| 2026-07-13 |

Автономность мелких моделей: OUTPUT DISCIPLINE, milestone-todo, перехват финала хода
...
Два последовательных захода над одной проблемой — мелкие модели (12–30B) в navi_code
теряют автономность на трудных шагах: «остановился поболтать» вместо действия и
слишком большое расстояние между пунктами плана.
Заход 1 (З1–З3):
- З1: OUTPUT DISCIPLINE в системном промпте navi_code — «act, don't announce»,
без few-shot антипримеров. Контракт хода: ответ без tool_calls = конец хода, поэтому
объявление намерения текстом убивает автономность; правила заставляют вызывать
инструмент в том же ходе.
- З2: плоский todo + метка группы milestone + декомпозиция. _parse_plan_steps
возвращает list[tuple[milestone, text]]; milestone — метка группировки (не сущность,
без статуса), «done» вычисляется при рендеринге; подшаги = больше плоских шагов
(без вложенности). TUI side-panel группирует по milestone (плоский фолбэк при пустом
milestone). Plan depth: max 15→20 + правило декомпозиции.
- З3: adaptive re-plan «длинный шаг» — nudge «разбей шаг» при in_progress ≥ порога
итераций без смены todo (порог 4, раньше общего anti-stall warning на 8).
Заход 2 (шаги 1–3, после cloud-теста 31b vs 12b):
Корневая структурная причина: весь спасательный механизм (anti-stall warning с явным
предложением reflect, adaptive re-plan) живёт только внутри tool-цикла — nudge
инжектируется в pre_turn *следующей* итерации, которой при «остановился поболтать»
нет (ход закрылся по return до post_turn). 31b застревала через «продолжаю
tool-итерации» → дожала до warning → спаслась; 12b — через «замолчала текстом» → мимо
всех nudge.
- Шаг 1: перехват финала хода. Если модель выдала bare-text, но в todo есть открытые
шаги (pending/in_progress) и лимит не исчерпан — НЕ эмитить StreamEnd, а сохранить
ассистентский текст в session.context, поставить системный nudge и continue
(без StreamEnd, без workers — консистентно с multi-iteration tool-турами). Счётчик
final_interceptions на AgentTurnContext, лимит final_intercept_limit (default 2),
эскалация жёсткости (мягкий → «second stop»). has_open_steps в todo.py: пустой
todo → False (защита casual-сообщений), failed/skipped терминальны. Профильные
флаги final_intercept_enabled/limit в base.py + loader + admin.
- Шаг 2: жёсткий reflect-триггер в промпте — «~3 tool attempts on the same step
without progress → call reflect IN THIS TURN (tool call, not reasoning aloud)».
- Шаг 3: открыть replan для застревания — «call replan when reflect showed the whole
approach is dead (not one failed step, but the approach itself)».
Тесты: 874 passed, 1 skipped. Новые — has_open_steps (5), final intercept (5),
milestone-группировка, adaptive long-step nudge, парсер шагов с milestone-маркером.
cloud: navi_code model → gemma4:31b-cloud для тестирования догадки (31b признала
застревание, 12b — нет); .env cloud-host уже gitignored.
Co-Authored-By: Claude <noreply@anthropic.com>
Eugene Sukhodolskiy
committed
21 hours ago
|
| 2026-07-11 |

Isolate sub-agent todo + render live todo in TUI side panel
...
Phase 1 — sub-agent todo isolation (backend):
- Add current_todo_session_id ContextVar; subagent_runner scopes it to the
sub-agent's ephemeral run id so its auto-populated plan and todo updates
land in an isolated KV row instead of clobbering the parent session's todo
(which the parent's goal-anchoring reads every iteration).
- todo._sid() and planning.set_tasks prefer current_todo_session_id; the
parent run leaves it unset, so all existing todo consumers (anti-stall,
goal anchor, get_progress_message) behave exactly as before.
Phase 2 — live todo in the TUI right column:
- TodoUpdated event + emit it from the agent loop after planning auto-populate
and after each tool-execution turn.
- GET /sessions/{id}/todos reads the parent session's todo KV row (explicit
user_id/session_id, optional injected kv).
- api.get_todos + TodoList/TodoPanel widgets: status-coloured markers
(pending dim, in_progress accent+bold, done success, failed error, skipped
dim), progress header, scrollable panel below the auto-height info block.
- Hybrid delivery: REST seeds the panel on attach/switch, todo_updated WS
events update it live.
Sub-agent todos as nested sub-lists is deferred to a later phase.
Co-Authored-By: Claude <noreply@anthropic.com>
Eugene Sukhodolskiy
committed
2 days ago
|
| 2026-07-09 |

agent: bounded autonomy — scope boundary + observe-vs-act
...
navi_code had unwanted "free flight": an observe request ("look at a
directory") triggered the full Phase 3 plan with milestones + auto-todo,
and goal_anchoring then drove the agent to finish those steps, climbing
into sibling projects and executing milestone docs it found.
Two toggleable, default-off profile flags (on for navi_code):
- scope_boundary_enabled: injects a standing system message keeping the
agent within the literally requested scope; forbids acting on
discovered TODO/roadmap/milestone docs (report only).
- observe_skips_plan_enabled: Phase 1 classifies MODE: observe|act; an
observe request skips Phase 2/3 — no multi-step plan, no auto-todo, no
"execute step by step" prompt. The agent just gathers info and answers.
Independent of force_plan (observe on the first message still skips).
Free flight stays reproducible by flipping both flags off.
Co-Authored-By: Claude <noreply@anthropic.com>
Eugene Sukhodolskiy
committed
4 days ago
|
| 2026-06-26 |
agent: skip planning for casual greetings + strengthen DIRECT shortcut in Phase 1
...
- Add fast _is_casual_message heuristic in navi/core/agent.py. Greetings and
social chat (e.g. 'привет', 'как дела', 'hi', 'thanks') bypass planning even
on the first session message, unless planning_mandatory is enabled.
- Strengthen Phase 1 planning prompt in navi/core/planning.py: explicitly
require DIRECT output for greetings, simple questions, and one-step
instructions.
- Fix broken ContextCompressed import in navi/core/compressor.py.
- Add unit tests covering the new heuristic and DIRECT prompt.
Co-Authored-By: Claude <noreply@anthropic.com>
Eugene Sukhodolskiy
committed
18 days ago
|
| 2026-05-25 |
Review fixes: restore _build_sessions, fix flags, search filter, tests
...
- Restored _load_messages_map and _build_sessions helpers that were
accidentally dropped in Phase 5 (list_all/list_page/search_list
called them but they were missing, causing NameError at runtime)
- _build_sessions now filters messages by is_display so list methods
return consistent display-only history like get()
- count_all/search_list EXISTS subquery now filters to is_display=true
so search only matches visible chat messages
- Updated pg_session_store docstring to remove stale dual-write claim
- compressor summary_msg now defaults to is_display=False
- Added unit tests for message flags (agent, compressor, planning)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Eugene Sukhodolskiy
committed
on 25 May
|
| 2026-05-12 |
Clarify knowledge persistence prompts
Eugene Sukhodolskiy
committed
on 12 May
|
| 2026-04-29 |
Add 62 tests across all planned phases + fix integration flakiness
...
- Phase 3: 19 API route integration tests (health, agents, sessions, messages)
- Phase 3: 7 WebSocket integration tests (connect, send, replay, invalid, stop)
- Phase 4: 9 agent tests (_check_context_size, _iter_stream_guarded)
- Phase 4: 5 planning tests (_parse_plan_steps)
- Phase 5: 22 tool tests (filesystem 13, code_exec 5, terminal 4)
- Fix flaky integration tests by patching module-level singletons
(_session_store, _registries, _workers) instead of getter functions,
because FastAPI Depends() captures the original function at import time.
- Update docs/testing.md coverage table (150 total tests)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Eugene Sukhodolskiy
committed
on 29 Apr
|