависит от уборки в этой |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Почему сильные модели всё равно ошибаются на реальных задачах? | Разрыв между бенчмарками и реальным инжинирингом |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | Что на самом деле означает «harness"? | Пять подсистем: Instructions, State, Verification, Scope, Lifecycle |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Почему репозиторий должен быть единственным источником истины? | Если агент не может это увидеть — этого не существует |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Почему одна гигантская инструкция обречена на провал? | Прогрессивное раскрытие: дать карту, а не энциклопедию |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Почему длительные задачи теряют связность? | Сохранять прогресс на диске; продолжать с того места, где остановились |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Почему инициализация требует отдельной фазы? | Проверить работоспособность окружения до того, как агент начнёт работу |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Почему агенты выходят за рамки и не доделывают? | Одна фича за раз; явное определение «готово" |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Почему feature-списки — это примитивы harness? | Машинно-читаемые границы scope, которые агент не может проигнорировать |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Почему агенты объявляют успех слишком рано? | Пробелы в верификации: доверие ≠ корректность |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Почему end-to-end-тестирование меняет результаты? | Только полный прогон pipeline считается настоящей верификацией |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Почему observability должна быть внутри harness? | Если вы не видите, что сделал агент, вы не сможете починить то, что он сломал |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Почему каждая сессия должна оставлять чистое состояние? | Успех следующей сессии зависит от уборки в этой |### Проекты — 6 практических проектов, применяющих методы лекций к одному и тому же Electron-приложению| Проект | Что вы делаете | Механизм harness ||---------|----------------|-------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Выполнить одну задачу дважды: только промпт vs. на основе правил | Минимальный harness: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | Реструктурировать репозиторий для чтения агентом | Агентно-читаемое рабочее пространство + постоянные файлы состояния |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | Позволить агенту продолжить с того места, где он остановился | Протокол прогресса + передача сессии + мультисессионная связность |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | Не дать агенту сделать слишком много или слишком мало | Runtime-обратная связь + контроль scope + инкрементальное индексирование |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | Заставить агента верифицировать собственную работу | Самоверификация + обоснованный Q&A + завершение на основе свидетельств |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | Построить полный harness с нуля (итоговый проект) | Полный harness: все механизмы + observability + абляционное исследование |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Выполнить одну задачу дважды: только промпт vs. на основе правил | Минимальный harness: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | Реструктурировать репозиторий для чтения агентом | Агентно-читаемое рабочее пространство + постоянные файлы состояния |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | Позволить агенту продолжить с того места, где он остановился | Протокол прогресса + передача сессии + мультисессионная связность |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | Не дать агенту сделать слишком много или слишком мало | Runtime-обратная связь + контроль scope + инкрементальное индексирование |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | Заставить агента верифицировать собственную работу | Самоверификация + обоснованный Q&A + завершение на основе свидетельств |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Построить полный harness с нуля (итоговый проект) | Полный harness: все механизмы + observability + абляционное исследование |```textЭВОЛЮЦИЯ ПРОЕКТОВdiff --git a/docs-readme/tr-TR/README.md b/docs-readme/tr-TR/README.mdindex 1aab471..efd6f8a 100644--- a/docs-readme/tr-TR/README.md+++ b/docs-readme/tr-TR/README.md@@ -315,29 +315,29 @@ Yarı zamanlı ilerliyorsanız her aşama yaklaşık bir hafta sürer. Daha hız| Oturum | Soru | Temel Fikir ||---------|------|-------------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Güçlü modeller gerçek görevlerde neden hâlâ başarısız olur? | Benchmark'lar ile gerçek mühendislik arasındaki yetenek boşluğu |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" aslında ne demek? | Beş alt sistem: talimatlar, durum, doğrulama, kapsam, yaşam döngüsü |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Depo neden tek kayıt sistemi olmalı? | Ajan göremiyorsa, o şey yok demektir |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Tek bir dev talimat dosyası neden yetmez? | Aşamalı açılım: bir harita verin, ansiklopedi değil |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Uzun süren görevler neden sürekliliği kaybeder? | İlerlemeyi diske yaz; kaldığın yerden devam et |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Başlatma neden kendine ait bir aşama olmalı? | Ajan işe başlamadan önce ortamın sağlıklı olduğunu doğrula |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Ajanlar neden sınırı aşar ve yarım bırakır? | Bir seferde tek özellik; bittinin açık tanımı |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Özellik listeleri neden harness'ın temel yapı taşı? | Ajanın görmezden gelemeyeceği, makine okur kapsam sınırları |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Ajanlar neden zaferi çok erken ilan eder? | Doğrulama boşlukları: güven ≠ doğruluk |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Uçtan uca test sonuçları neden değiştirir? | Yalnızca tam hat koşusu gerçek doğrulama sayılır |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Gözlemlenebilirlik neden harness'ın içinde olmalı? | Ajanın ne yaptığını göremiyorsanız, bozduğunu da düzeltemezsiniz |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Her oturum neden temiz bir durumla bitmeli? | Sonraki oturumun başarısı bu oturumun temizliğine bağlıdır |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Güçlü modeller gerçek görevlerde neden hâlâ başarısız olur? | Benchmark'lar ile gerçek mühendislik arasındaki yetenek boşluğu |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" aslında ne demek? | Beş alt sistem: talimatlar, durum, doğrulama, kapsam, yaşam döngüsü |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Depo neden tek kayıt sistemi olmalı? | Ajan göremiyorsa, o şey yok demektir |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Tek bir dev talimat dosyası neden yetmez? | Aşamalı açılım: bir harita verin, ansiklopedi değil |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Uzun süren görevler neden sürekliliği kaybeder? | İlerlemeyi diske yaz; kaldığın yerden devam et |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Başlatma neden kendine ait bir aşama olmalı? | Ajan işe başlamadan önce ortamın sağlıklı olduğunu doğrula |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Ajanlar neden sınırı aşar ve yarım bırakır? | Bir seferde tek özellik; bittinin açık tanımı |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Özellik listeleri neden harness'ın temel yapı taşı? | Ajanın görmezden gelemeyeceği, makine okur kapsam sınırları |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Ajanlar neden zaferi çok erken ilan eder? | Doğrulama boşlukları: güven ≠ doğruluk |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Uçtan uca test sonuçları neden değiştirir? | Yalnızca tam hat koşusu gerçek doğrulama sayılır |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Gözlemlenebilirlik neden harness'ın içinde olmalı? | Ajanın ne yaptığını göremiyorsanız, bozduğunu da düzeltemezsiniz |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Her oturum neden temiz bir durumla bitmeli? | Sonraki oturumun başarısı bu oturumun temizliğine bağlıdır |### Projeler — ders yöntemlerini aynı Electron uygulamasına uygulayan 6 uygulamalı proje| Proje | Ne yaparsınız | Harness Mekanizması ||---------|---------------|----------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Aynı görevi iki kez çalıştırın: yalnızca prompt vs. önce kurallar | Minimal harness: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | Depoyu ajanın okuyabileceği şekilde yeniden yapılandırın | Ajanın okuyabildiği çalışma alanı + kalıcı durum dosyaları |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | Ajanın kaldığı yerden devam etmesini sağlayın | İlerleme günlüğü + oturum devri + çok oturumlu süreklilik |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | Ajanın çok fazla ya da çok az iş yapmasını engelleyin | Runtime geri bildirimi + kapsam kontrolü + artımlı dizinleme |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | Ajanın kendi işini doğrulamasını sağlayın | Öz-doğrulama + dayanaklı Soru-Cevap + kanıta dayalı tamamlama |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | Eksiksiz bir harness'ı sıfırdan kurun (bitirme projesi) | Tam harness: tüm mekanizmalar + gözlemlenebilirlik + ablasyon çalışması |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Aynı görevi iki kez çalıştırın: yalnızca prompt vs. önce kurallar | Minimal harness: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | Depoyu ajanın okuyabileceği şekilde yeniden yapılandırın | Ajanın okuyabildiği çalışma alanı + kalıcı durum dosyaları |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | Ajanın kaldığı yerden devam etmesini sağlayın | İlerleme günlüğü + oturum devri + çok oturumlu süreklilik |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | Ajanın çok fazla ya da çok az iş yapmasını engelleyin | Runtime geri bildirimi + kapsam kontrolü + artımlı dizinleme |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | Ajanın kendi işini doğrulamasını sağlayın | Öz-doğrulama + dayanaklı Soru-Cevap + kanıta dayalı tamamlama |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Eksiksiz bir harness'ı sıfırdan kurun (bitirme projesi) | Tam harness: tüm mekanizmalar + gözlemlenebilirlik + ablasyon çalışması |```textPROJE EVRİMİdiff --git a/docs-readme/uz-UZ/README.md b/docs-readme/uz-UZ/README.mdindex cac0275..fe19bdb 100644--- a/docs-readme/uz-UZ/README.md+++ b/docs-readme/uz-UZ/README.md@@ -316,29 +316,29 @@ Agar parallel oʻqisangiz, har bir bosqich taxminan bir hafta davom etadi. Agar| Sessiya | Savol | Asosiy gʻoya ||---------|-------|--------------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Kuchli modellar nega haqiqiy vazifalarda muvaffaqiyatsiz boʻladi? | Benchmarkʼlar va haqiqiy muhandislik oʻrtasidagi farq |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" nima degani? | Besh quyi tizim: Koʻrsatmalar, Holat, Tekshiruv, Doira, Hayot sikli |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Nega repozitoriy yagona haqiqat manbai boʻlishi kerak? | Agar agent koʻrolmasa, u mavjud emas |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Nega bitta ulkan koʻrsatma fayli muvaffaqiyatsiz boʻladi? | Progressiv ochilish: xarita berish, ensiklopediya emas |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Nega uzoq davom etuvchi vazifalar uzluksizlikni yoʻqotadi? | Taraqqiyotni diskda saqlash; toʻxtagan joydan davom ettirish |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Nega ishga tushirish alohida bosqichga muhtoj? | Agent ishni boshlashdan oldin muhit ishlashini tekshirish |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Nega agentlar haddan oshadi va yarim-yorti tugatadi? | Bir vaqtda bitta funksiya; "Tugadi" ning aniq taʼrifi |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Nega funksiya roʻyxatlari harness primitivlari hisoblanadi? | Agent eʼtiborsiz qoldirolmaydigan, mashina oʻqiyoladigan doira chegaralari |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Nega agentlar juda erta muvaffaqiyat haqida xabar beradi? | Tekshiruv boʻshliqlari: ishonch = toʻgʻrilik emas |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Nega uchdan-uchgacha testlash natijalarni oʻzgartiradi? | Faqat toʻliq pipeline ishga tushirish haqiqiy tekshiruv hisoblanadi |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Nega kuzatuvchanlik harness ichida boʻlishi kerak? | Agent nima qilganini koʻrolmasangiz, u buzgan narsani tuzata olmaysiz |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Nega har bir sessiya toiza holat qoldirishi kerak? | Keyingi sessiyaning muvaffaqiyati shu sessiyaning tozalanishiga bogʻliq |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Kuchli modellar nega haqiqiy vazifalarda muvaffaqiyatsiz boʻladi? | Benchmarkʼlar va haqiqiy muhandislik oʻrtasidagi farq |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" nima degani? | Besh quyi tizim: Koʻrsatmalar, Holat, Tekshiruv, Doira, Hayot sikli |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Nega repozitoriy yagona haqiqat manbai boʻlishi kerak? | Agar agent koʻrolmasa, u mavjud emas |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Nega bitta ulkan koʻrsatma fayli muvaffaqiyatsiz boʻladi? | Progressiv ochilish: xarita berish, ensiklopediya emas |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Nega uzoq davom etuvchi vazifalar uzluksizlikni yoʻqotadi? | Taraqqiyotni diskda saqlash; toʻxtagan joydan davom ettirish |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Nega ishga tushirish alohida bosqichga muhtoj? | Agent ishni boshlashdan oldin muhit ishlashini tekshirish |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Nega agentlar haddan oshadi va yarim-yorti tugatadi? | Bir vaqtda bitta funksiya; "Tugadi" ning aniq taʼrifi |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Nega funksiya roʻyxatlari harness primitivlari hisoblanadi? | Agent eʼtiborsiz qoldirolmaydigan, mashina oʻqiyoladigan doira chegaralari |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Nega agentlar juda erta muvaffaqiyat haqida xabar beradi? | Tekshiruv boʻshliqlari: ishonch = toʻgʻrilik emas |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Nega uchdan-uchgacha testlash natijalarni oʻzgartiradi? | Faqat toʻliq pipeline ishga tushirish haqiqiy tekshiruv hisoblanadi |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Nega kuzatuvchanlik harness ichida boʻlishi kerak? | Agent nima qilganini koʻrolmasangiz, u buzgan narsani tuzata olmaysiz |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Nega har bir sessiya toiza holat qoldirishi kerak? | Keyingi sessiyaning muvaffaqiyati shu sessiyaning tozalanishiga bogʻliq |### Loyihalar — maʼruza usullarini bir xil Electron ilovasiga qoʻllaydigan 6 ta amaliy loyiha| Loyiha | Nima qilasiz | Harness mexanizmi ||---------|--------------|-------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Bir xil vazifani ikki marta bajarish: faqat prompt vs. qoidalarga asoslangan | Minimal harness: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | Repoʼni agent oʻqiy oladigan qayta tuzish | Agent oʻqiy oladigan ish muhiti + doimiy holat fayllari |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | Agentni toʻxtagan joyidan davom ettirish | Taraqqiyot jurnali + sessiya uzatish + koʻp sessiyali uzluksizlik |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | Agentning koʻp yoki oz ishlashining oldini olish | Runtime fikr-mulohaza + doira nazorati + inkremental indekslash |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | Agentni oʻz ishini tekshirishga majburlash | Oʻz-oʻzini tekshirish + asoslangan S&S + dalillarga asoslangan tugatish |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | Toʻliq harnessʼni noldan qurish (yakuniy loyiha) | Toʻliq harness: barcha mexanizmlar + kuzatuvchanlik + ablyatsiya tadqiqoti |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Bir xil vazifani ikki marta bajarish: faqat prompt vs. qoidalarga asoslangan | Minimal harness: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | Repoʼni agent oʻqiy oladigan qayta tuzish | Agent oʻqiy oladigan ish muhiti + doimiy holat fayllari |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | Agentni toʻxtagan joyidan davom ettirish | Taraqqiyot jurnali + sessiya uzatish + koʻp sessiyali uzluksizlik |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | Agentning koʻp yoki oz ishlashining oldini olish | Runtime fikr-mulohaza + doira nazorati + inkremental indekslash |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | Agentni oʻz ishini tekshirishga majburlash | Oʻz-oʻzini tekshirish + asoslangan S&S + dalillarga asoslangan tugatish |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Toʻliq harnessʼni noldan qurish (yakuniy loyiha) | Toʻliq harness: barcha mexanizmlar + kuzatuvchanlik + ablyatsiya tadqiqoti |```textLOYIHA RIVOJLANISHIdiff --git a/docs-readme/vi-VN/README.md b/docs-readme/vi-VN/README.mdindex e61687b..b916aed 100644--- a/docs-readme/vi-VN/README.md+++ b/docs-readme/vi-VN/README.md@@ -316,29 +316,29 @@ Mỗi giai đoạn mất khoảng một tuần nếu bạn học bán thời gia| Phiên | Câu hỏi | Ý tưởng cốt lõi ||-------|---------|------------------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Tại sao các mô hình mạnh vẫn thất bại trên tác vụ thực tế? | Khoảng cách năng lực giữa benchmark và kỹ thuật thực tế |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" thực sự có nghĩa là gì? | Năm hệ thống con: instructions, state, verification, scope, lifecycle |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Tại sao kho mã phải là nguồn chân lý duy nhất? | Nếu agent không thể thấy nó, nó không tồn tại |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Tại sao một tệp hướng dẫn khổng lồ lại thất bại? | Tiết lộ dần: cho một bản đồ, không phải một bộ bách khoa toàn thư |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Tại sao các tác vụ chạy dài mất tính liên tục? | Lưu trữ tiến trình vào đĩa; tiếp tục từ nơi bạn đã dừng |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Tại sao khởi tạo cần một giai đoạn riêng? | Xác minh môi trường khỏe mạnh trước khi agent bắt đầu làm việc |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Tại sao agent lại vượt quá phạm vi và không hoàn thành? | Một tính năng tại một thời điểm; định nghĩa rõ ràng về "hoàn thành" |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Tại sao danh sách tính năng là nguyên thủy của harness? | Ranh giới phạm vi có thể đọc bởi máy mà agent không thể bỏ qua |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Tại sao agent tuyên bố hoàn thành quá sớm? | Khoảng trống kiểm chứng: sự tự tin ≠ sự chính xác |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Tại sao kiểm thử đầu-cuối lại thay đổi kết quả? | Chỉ một lần chạy toàn bộ pipeline mới được tính là kiểm chứng thực sự |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Tại sao khả năng quan sát thuộc về bên trong harness? | Nếu bạn không thể thấy agent đã làm gì, bạn không thể sửa những gì nó đã làm hỏng |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Tại sao mỗi phiên phải để lại trạng thái sạch? | Sự thành công của phiên tiếp theo phụ thuộc vào việc dọn dẹp của phiên này |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | Tại sao các mô hình mạnh vẫn thất bại trên tác vụ thực tế? | Khoảng cách năng lực giữa benchmark và kỹ thuật thực tế |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" thực sự có nghĩa là gì? | Năm hệ thống con: instructions, state, verification, scope, lifecycle |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | Tại sao kho mã phải là nguồn chân lý duy nhất? | Nếu agent không thể thấy nó, nó không tồn tại |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | Tại sao một tệp hướng dẫn khổng lồ lại thất bại? | Tiết lộ dần: cho một bản đồ, không phải một bộ bách khoa toàn thư |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | Tại sao các tác vụ chạy dài mất tính liên tục? | Lưu trữ tiến trình vào đĩa; tiếp tục từ nơi bạn đã dừng |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | Tại sao khởi tạo cần một giai đoạn riêng? | Xác minh môi trường khỏe mạnh trước khi agent bắt đầu làm việc |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | Tại sao agent lại vượt quá phạm vi và không hoàn thành? | Một tính năng tại một thời điểm; định nghĩa rõ ràng về "hoàn thành" |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | Tại sao danh sách tính năng là nguyên thủy của harness? | Ranh giới phạm vi có thể đọc bởi máy mà agent không thể bỏ qua |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | Tại sao agent tuyên bố hoàn thành quá sớm? | Khoảng trống kiểm chứng: sự tự tin ≠ sự chính xác |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | Tại sao kiểm thử đầu-cuối lại thay đổi kết quả? | Chỉ một lần chạy toàn bộ pipeline mới được tính là kiểm chứng thực sự |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | Tại sao khả năng quan sát thuộc về bên trong harness? | Nếu bạn không thể thấy agent đã làm gì, bạn không thể sửa những gì nó đã làm hỏng |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Tại sao mỗi phiên phải để lại trạng thái sạch? | Sự thành công của phiên tiếp theo phụ thuộc vào việc dọn dẹp của phiên này |### Dự án — 6 dự án thực hành áp dụng phương pháp bài giảng vào cùng ứng dụng Electron| Dự án | Những gì bạn làm | Cơ chế Harness ||-------|-------------------|----------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | Chạy cùng tác vụ hai lần: chỉ dùng prompt vs. ưu tiên quy tắc | Harness tối thiểu: AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | Tái cấu trúc kho mã để agent có thể đọc được | Không gian làm việc agent có thể đọc + các tệp trạng thái liên tục |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | Khiến agent tiếp tục từ nơi nó đã dừng | Nhật ký tiến trình + bàn giao phiên + tính liên tục đa phiên |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | Ngăn agent làm quá nhiều hoặc quá ít | Phản hồi thời gian chạy + kiểm soát phạm vi + lập chỉ mục gia tăng |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | Khiến agent tự kiểm chứng công việc của mình | Tự kiểm chứng + Q&A có căn cứ + hoàn thành dựa trên bằng chứng |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | Xây dựng một harness hoàn chỉnh từ đầu (tổng kết) | Harness đầy đủ: tất cả cơ chế + khả năng quan sát + nghiên cứu ablation |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | Chạy cùng tác vụ hai lần: chỉ dùng prompt vs. ưu tiên quy tắc | Harness tối thiểu: AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | Tái cấu trúc kho mã để agent có thể đọc được | Không gian làm việc agent có thể đọc + các tệp trạng thái liên tục |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | Khiến agent tiếp tục từ nơi nó đã dừng | Nhật ký tiến trình + bàn giao phiên + tính liên tục đa phiên |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | Ngăn agent làm quá nhiều hoặc quá ít | Phản hồi thời gian chạy + kiểm soát phạm vi + lập chỉ mục gia tăng |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | Khiến agent tự kiểm chứng công việc của mình | Tự kiểm chứng + Q&A có căn cứ + hoàn thành dựa trên bằng chứng |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | Xây dựng một harness hoàn chỉnh từ đầu (tổng kết) | Harness đầy đủ: tất cả cơ chế + khả năng quan sát + nghiên cứu ablation |```textSỰ PHÁT TRIỂN DỰ ÁNdiff --git a/docs-readme/zh-CN/README.md b/docs-readme/zh-CN/README.mdindex 4759259..4d4e237 100644--- a/docs-readme/zh-CN/README.md+++ b/docs-readme/zh-CN/README.md@@ -313,29 +313,29 @@ Harness Engineering 是围绕模型构建一个完整的工作环境,使其产| 讲次 | 问题 | 核心观点 ||------|------|----------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | 为什么强模型在真实任务上仍然会失败? | 基准测试与真实工程之间的能力差距 |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" 到底是什么意思? | 五个子系统:指令、状态、验证、范围、生命周期 |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | 为什么仓库必须是唯一的真实来源? | 如果代理看不到它,它就不存在 |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | 为什么一个巨大的指令文件会失败? | 渐进式披露:给一张地图,不是一本百科全书 |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | 为什么长时间运行的任务会失去连续性? | 将进度持久化到磁盘;从上次离开处继续 |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | 为什么初始化需要单独的阶段? | 在代理开始工作前验证环境是否健康 |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | 为什么代理会越界和欠完成? | 一次一个功能;明确的完成定义 |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | 为什么功能列表是 Harness 基本单元? | 代理无法忽视的机器可读范围边界 |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | 为什么代理过早宣布完成? | 验证缺口:信心 ≠ 正确 |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | 为什么端到端测试能改变结果? | 只有完整的流水线运行才算真正的验证 |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | 为什么可观测性应该属于 Harness? | 如果你看不到代理做了什么,你就无法修复它破坏的东西 |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | 为什么每次会话都必须留下干净的状态? | 下一次会话的成功取决于这一次会话的清理 |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | 为什么强模型在真实任务上仍然会失败? | 基准测试与真实工程之间的能力差距 |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | "Harness" 到底是什么意思? | 五个子系统:指令、状态、验证、范围、生命周期 |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | 为什么仓库必须是唯一的真实来源? | 如果代理看不到它,它就不存在 |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | 为什么一个巨大的指令文件会失败? | 渐进式披露:给一张地图,不是一本百科全书 |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | 为什么长时间运行的任务会失去连续性? | 将进度持久化到磁盘;从上次离开处继续 |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | 为什么初始化需要单独的阶段? | 在代理开始工作前验证环境是否健康 |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | 为什么代理会越界和欠完成? | 一次一个功能;明确的完成定义 |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | 为什么功能列表是 Harness 基本单元? | 代理无法忽视的机器可读范围边界 |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | 为什么代理过早宣布完成? | 验证缺口:信心 ≠ 正确 |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | 为什么端到端测试能改变结果? | 只有完整的流水线运行才算真正的验证 |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | 为什么可观测性应该属于 Harness? | 如果你看不到代理做了什么,你就无法修复它破坏的东西 |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | 为什么每次会话都必须留下干净的状态? | 下一次会话的成功取决于这一次会话的清理 |### 项目——6 个动手项目,将讲座方法应用到同一个 Electron 应用上| 项目 | 你要做什么 | Harness 机制 ||------|-----------|--------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | 同一个任务运行两次:仅提示词 vs. 规则优先 | 最小 Harness:AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | 重构仓库使代理可读 | 代理可读工作空间 + 持久化状态文件 |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | 让代理从上次离开处继续 | 进度日志 + 会话交接 + 多会话连续性 |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | 阻止代理做得太多或太少 | 运行时反馈 + 范围控制 + 增量索引 |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | 让代理验证自己的工作 | 自验证 + 有据问答 + 基于证据的完成 |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | 从零构建完整的 Harness(毕业项目) | 完整 Harness:所有机制 + 可观测性 + 消融实验 |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | 同一个任务运行两次:仅提示词 vs. 规则优先 | 最小 Harness:AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | 重构仓库使代理可读 | 代理可读工作空间 + 持久化状态文件 |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | 让代理从上次离开处继续 | 进度日志 + 会话交接 + 多会话连续性 |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | 阻止代理做得太多或太少 | 运行时反馈 + 范围控制 + 增量索引 |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | 让代理验证自己的工作 | 自验证 + 有据问答 + 基于证据的完成 |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | 从零构建完整的 Harness(毕业项目) | 完整 Harness:所有机制 + 可观测性 + 消融实验 |```text项目演进diff --git a/docs-readme/zh-TW/README.md b/docs-readme/zh-TW/README.mdindex f54b309..9da768f 100644--- a/docs-readme/zh-TW/README.md+++ b/docs-readme/zh-TW/README.md@@ -309,29 +309,29 @@ Harness Engineering 是關於在模型周圍建構一個完整的工作環境,| 場次 | 問題 | 核心概念 ||---------|----------|-----------|-| [L01](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md) | 為什麼強大的模型在真實任務上仍然會失敗? | 基準測試與真實工程之間的能力差距 |-| [L02](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md) | 「harness」到底是什麼意思? | 五個子系統:指令、狀態、驗證、範圍、生命週期 |-| [L03](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | 為什麼儲存庫必須是唯一的真實來源? | 如果代理看不到它,它就不存在 |-| [L04](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | 為什麼一個巨大的指令檔案會失敗? | 漸進揭露:給一張地圖,不是一本百科全書 |-| [L05](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | 為什麼長時間執行的任務會失去連續性? | 將進度持久化到磁碟;從你停止的地方接續 |-| [L06](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | 為什麼初始化需要自己的階段? | 在代理開始工作之前驗證環境是否健康 |-| [L07](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | 為什麼代理會過度延伸和過早結束? | 每次一個功能;明確的完成定義 |-| [L08](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | 為什麼功能列表是 harness 的基本元素? | 機器可讀的範圍邊界,代理無法忽略 |-| [L09](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | 為什麼代理會過早宣告勝利? | 驗證缺口:信心不等於正確 |-| [L10](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | 為什麼端到端測試能改變結果? | 只有完整的流程執行才算真正的驗證 |-| [L11](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | 為什麼可觀測性應該屬於 harness 內部? | 如果你看不到代理做了什麼,你就無法修復它破壞的東西 |-| [L12](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | 為什麼每個工作階段都必須留下乾淨的狀態? | 下一個工作階段的成功取決於這個工作階段的清理 |+| [L01](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md) | 為什麼強大的模型在真實任務上仍然會失敗? | 基準測試與真實工程之間的能力差距 |+| [L02](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md) | 「harness」到底是什麼意思? | 五個子系統:指令、狀態、驗證、範圍、生命週期 |+| [L03](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md) | 為什麼儲存庫必須是唯一的真實來源? | 如果代理看不到它,它就不存在 |+| [L04](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md) | 為什麼一個巨大的指令檔案會失敗? | 漸進揭露:給一張地圖,不是一本百科全書 |+| [L05](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md) | 為什麼長時間執行的任務會失去連續性? | 將進度持久化到磁碟;從你停止的地方接續 |+| [L06](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md) | 為什麼初始化需要自己的階段? | 在代理開始工作之前驗證環境是否健康 |+| [L07](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md) | 為什麼代理會過度延伸和過早結束? | 每次一個功能;明確的完成定義 |+| [L08](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md) | 為什麼功能列表是 harness 的基本元素? | 機器可讀的範圍邊界,代理無法忽略 |+| [L09](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md) | 為什麼代理會過早宣告勝利? | 驗證缺口:信心不等於正確 |+| [L10](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md) | 為什麼端到端測試能改變結果? | 只有完整的流程執行才算真正的驗證 |+| [L11](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md) | 為什麼可觀測性應該屬於 harness 內部? | 如果你看不到代理做了什麼,你就無法修復它破壞的東西 |+| [L12](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | 為什麼每個工作階段都必須留下乾淨的狀態? | 下一個工作階段的成功取決於這個工作階段的清理 |### 專案 — 6 個動手專案,將講座方法應用於同一個 Electron 應用程式| 專案 | 你要做什麼 | Harness 機制 ||---------|------------|-------------------|-| [P01](../../docs/projects/project-01-baseline-vs-minimal-harness/index.md) | 將同一任務執行兩次:僅提示 vs. 規則優先 | 最小 harness:AGENTS.md + init.sh + feature_list.json |-| [P02](../../docs/projects/project-02-agent-readable-workspace/index.md) | 重構儲存庫,讓代理能夠閱讀它 | 代理可讀的工作空間 + 持久化狀態檔案 |-| [P03](../../docs/projects/project-03-multi-session-continuity/index.md) | 讓代理從上次停止的地方接續 | 進度日誌 + 工作階段交接 + 多工作階段連續性 |-| [P04](../../docs/projects/project-04-incremental-indexing/index.md) | 阻止代理做得太多或太少 | 執行時回饋 + 範圍控制 + 增量索引 |-| [P05](../../docs/projects/project-05-grounded-qa-verification/index.md) | 讓代理驗證自己的工作 | 自我驗證 + 有依據的問答 + 基於證據的完成 |-| [P06](../../docs/projects/project-06-runtime-observability-and-debugging/index.md) | 從零建構一個完整的 harness(畢業專案) | 完整 harness:所有機制 + 可觀測性 + 消融實驗 |+| [P01](../../docs/en/projects/project-01-baseline-vs-minimal-harness/index.md) | 將同一任務執行兩次:僅提示 vs. 規則優先 | 最小 harness:AGENTS.md + init.sh + feature_list.json |+| [P02](../../docs/en/projects/project-02-agent-readable-workspace/index.md) | 重構儲存庫,讓代理能夠閱讀它 | 代理可讀的工作空間 + 持久化狀態檔案 |+| [P03](../../docs/en/projects/project-03-multi-session-continuity/index.md) | 讓代理從上次停止的地方接續 | 進度日誌 + 工作階段交接 + 多工作階段連續性 |+| [P04](../../docs/en/projects/project-04-incremental-indexing/index.md) | 阻止代理做得太多或太少 | 執行時回饋 + 範圍控制 + 增量索引 |+| [P05](../../docs/en/projects/project-05-grounded-qa-verification/index.md) | 讓代理驗證自己的工作 | 自我驗證 + 有依據的問答 + 基於證據的完成 |+| [P06](../../docs/en/projects/project-06-runtime-observability-and-debugging/index.md) | 從零建構一個完整的 harness(畢業專案) | 完整 harness:所有機制 + 可觀測性 + 消融實驗 |```text專案演進diff --git a/docs/ar/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/ar/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex b112f8a..549ea95 100644--- a/docs/ar/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/ar/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 database.- All PRs must pass pytest + mypy --strict + ruff check## Topic Docs-- [API Design Patterns](docs/api-patterns.md) — Required reading when adding endpoints-- [Database Rules](docs/database-rules.md) — Required when modifying database operations-- [Testing Standards](docs/testing-standards.md) — Reference when writing tests+- API Design Patterns (`docs/api-patterns.md`) — Required reading when adding endpoints+- Database Rules (`docs/database-rules.md`) — Required when modifying database operations+- Testing Standards (`docs/testing-standards.md`) — Reference when writing tests```كل مستند موضوعي يكون بين 50 و150 سطرًا، منظمًا حسب الموضوع داخل `docs/` أو بجانب الوحدة المقابلة. يقرأه الوكيل فقط عند الحاجة. مثل مكعبات التنظيم داخل حقيبة السفر: الملابس في مكعب، أدوات العناية في آخر، الشواحن في ثالث. العثور على شيء لا يتطلب إفراغ الحقيبة كلها.diff --git a/docs/de/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/de/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex b775e16..2f399cb 100644--- a/docs/de/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/de/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 database.- All PRs must pass pytest + mypy --strict + ruff check## Topic Docs-- [API Design Patterns](docs/api-patterns.md) — Required reading when adding endpoints-- [Database Rules](docs/database-rules.md) — Required when modifying database operations-- [Testing Standards](docs/testing-standards.md) — Reference when writing tests+- API Design Patterns (`docs/api-patterns.md`) — Required reading when adding endpoints+- Database Rules (`docs/database-rules.md`) — Required when modifying database operations+- Testing Standards (`docs/testing-standards.md`) — Reference when writing tests```Jedes Themendokument umfasst 50-150 Zeilen, nach Thema im `docs/`-Verzeichnis oder neben dem entsprechenden Modul organisiert. Der Agent liest es nur bei Bedarf. Wie Packwürfel im Koffer: Unterwäsche in einem, Toilettenartikel in einem anderen, Ladegeräte in einem dritten. Um etwas zu finden, musst du nicht den ganzen Koffer ausleeren.diff --git a/docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 88fa271..7006c9b 100644--- a/docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 database.- All PRs must pass pytest + mypy --strict + ruff check## Topic Docs-- [API Design Patterns](docs/api-patterns.md) — Required reading when adding endpoints-- [Database Rules](docs/database-rules.md) — Required when modifying database operations-- [Testing Standards](docs/testing-standards.md) — Reference when writing tests+- API Design Patterns (`docs/api-patterns.md`) — Required reading when adding endpoints+- Database Rules (`docs/database-rules.md`) — Required when modifying database operations+- Testing Standards (`docs/testing-standards.md`) — Reference when writing tests```Each topic document is 50-150 lines, organized by subject in the `docs/` directory or next to the corresponding module. The agent only reads them when needed. Like packing cubes in a suitcase — underwear in one cube, toiletries in another, chargers in a third. Finding things doesn't require emptying the whole bag.diff --git a/docs/es/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/es/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 640d9db..4252595 100644--- a/docs/es/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/es/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 database.- All PRs must pass pytest + mypy --strict + ruff check## Topic Docs-- [API Design Patterns](docs/api-patterns.md) — Required reading when adding endpoints-- [Database Rules](docs/database-rules.md) — Required when modifying database operations-- [Testing Standards](docs/testing-standards.md) — Reference when writing tests+- API Design Patterns (`docs/api-patterns.md`) — Required reading when adding endpoints+- Database Rules (`docs/database-rules.md`) — Required when modifying database operations+- Testing Standards (`docs/testing-standards.md`) — Reference when writing tests```Cada documento temático debe tener 50-150 líneas, organizado por tema en `docs/` o junto al módulo correspondiente. El agente solo lo lee cuando hace falta. Como cubos de organización dentro de una maleta: ropa interior en uno, artículos de aseo en otro, cargadores en un tercero. Encontrar algo no requiere vaciar toda la bolsa.diff --git a/docs/fr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/fr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 7102d89..068dc34 100644--- a/docs/fr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/fr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 database.- All PRs must pass pytest + mypy --strict + ruff check## Topic Docs-- [API Design Patterns](docs/api-patterns.md) — Required reading when adding endpoints-- [Database Rules](docs/database-rules.md) — Required when modifying database operations-- [Testing Standards](docs/testing-standards.md) — Reference when writing tests+- API Design Patterns (`docs/api-patterns.md`) — Required reading when adding endpoints+- Database Rules (`docs/database-rules.md`) — Required when modifying database operations+- Testing Standards (`docs/testing-standards.md`) — Reference when writing tests```Chaque document thématique fait 50-150 lignes, organisé par sujet dans `docs/` ou près du module correspondant. L'agent ne les lit que lorsque c'est nécessaire. Comme des pochettes de rangement dans une valise : les sous-vêtements dans l'une, les produits de toilette dans une autre, les chargeurs dans une troisième. Trouver quelque chose n'exige pas de vider tout le sac.diff --git a/docs/ja/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/ja/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex a1bf3ef..9dfc197 100644--- a/docs/ja/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/ja/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 database.- All PRs must pass pytest + mypy --strict + ruff check## Topic Docs-- [API Design Patterns](docs/api-patterns.md) — Required reading when adding endpoints-- [Database Rules](docs/database-rules.md) — Required when modifying database operations-- [Testing Standards](docs/testing-standards.md) — Reference when writing tests+- API Design Patterns (`docs/api-patterns.md`) — Required reading when adding endpoints+- Database Rules (`docs/database-rules.md`) — Required when modifying database operations+- Testing Standards (`docs/testing-standards.md`) — Reference when writing tests```各トピック文書は 50-150 行にし、`docs/` ディレクトリか対応モジュールの近くで主題ごとに整理する。エージェントは必要なときだけ読む。スーツケースのパッキングキューブのようなものだ。下着は 1 つ、洗面用品は別、充電器はさらに別。探し物のためにバッグ全体を空にする必要はない。diff --git a/docs/ko/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/ko/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex a8e0fa1..078026f 100644--- a/docs/ko/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/ko/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI 백엔드, PostgreSQL 15 데이터베이스.- 모든 PR은 pytest + mypy --strict + ruff check를 통과해야 함## 주제 문서-- [API 설계 패턴](docs/api-patterns.md) — 엔드포인트 추가 시 필독-- [데이터베이스 규칙](docs/database-rules.md) — 데이터베이스 작업 수정 시 필독-- [테스트 표준](docs/testing-standards.md) — 테스트 작성 시 참조+- API 설계 패턴 (`docs/api-patterns.md`) — 엔드포인트 추가 시 필독+- 데이터베이스 규칙 (`docs/database-rules.md`) — 데이터베이스 작업 수정 시 필독+- 테스트 표준 (`docs/testing-standards.md`) — 테스트 작성 시 참조```각 주제 문서는 50~150줄이며, `docs/` 디렉터리 또는 해당 모듈 옆에 주제별로 정리됩니다. 에이전트는 필요할 때만 읽습니다. 여행 가방 안의 패킹 큐브와 같습니다. 속옷은 한 큐브에, 세면도구는 다른 큐브에, 충전기는 세 번째 큐브에. 전체 가방을 비우지 않아도 원하는 것을 찾을 수 있습니다.diff --git a/docs/ru/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/ru/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 709b865..2ae3160 100644--- a/docs/ru/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/ru/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 database.- All PRs must pass pytest + mypy --strict + ruff check## Topic Docs-- [API Design Patterns](docs/api-patterns.md) — Required reading when adding endpoints-- [Database Rules](docs/database-rules.md) — Required when modifying database operations-- [Testing Standards](docs/testing-standards.md) — Reference when writing tests+- API Design Patterns (`docs/api-patterns.md`) — Required reading when adding endpoints+- Database Rules (`docs/database-rules.md`) — Required when modifying database operations+- Testing Standards (`docs/testing-standards.md`) — Reference when writing tests```Каждый тематический документ — 50–150 строк, организованы по темам в каталоге `docs/` или рядом с соответствующим модулем. Агент читает их только при необходимости. Как органайзеры в чемодане: бельё в одном, косметика в другом, зарядки в третьем. Не нужно вытряхивать весь чемодан, чтобы что-то найти.diff --git a/docs/tr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/tr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 26697a6..45f6740 100644--- a/docs/tr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/tr/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 veritabanı.- Tüm PR'lar pytest + mypy --strict + ruff check'i geçmeli## Konu Dokümanları-- [API Tasarım Kalıpları](docs/api-patterns.md) — Uç nokta eklerken okunması zorunlu-- [Veritabanı Kuralları](docs/database-rules.md) — Veritabanı işlemleri değiştirilirken zorunlu-- [Test Standartları](docs/testing-standards.md) — Test yazarken referans+- API Tasarım Kalıpları (`docs/api-patterns.md`) — Uç nokta eklerken okunması zorunlu+- Veritabanı Kuralları (`docs/database-rules.md`) — Veritabanı işlemleri değiştirilirken zorunlu+- Test Standartları (`docs/testing-standards.md`) — Test yazarken referans```Her konu dokümanı 50-150 satırdır, `docs/` dizininde veya ilgili modülün yanında konuya göre organize edilmiştir. Ajan bunları yalnızca gerektiğinde okur. Bavuldaki paket küpleri gibi — bir küpte iç çamaşırı, diğerinde tuvalet malzemeleri, üçüncüsünde şarj cihazları. Bir şey bulmak tüm çantayı boşaltmayı gerektirmez.diff --git a/docs/uz/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/uz/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 435cdca..84abee4 100644--- a/docs/uz/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/uz/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI backend, PostgreSQL 15 maʼlumotlar bazasi.- Barcha PRʼlar pytest + mypy --strict + ruff check dan oʻtishi shart## Mavzuli hujjatlar-- [API dizayn andozalari](docs/api-patterns.md) — Endpointʼlar qoʻshganda oʻqish majburiy-- [Maʼlumotlar bazasi qoidalari](docs/database-rules.md) — Maʼlumotlar bazasi amallarini oʻzgartirganda kerak boʻladi-- [Testlash standartlari](docs/testing-standards.md) — Test yozish uchun qoʻllanma+- API dizayn andozalari (`docs/api-patterns.md`) — Endpointʼlar qoʻshganda oʻqish majburiy+- Maʼlumotlar bazasi qoidalari (`docs/database-rules.md`) — Maʼlumotlar bazasi amallarini oʻzgartirganda kerak boʻladi+- Testlash standartlari (`docs/testing-standards.md`) — Test yozish uchun qoʻllanma```Har bir mavzu hujjati `docs/` katalogida yoki tegishli modulning yonida mavzu boʻyicha tashkillashtirilgan holda 50-150 qatordan iborat boʻladi. Agent ularni faqat kerak boʻlganda oʻqiydi. Xuddi chamadondagi taqsimlagichlar (packing cubes) kabi — ichki kiyimlar bir boʻlimda, yuvinish vositalari ikkinchisida, quvvatlagichlar uchinchisida. Biror narsani qidirib topish uchun butun sumkani boʻshatish shart emas.diff --git a/docs/vi/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/vi/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 0ee754e..9e15bf8 100644--- a/docs/vi/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/vi/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Backend FastAPI Python 3.11, cơ sở dữ liệu PostgreSQL 15.- Tất cả PR phải vượt qua pytest + mypy --strict + ruff check## Tài liệu Chủ đề-- [Mẫu Thiết kế API](docs/api-patterns.md) — Đọc bắt buộc khi thêm endpoint-- [Quy tắc Cơ sở dữ liệu](docs/database-rules.md) — Bắt buộc khi sửa đổi hoạt động cơ sở dữ liệu-- [Tiêu chuẩn Testing](docs/testing-standards.md) — Tham khảo khi viết test+- Mẫu Thiết kế API (`docs/api-patterns.md`) — Đọc bắt buộc khi thêm endpoint+- Quy tắc Cơ sở dữ liệu (`docs/database-rules.md`) — Bắt buộc khi sửa đổi hoạt động cơ sở dữ liệu+- Tiêu chuẩn Testing (`docs/testing-standards.md`) — Tham khảo khi viết test```Mỗi tài liệu chủ đề có 50-150 dòng, được tổ chức theo chủ đề trong thư mục `docs/` hoặc cạnh module tương ứng. Agent chỉ đọc chúng khi cần. Giống như túi đựng đồ trong vali — đồ lót một túi, đồ vệ sinh một túi, dây sạc một túi. Tìm đồ không cần đổ toàn bộ túi.diff --git a/docs/zh-TW/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/zh-TW/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 8ff9acf..49cebaf 100644--- a/docs/zh-TW/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/zh-TW/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI 後端,PostgreSQL 15 資料庫。- 所有 PR 必須通過 pytest + mypy --strict + ruff check## 专题文檔-- [API 設計規範](docs/api-patterns.md) — 添加新端点時必讀-- [資料庫操作约束](docs/database-rules.md) — 涉及資料庫修改時必讀-- [測試標準](docs/testing-standards.md) — 编寫測試時参考+- API 設計規範 (`docs/api-patterns.md`) — 添加新端点時必讀+- 資料庫操作约束 (`docs/database-rules.md`) — 涉及資料庫修改時必讀+- 測試標準 (`docs/testing-standards.md`) — 编寫測試時参考```每個專題文檔 50-150 行,按主題放在 `docs/` 目錄下或對應模塊目錄旁。Agent 只在需要時才去讀。就像行李箱裡的收納袋——內衣一個袋,洗漱一個袋,充電器一個袋。找東西不用翻整個箱子。diff --git a/docs/zh/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md b/docs/zh/lectures/lecture-04-why-one-giant-instruction-file-fails/index.mdindex 1839287..af859ac 100644--- a/docs/zh/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md+++ b/docs/zh/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md@@ -78,9 +78,9 @@ Python 3.11 FastAPI 后端,PostgreSQL 15 数据库。- 所有 PR 必须通过 pytest + mypy --strict + ruff check## 专题文档-- [API 设计规范](docs/api-patterns.md) — 添加新端点时必读-- [数据库操作约束](docs/database-rules.md) — 涉及数据库修改时必读-- [测试标准](docs/testing-standards.md) — 编写测试时参考+- API 设计规范 (`docs/api-patterns.md`) — 添加新端点时必读+- 数据库操作约束 (`docs/database-rules.md`) — 涉及数据库修改时必读+- 测试标准 (`docs/testing-standards.md`) — 编写测试时参考```每个专题文档 50-150 行,按主题放在 `docs/` 目录下或对应模块目录旁。Agent 只在需要时才去读。就像行李箱里的收纳袋——内衣一个袋,洗漱一个袋,充电器一个袋。找东西不用翻整个箱子。diff --git a/projects/project-01/README-CN.md b/projects/project-01/README-CN.mdindex 88baea1..a8e3243 100644--- a/projects/project-01/README-CN.md+++ b/projects/project-01/README-CN.md@@ -54,5 +54,5 @@ documents and answer questions." 请用 solution 中的 harness 文件把这句## 对应课件-- [Lecture 01: 为什么强大的模型仍然会失败](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md)-- [Lecture 02: Harness 到底是什么](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md)+- [Lecture 01: 为什么强大的模型仍然会失败](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md)+- [Lecture 02: Harness 到底是什么](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md)diff --git a/projects/project-01/README-KO.md b/projects/project-01/README-KO.mdindex 284016e..199211b 100644--- a/projects/project-01/README-KO.md+++ b/projects/project-01/README-KO.md@@ -42,5 +42,5 @@ npm install## 관련 강의-- [강의 01: 강력한 모델이 왜 여전히 실패하는가](../../docs/lectures/lecture-01-why-capable-agents-still-fail/index.md)-- [강의 02: 하네스가 실제로 무엇인가](../../docs/lectures/lecture-02-what-a-harness-actually-is/index.md)+- [강의 01: 강력한 모델이 왜 여전히 실패하는가](../../docs/en/lectures/lecture-01-why-capable-agents-still-fail/index.md)+- [강의 02: 하네스가 실제로 무엇인가](../../docs/en/lectures/lecture-02-what-a-harness-actually-is/index.md)diff --git a/projects/project-02/README-CN.md b/projects/project-02/README-CN.mdindex e98b9da..0438ed8 100644--- a/projects/project-02/README-CN.md+++ b/projects/project-02/README-CN.md@@ -45,5 +45,5 @@ harness。本项目要补的是 Project 02 的产品切片,以及让第二个## 对应课件-- [Lecture 03: 让仓库成为唯一的真相来源](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md)-- [Lecture 04: 拆分指令文件,而不是一个巨型文件](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md)+- [Lecture 03: 让仓库成为唯一的真相来源](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md)+- [Lecture 04: 拆分指令文件,而不是一个巨型文件](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md)diff --git a/projects/project-02/README-KO.md b/projects/project-02/README-KO.mdindex cfe7031..6f98fd2 100644--- a/projects/project-02/README-KO.md+++ b/projects/project-02/README-KO.md@@ -35,5 +35,5 @@ npm install## 관련 강의-- [강의 03: 저장소가 왜 단일 진실 원천이어야 하는가](../../docs/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md)-- [강의 04: 왜 하나의 거대한 지시 파일이 실패하는가](../../docs/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md)+- [강의 03: 저장소가 왜 단일 진실 원천이어야 하는가](../../docs/en/lectures/lecture-03-why-the-repository-must-become-the-system-of-record/index.md)+- [강의 04: 왜 하나의 거대한 지시 파일이 실패하는가](../../docs/en/lectures/lecture-04-why-one-giant-instruction-file-fails/index.md)diff --git a/projects/project-03/README-CN.md b/projects/project-03/README-CN.mdindex 1c55c25..59558d6 100644--- a/projects/project-03/README-CN.md+++ b/projects/project-03/README-CN.md@@ -45,5 +45,5 @@ Project 03 starter 不是空应用,而是 Project 02 加上未完成的索引## 对应课件-- [Lecture 05: 保持跨会话上下文](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md)-- [Lecture 06: 每次会话前先初始化](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md)+- [Lecture 05: 保持跨会话上下文](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md)+- [Lecture 06: 每次会话前先初始化](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md)diff --git a/projects/project-03/README-KO.md b/projects/project-03/README-KO.mdindex 1366f18..6421e06 100644--- a/projects/project-03/README-KO.md+++ b/projects/project-03/README-KO.md@@ -34,5 +34,5 @@ npm install## 관련 강의-- [강의 05: 세션 간 컨텍스트를 유지하는 방법](../../docs/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md)-- [강의 06: 모든 에이전트 세션 전에 초기화가 필요한 이유](../../docs/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md)+- [강의 05: 세션 간 컨텍스트를 유지하는 방법](../../docs/en/lectures/lecture-05-why-long-running-tasks-lose-continuity/index.md)+- [강의 06: 모든 에이전트 세션 전에 초기화가 필요한 이유](../../docs/en/lectures/lecture-06-why-initialization-needs-its-own-phase/index.md)diff --git a/projects/project-04/README-CN.md b/projects/project-04/README-CN.mdindex 98cadc8..a601a3d 100644--- a/projects/project-04/README-CN.md+++ b/projects/project-04/README-CN.md@@ -46,5 +46,5 @@ Project 04 是调试和护栏练习。starter 已有 Project 03 的产品切片## 对应课件-- [Lecture 07: 给代理划定清晰的任务边界](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md)-- [Lecture 08: 用功能列表约束代理行为](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md)+- [Lecture 07: 给代理划定清晰的任务边界](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md)+- [Lecture 08: 用功能列表约束代理行为](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md)diff --git a/projects/project-04/README-KO.md b/projects/project-04/README-KO.mdindex 7e65a25..1514235 100644--- a/projects/project-04/README-KO.md+++ b/projects/project-04/README-KO.md@@ -36,5 +36,5 @@ npm install## 관련 강의-- [강의 07: 에이전트에게 명확한 작업 경계를 설정하는 방법](../../docs/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md)-- [강의 08: 기능 목록으로 에이전트 행동을 제약하는 방법](../../docs/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md)+- [강의 07: 에이전트에게 명확한 작업 경계를 설정하는 방법](../../docs/en/lectures/lecture-07-why-agents-overreach-and-under-finish/index.md)+- [강의 08: 기능 목록으로 에이전트 행동을 제약하는 방법](../../docs/en/lectures/lecture-08-why-feature-lists-are-harness-primitives/index.md)diff --git a/projects/project-05/README-CN.md b/projects/project-05/README-CN.mdindex eab5ea2..a87a089 100644--- a/projects/project-05/README-CN.md+++ b/projects/project-05/README-CN.md@@ -51,5 +51,5 @@ cd solution/plan-gen-eval && npm install # 完整三角色模式## 对应课件-- [Lecture 09: 阻止代理过早宣布胜利](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md)-- [Lecture 10: 只有全流程运行才算真正的验证](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md)+- [Lecture 09: 阻止代理过早宣布胜利](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md)+- [Lecture 10: 只有全流程运行才算真正的验证](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md)diff --git a/projects/project-05/README-KO.md b/projects/project-05/README-KO.mdindex cfe1a19..2893d0b 100644--- a/projects/project-05/README-KO.md+++ b/projects/project-05/README-KO.md@@ -37,5 +37,5 @@ cd solution/plan-gen-eval && npm install # 완전한 3역할 모드## 관련 강의-- [강의 09: 에이전트가 너무 일찍 완료를 선언하지 못하도록 막는 방법](../../docs/lectures/lecture-09-why-agents-declare-victory-too-early/index.md)-- [강의 10: 전체 파이프라인 실행만이 진정한 검증인 이유](../../docs/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md)+- [강의 09: 에이전트가 너무 일찍 완료를 선언하지 못하도록 막는 방법](../../docs/en/lectures/lecture-09-why-agents-declare-victory-too-early/index.md)+- [강의 10: 전체 파이프라인 실행만이 진정한 검증인 이유](../../docs/en/lectures/lecture-10-why-end-to-end-testing-changes-results/index.md)diff --git a/projects/project-06/README-CN.md b/projects/project-06/README-CN.mdindex b0f2eda..26214bd 100644--- a/projects/project-06/README-CN.md+++ b/projects/project-06/README-CN.md@@ -54,5 +54,5 @@ Project 06 是完整产品 + 弱 harness 表面,与完整产品 + 强 harness## 对应课件-- [Lecture 11: 让代理的运行时可观测](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md)-- [Lecture 12: 每次会话都要留下干净的状态](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md)+- [Lecture 11: 让代理的运行时可观测](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md)+- [Lecture 12: 每次会话都要留下干净的状态](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md)diff --git a/projects/project-06/README-KO.md b/projects/project-06/README-KO.mdindex ea1cfc3..559ccdc 100644--- a/projects/project-06/README-KO.md+++ b/projects/project-06/README-KO.md@@ -43,5 +43,5 @@ npm install## 관련 강의-- [강의 11: 에이전트의 런타임을 가관측하게 만드는 방법](../../docs/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md)-- [강의 12: 모든 세션이 왜 깨끗한 상태를 남겨야 하는가](../../docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md)+- [강의 11: 에이전트의 런타임을 가관측하게 만드는 방법](../../docs/en/lectures/lecture-11-why-observability-belongs-inside-the-harness/index.md)+- [강의 12: 모든 세션이 왜 깨끗한 상태를 남겨야 하는가](../../docs/en/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md)diff --git a/skills/harness-creator/references/tool-registry-pattern.md b/skills/harness-creator/references/tool-registry-pattern.mdindex 8bd42c7..1a38db9 100644--- a/skills/harness-creator/references/tool-registry-pattern.md+++ b/skills/harness-creator/references/tool-registry-pattern.md@@ -162,7 +162,7 @@ protected_commands:## Related Patterns- [Lifecycle & Bootstrap](lifecycle-bootstrap-pattern.md) — How tools are registered at init-- [Hook Lifecycle](hook-lifecycle-pattern.md) — Pre/post tool execution hooks+- Hook Lifecycle (`hook-lifecycle-pattern.md`) — Pre/post tool execution hooks## Template: Tool Safety Checklist