diff --git a/.serena/.gitignore b/.serena/.gitignore
new file mode 100644
index 0000000..2e510af
--- /dev/null
+++ b/.serena/.gitignore
@@ -0,0 +1,2 @@
+/cache
+/project.local.yml
diff --git a/.serena/memories/conventions.md b/.serena/memories/conventions.md
new file mode 100644
index 0000000..1e7d79e
--- /dev/null
+++ b/.serena/memories/conventions.md
@@ -0,0 +1,39 @@
+# conventions
+
+## Стиль / кодстайл
+- Стандартный Go-стиль; гофм `gofmt`/`go fmt ./...`. Документация-комментарии и
+  package-doc на русском языке (в START-комментариях файлов и doc-комментариях).
+- Типизация: строгие типы, интерфейсы для абстракций (Decider, LiveProber).
+- Свой тип `config.Duration` для времени (YAML-строки "5s"/"10m"), метод `.Duration()`.
+
+## Обработка ошибок
+- Ошибки классифицируются по идентификаторам классов в исходниках (см. ниже).
+- Ошибка-обёртка: `fmt.Errorf("%w: %v", ErrXxx, err)`.
+- `errors.Join` для склейки нескольких ошибок валидации (config.Validate).
+
+## Классы ошибок (маркируются в коде, документированы в README)
+| Блок | Коды | Где |
+|---|---|---|
+| C  | C1–C4 | internal/config |
+| A  | A1–A4 | internal/analyst |
+| M  | M1–M5 | internal/chat |
+| O  | O1–O4 | internal/opencode |
+| S  | S1–S5 | internal/storage |
+| W  | W1–W5 | internal/worker |
+| E  | E1–E4 | internal/worker (репозитории) |
+| R  | R1–R6 | internal/worker/review_errors.go |
+| U  | U1–U6 | internal/update |
+
+## Архитектурные конвенции
+- **Composition root** — internal/app; подсистемы собираются там, лимиты Core
+  (MaxTurns=15, MaxConfirmCycles=3, MaxQuestionsPerTurn=5) в core.New.
+- **Агенты** (analyst.md/dev.md/reviewer.md) — markdown-промпты, встроены через go:embed
+  (internal/agents/*.md + embed.go), распаковываются в config_dir. Вердикт — строгий JSON.
+- Репо-клонирование/воркеры — через gitops; ветки задач `feat/<taskTag>` (см. mem:core).
+- Обратная совместимость: поле `Repo` (одиночный) и `Repos` (список); EffectiveRepos/
+  SetReposFromDB/ReposJoined в storage/models.go.
+
+## Версии
+- `app.Version` — семантическая major.minor.patch (ручной инкремент: patch=фиксы,
+  minor=новая обратно-совместимая функциональность, major=несовместимые изменения).
+- `main.version` (ldflag) — build-идентификатор `commit-<sha7>`, отдельно от app.Version.
\ No newline at end of file
diff --git a/.serena/memories/core.md b/.serena/memories/core.md
new file mode 100644
index 0000000..6ae8029
--- /dev/null
+++ b/.serena/memories/core.md
@@ -0,0 +1,51 @@
+# core
+
+Ratatoskr-go — оркестратор конвейера Ratatoskr (порт с Python на Go) в единый
+статический бинарь (CGO_ENABLED=0). Субагенты запускаются через внешний процесс
+[opencode](https://opencode.ai). Взаимодействие — Telegram-бот.
+
+## Структура (модули internal/)
+
+```
+cmd/ratatoskr/   точка входа, сборка бинаря; main.version и main.updateToken вшиваются ldflag'ом
+internal/
+  app/           composition root/DI: App.New -> config.Load+Validate, ResolveExePaths, storage, Runner, Analyst, Core, Worker, Updater. packageOwner="kamelion", Version="0.1.0"
+  config/        YAML+env загрузка (${VAR:-default}), defaults, validate C1-C4
+  chat/          мультиканальный Router; telegram — long-poll канал. Коды M1-M5
+  core/          state-machine задач + Decider/analyst интерфейс. Коды D3/D4
+  analyst/       аналитик: промпт + разбор JSON-вердикта (opencode agent). Коды A1-A4
+  worker/        polling-планировщик + dev/reviewer-конвейер + gitops. Коды W*, E*, R*
+  agents/        встроенные opencode-агенты (analyst.md, dev.md, reviewer.md) через go:embed
+  opencode/      обёртка запуска opencode, LiveRegistry, парсинг вердикта. Коды O1-O4
+  storage/       SQLite (modernc.org/sqlite, без CGO): tasks, traces, task_history. Коды S1-S5
+  update/        автообновление из Gitea Packages. Коды U1-U6
+```
+
+## Ключевые инварианты
+
+- **Команды/ядро:** Core.ProcessTurn — state-machine поверх storage. Команды:
+  /start /cancel /skip /retry N /status N /continue N. Активная задача — одна на чат.
+- **Фазы аналитика (Decision.Phase):** `ask` (уточняющие вопросы), `propose` (правки
+  черновика), `ready` (черновик полон как есть), `abort` (тема вне проекта). propose и ready
+  в core обрабатываются одинаково.
+- **Статусы задач:** draft→collecting→ready→approved→running→success/failed/timeout,
+  плюс cancelled/aborted/closed. approved — финальное одобрение («создавай»), после чего
+  воркер берёт задачу. IsValidTransition/IsTerminal в storage/models.go.
+- **Decider/Worker/Analyst/Reviewer:** Decider=analyst интерфейс (analyst пакет реализует);
+  Worker — polling-планировщик dev-агента; Reviewer проверяет diff dev-ветки (R1-R6),
+  вердикт JSON {passed, critical_issues, solid_violations, comments}.
+- **gitops (worker):** worker работает с worktrees; feature-ветка = `feat/<taskTag>` от
+  origin/main; ensureBranch (reset --hard + clean -fd + checkout -B), branchDiff
+  (`origin/main...<branch>`), push через http.extraHeader, токен как Bearer.
+- **Пути «всё рядом с .exe»:** относительные db/worktree резолвятся от каталога бинаря
+  (ExeDir), не от cwd. config.yaml ищутся рядом с бинарём, фоллбэк cwd.
+- **Автообновление:** авто = только Check+уведомление; замена — по /update. Версии в
+  Gitea Packages `commit-<sha7>/` (не `latest/`). Вердикты агентов — строгий JSON.
+
+## Контракты (не ломать)
+
+- `App.New(configPath, version, updateToken string)` — сигнатура.
+- `packageOwner` — константа "kamelion" (не плодить vars/ldflag/конфиг).
+- `update.Updater` — создаётся структурой `&update.Updater{...}`, конструктора нет.
+
+См. также `mem:tech_stack`, `mem:conventions`, `mem:task_completion`, `mem:suggested_commands`.
\ No newline at end of file
diff --git a/.serena/memories/memory_maintenance.md b/.serena/memories/memory_maintenance.md
new file mode 100644
index 0000000..6f84514
--- /dev/null
+++ b/.serena/memories/memory_maintenance.md
@@ -0,0 +1,33 @@
+# Memory Maintenance
+
+## Discovery Model
+
+- Core principle: progressive discovery through references, building a graph of memories.
+- Initially, agents are provided with the list of all memories (names only).
+- Agents should read `mem:core` as the top-level entry point (graph root).
+  This memory should contain references to other memories covering major project domains.
+  The referenced memories shall, in turn, shall contain references to even more specific memories, and so on.
+  The depth of the graph shall depend on the project complexity.
+- Use topics/folders to group related memories in order to make the content structure explicit.
+  Folders can mirror project structure (e.g. modules like frontend/backend) or topics like debugging, architecture, etc.
+- Memory references must use a mem: prefix inside backticks, e.g. `mem:frontend/core`.
+  The surrounding text should clearly indicate when to read the memory/which content to expect.
+  The text should provide more precise guidance than the memory name alone, 
+  i.e. avoid a reference like "frontend debugging: `mem:frontend/debugging` and instead make clear which aspects of frontend debugging are covered.
+- Memories themselves should not contain information about when to read them; this is the responsibility of the referring memory.
+
+## Style
+
+Dense agent notes, not prose docs. Prefer invariants, terse bullets. 
+Avoid obvious context, rationale, and examples unless they prevent likely mistakes. 
+Keep guidance durable and generalizable, not task-local.
+
+## Add/update threshold
+
+Add or update memories only with stable, non-obvious project conventions that avoid complex rediscovery in the future.
+Do not add: quick-read facts; generic language/framework knowledge; one-off task notes; volatile line-level details; behavior likely to change soon.
+
+## Maintenance Actions
+
+- Renaming memories: References are updated automatically if handled via Serena's memory rename tool.
+- Checking for stale memories (e.g. after deletion): Call `serena memories check` for a report.
\ No newline at end of file
diff --git a/.serena/memories/suggested_commands.md b/.serena/memories/suggested_commands.md
new file mode 100644
index 0000000..b00ffa5
--- /dev/null
+++ b/.serena/memories/suggested_commands.md
@@ -0,0 +1,27 @@
+# suggested_commands
+
+## Сборка / проверки (из корня репо)
+- `go test ./... -v -count=1 -timeout 120s` (или `make test`) — все тесты.
+- `go vet ./...` (или `make vet`).
+- `go fmt ./...` (или `make fmt`).
+- `go build -o ratatoskr ./cmd/ratatoskr/` (или `make build`).
+- `./ratatoskr -config config.yaml` (или `make run`).
+- `./ratatoskr -version` — показать версию бинаря.
+- Кросс-сборка: `make cross` (linux/amd64 + windows/amd64).
+
+## Go-тулчейн
+Хост без `go` в PATH — экспорт вручную:
+```
+export PATH=/opt/data/.local/go/bin:$PATH
+```
+На машине разработки (Windows, cmd) — обычный system Go.
+
+## git (worktree-процесс Ratatoskr)
+- Feature-ветка: `feat/<taskTag>`, база — `origin/main`. Пример проверки diff всей ветки:
+  `git diff origin/main...HEAD`.
+- Проверить состав отслеживаемых файлов (например наличие .serena): `git ls-files`.
+- Статус: `git status`. Лог: `git log --oneline -10`.
+
+## Замечания про среду
+- ОС Windows + PowerShell 5.1 (shell: powershell) — команды собирать/запускать с учётом
+  этом (нет `&&`; использовать `;`/`if ($?) {}`; & для путей с пробелами).
\ No newline at end of file
diff --git a/.serena/memories/task_completion.md b/.serena/memories/task_completion.md
new file mode 100644
index 0000000..87d4220
--- /dev/null
+++ b/.serena/memories/task_completion.md
@@ -0,0 +1,15 @@
+# task_completion
+
+Считается, что задача по коду выполнена строго после:
+
+1. **Формат/линт:** `go fmt ./...` (без неотформатированных файлов).
+2. **Тесты:** `go test ./... -v -count=1 -timeout 120s` — все проходят (`make test`).
+3. **Статический анализ:** `go vet ./...` — чисто (`make vet`).
+4. **Сборка:** `go build -o ratatoskr ./cmd/ratatoskr/` (`make build`) — компилируется.
+   (Кросс-сборка `make cross` — только при необходимости.)
+5. **Пересмотр контрактов:** если менялась сигнатура `App.New(configPath, version,
+   updateToken string)` — обновить вызовы в `internal/app/app_test.go` (иначе go vet падает).
+6. Коммит осмысленными атомарными коммитами в feature-ветку `feat/<taskTag>` от origin/main.
+
+Рабочий процесс Ratatoskr (агент dev в этом конвейере): изучить код, реализовать так, чтобы
+все acceptance criteria были закрыты, закоммитить в ветку, вернуть отчёт.
\ No newline at end of file
diff --git a/.serena/memories/tech_stack.md b/.serena/memories/tech_stack.md
new file mode 100644
index 0000000..ff27906
--- /dev/null
+++ b/.serena/memories/tech_stack.md
@@ -0,0 +1,30 @@
+# tech_stack
+
+## Язык / рантайм
+- Go **1.25.0** (go.mod `go 1.25.0`). Модуль `github.com/kamelion/ratatoskr-go`.
+- Сборка: статический бинарь, `CGO_ENABLED=0`. Локальный Go-тулчейн на хосте:
+  `export PATH=/opt/data/.local/go/bin:$PATH` (go1.25.0 linux/amd64).
+
+## Основные зависимости (go.mod)
+- `gopkg.in/yaml.v3 v3.0.1` — парсинг config.yaml.
+- `modernc.org/sqlite v1.56.0` — SQLite без CGO (чистый Go).
+- (indirect) google/uuid, go-humanize, mattn/go-isatty, x/sys, modernc.org/libc/mathutil/memory.
+
+## Внешние процессы
+- **opencode** (opencode.ai) — внешний процесс для субагентов (analyst/dev/reviewer).
+  Управляется через internal/opencode (Runner, LiveRegistry). Настраивается в конфиге
+  (opencode.bin / config / config_dir / hard_timeout / idle_timeout / poll_ms).
+
+## Сборка / Makefile
+- `make build` — go build -ldflags="-s -w -X main.version=commit-<sha7> -X main.updateToken=..." -o ratatoskr ./cmd/ratatoskr/.
+- `make test` — go test ./... -v -count=1 -timeout 120s.
+- `make vet` — go vet ./...   `make fmt` — go fmt ./...
+- `make run` — build + ./ratatoskr -config config.yaml.
+- `make cross` — кросс-сборка linux/amd64 + windows/amd64 (ratatoskr-windows-amd64.exe — Windows-машина Камиля).
+- GIT_SHA вшивается в main.version; UPDATE_TOKEN — в main.updateToken (секрет только у CI).
+
+## CI (.gitea/workflows/ci.yaml)
+- Job `test`: go test ./... + go vet ./....
+- Job `build-and-package` (matrix linux/amd64+windows/amd64): собирает и публикует в
+  Gitea Packages на `main` в версию `commit-<sha7>/` + companion-файлы `.version`/`.sha256`.
+- Секреты: TC_GITEA_TOKEN (write:packages), TC_UPDATE_TOKEN (read:package), GIT_MAIN_URL.
\ No newline at end of file
diff --git a/.serena/project.yml b/.serena/project.yml
new file mode 100644
index 0000000..fb466c8
--- /dev/null
+++ b/.serena/project.yml
@@ -0,0 +1,133 @@
+# the name by which the project can be referenced within Serena
+project_name: "ratatoskr-go"
+
+
+# list of languages for which language servers are started; choose from:
+#   al                  angular             ansible             bash                clojure
+#   cpp                 cpp_ccls            crystal             csharp              csharp_omnisharp
+#   dart                elixir              elm                 erlang              fortran
+#   fsharp              go                  groovy              haskell             haxe
+#   hlsl                html                java                json                julia
+#   kotlin              lean4               lua                 luau                markdown
+#   matlab              msl                 nix                 ocaml               pascal
+#   perl                php                 php_phpactor        powershell          python
+#   python_jedi         python_ty           r                   rego                ruby
+#   ruby_solargraph     rust                scala               scss                solidity
+#   svelte              swift               systemverilog       terraform           toml
+#   typescript          typescript_vts      vue                 yaml                zig
+#   (This list may be outdated. For the current list, see values of Language enum here:
+#   https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py
+#   For some languages, there are alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.)
+# Note:
+#   - For C, use cpp
+#   - For JavaScript, use typescript
+#   - For Angular projects, use angular (subsumes typescript+html; requires `npm install` in the project root)
+#   - For Svelte projects, use svelte (subsumes typescript/javascript for .svelte projects; requires npm)
+#   - For SCSS / Sass / plain CSS, use scss (some-sass-language-server handles all three)
+#   - For Free Pascal/Lazarus, use pascal
+# Special requirements:
+#   Some languages require additional setup/installations.
+#   See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers
+# When using multiple languages, the first language server that supports a given file will be used for that file.
+# The first language is the default language and the respective language server will be used as a fallback.
+# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
+languages:
+- go
+
+# the encoding used by text files in the project
+# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
+encoding: "utf-8"
+
+# line ending convention to use when writing source files.
+# Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default)
+# This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings.
+line_ending:
+
+# The language backend to use for this project.
+# If not set, the global setting from serena_config.yml is used.
+# Valid values: LSP, JetBrains
+# Note: the backend is fixed at startup. If a project with a different backend
+# is activated post-init, an error will be returned.
+language_backend:
+
+# whether to use project's .gitignore files to ignore files
+ignore_all_files_in_gitignore: true
+
+# advanced configuration option allowing to configure language server-specific options.
+# Maps the language key to the options.
+# Have a look at the docstring of the constructors of the LS implementations within solidlsp (e.g., for C# or PHP) to see which options are available.
+# No documentation on options means no options are available.
+ls_specific_settings: {}
+
+# list of additional workspace folder paths for cross-package reference support (e.g. in monorepos).
+# Paths can be absolute or relative to the project root.
+# Each folder is registered as an LSP workspace folder, enabling language servers to discover
+# symbols and references across package boundaries.
+# Currently supported for: TypeScript.
+# Example:
+#   additional_workspace_folders:
+#     - ../sibling-package
+#     - ../shared-lib
+additional_workspace_folders: []
+
+# list of additional paths to ignore in this project.
+# Same syntax as gitignore, so you can use * and **.
+# Note: global ignored_paths from serena_config.yml are also applied additively.
+ignored_paths: []
+
+# whether the project is in read-only mode
+# If set to true, all editing tools will be disabled and attempts to use them will result in an error
+# Added on 2025-04-18
+read_only: false
+
+# list of tool names to exclude.
+# This extends the existing exclusions (e.g. from the global configuration)
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+excluded_tools: []
+
+# list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default).
+# This extends the existing inclusions (e.g. from the global configuration).
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+included_optional_tools: []
+
+# fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools.
+# This cannot be combined with non-empty excluded_tools or included_optional_tools.
+# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html
+fixed_tools: []
+
+# list of mode names that are to be activated by default, overriding the setting in the global configuration.
+# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
+# If the setting is undefined/empty, the default_modes from the global configuration (serena_config.yml) apply.
+# Otherwise, this overrides the setting from the global configuration (serena_config.yml).
+# Therefore, you can set this to [] if you do not want the default modes defined in the global config to apply
+# for this project.
+# This setting can, in turn, be overridden by CLI parameters (--mode).
+# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
+default_modes:
+
+# list of mode names to be activated additionally for this project, e.g. ["query-projects"]
+# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes.
+# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes
+added_modes:
+
+# initial prompt for the project. It will always be given to the LLM upon activating the project
+# (contrary to the memories, which are loaded on demand).
+initial_prompt: ""
+
+# time budget (seconds) per tool call for the retrieval of additional symbol information
+# such as docstrings or parameter information.
+# This overrides the corresponding setting in the global configuration; see the documentation there.
+# If null or missing, use the setting from the global configuration.
+symbol_info_budget:
+
+# list of regex patterns which, when matched, mark a memory entry as read‑only.
+# Extends the list from the global configuration, merging the two lists.
+read_only_memory_patterns: []
+
+# list of regex patterns for memories to completely ignore.
+# Matching memories will not appear in list_memories or activate_project output
+# and cannot be accessed via read_memory or write_memory.
+# To access ignored memory files, use the read_file tool on the raw file path.
+# Extends the list from the global configuration, merging the two lists.
+# Example: ["_archive/.*", "_episodes/.*"]
+ignored_memory_patterns: []