micro-models-agent 0.61.1 → 0.63.0

package/CHANGELOG.md

@@ -4,6 +4,32 @@ All notable changes to Micro Models Agent (MMA) will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/), and this project adheres to [Semantic Versioning](https://semver.org/).
 
+## [0.63.0] - 2026-09-17
+
+### Added
+- **REPL `/provider add`**: add a provider without leaving the agent. Mirrors `mma provider add` — `/provider add <name> [--url <url>] [--key <key>] [--priority <n>] [--context-window <n>] [--rpm <n>] [--parallel <n>]`. Seeds the legacy provider into `provider.entries` on first use, saves the config and hot-reloads the agent; switch with `/provider use <name>`. `/provider` autocompletion now includes `add`; i18n `repl.provider_add_missing_value`, `repl.provider_switch_hint` (en+ru).
+
+### Changed
+- **Subcommand dispatch via handler maps** (new architecture rule #17): `/provider`, `/model` and `/skill` (`src/cli/repl-commands.ts`) and `SkillNameProvider.complete` (`src/cli/completer.ts`) now resolve subcommands through a `Record<string, handler>` map instead of `if (subcmd === …)` chains.
+
+## [0.62.0] - 2026-09-17
+
+### Added
+- **Prompt-cache awareness (cloud + local)**: every provider declares its cache behavior via a new `CacheCapability` (`ProviderCapabilities.cache`, overridable per entry with `provider.entries[].cache`). The OpenAI-compatible provider now sends the right request hints per backend — `cache_prompt` (llama.cpp), `prompt_cache_key` (OpenAI), `session_id` (OpenRouter sticky routing) — while `x-opencode-session` is gated by `sessionHeader` (legacy behavior preserved when no capability is set). `parseCacheUsage` (`src/llm/cache-usage.ts`) normalizes response formats (OpenAI/LM Studio/llama.cpp/vLLM/OpenRouter/Zen/Go, DeepSeek, Anthropic, Ollama) into `Chunk.usage.cache`.
+- **Cache metrics & savings**: `ModelPrice.cachedInput`/`cacheWrite`, `calculateCostDetailed` and `CostTracker.saved` bill cached reads at the cached rate and report the savings; builtin cached-read prices for MiniMax/GLM. A client-side prefix monitor (`src/core/agent/prefix-monitor.ts`) classifies why a cacheable prefix broke (`system`/`tools`/`history`/`volatile`) even when the provider reports nothing.
+- **Cache display**: a single footer line (`Cache: 87% hit · saved $0.42`, or `Prefix stable: 93% · broke: tool set`) in the REPL, single-run result and `--json` (`cache`); `mma session show <id>` aggregates `llm_usage` into token totals and cache hit rate.
+- **Streaming usage**: OpenAI-compatible streaming requests now send `stream_options: { include_usage: true }` (new `CacheCapability.requestStreamUsage`, on by default for OpenAI-shaped providers), so backends that only report usage in the final chunk — LM Studio, vLLM, OpenAI, OpenRouter — return real token counts (and `cached_tokens` where available) instead of the local chars/4 estimate.
+- **`mma usage`**: shows the active provider's balance/usage. OpenRouter is supported (`GET /key` for per-key usage/limit, plus `GET /credits` for account balance when a management key is configured); other providers report that they do not expose an API balance (OpenCode Zen/Go show it in the web dashboard).
+
+### Changed
+- **Code comments are Russian** (new architecture rule #15).
+- **Cross-platform rule** (new architecture rule #16): processes/paths/shell/FS code must work on Windows, macOS and Linux (no `mklink`, no `npx` for local tools, quote paths, skip-not-fail tests when an OS lacks a primitive).
+
+### Fixed
+- **One-shot subcommands hung when piped**: `mma session show <id> | cat` never exited because `bootstrap()` fired the background startup health check, which spawns an LSP/npx child that `process.exit` does not reap — the orphan kept the stdout pipe open. Subcommands never run an agent, so `setOneShotMode` now skips that check (detected in `main.ts` before `program.parse`). The recursive `postAction → process.exit(0)` hook (nested subcommands previously never fired it) is kept, and the startup check's `npx tsc` fallback now uses the local tsc.
+- **Prefix-cache line false alarm**: the footer treated the first iteration (`cause: unknown`, ratio 0) and normal history appends (`cause: none`) as a broken prefix. It now shows `Prefix stable …` only for a real break (`system`/`tools`/`history`/`volatile`) and surfaces the most recent such break even if later iterations are stable again.
+- **TypeScript checks were slow and unreliable**: syntax/type checks shelled out to `npx tsc`, which on Windows takes 5–13s (and tries the network without a local `typescript`), tripping test timeouts and stalling writes. New `resolveTscCommand` (`src/modules/lsp/project-root.ts`) runs the nearest local `tsc` via the current runtime (`process.execPath`), used by `verifier.ts`, `lint-on-write.ts` and `audit-runners.ts`; when no local tsc exists the check is skipped fast instead of hanging. The nested-project verifier test now links TypeScript with a cross-platform `symlinkSync(..., "junction")` instead of Windows-only `mklink`, and `bash.test.ts` resets the leaked grace window between tests.
+
 ## [0.61.1] - 2026-09-16
 
 ### Fixed

package/dist/i18n/en.json

@@ -494,7 +494,9 @@
   "repl.provider_list": "List configured providers or hot-swap the active one",
   "repl.provider_current": "Current provider",
   "repl.provider_set": "Provider set to: {name}",
-  "repl.provider_usage": "/provider list - show entries (* = active, prio = fallback order) | /provider use <name> - switch without restart",
+  "repl.provider_usage": "/provider list - show entries (* = active, prio = fallback order) | /provider use <name> - switch without restart | /provider add <name> [--url <url>] [--key <key>] [--priority <n>] [--context-window <n>] [--rpm <n>] [--parallel <n>] - add to config",
+  "repl.provider_add_missing_value": "Missing value for {flag}",
+  "repl.provider_switch_hint": "Switch to it with: /provider use {name}",
   "repl.model_list": "List models of the active provider or switch the model",
   "repl.model_current": "Current model",
   "repl.model_set": "Model set to: {name}",
@@ -712,6 +714,25 @@
   "repl.cost": "Total cost: {cost}",
   "repl.cost_breakdown": "By provider: {breakdown}",
   "repl.tokens": "Tokens used: {tokens}",
+  "repl.cache": "Cache: {hit}% hit · saved {saved}",
+  "repl.cache_nosave": "Cache: {hit}% hit",
+  "repl.prefix": "Prefix stable: {stable}% · broke: {cause}",
+  "cache.cause.system": "system prompt",
+  "cache.cause.tools": "tool set",
+  "cache.cause.history": "history",
+  "cache.cause.volatile": "volatile content",
+  "cache.cause.unknown": "unknown",
+  "cli.session_usage": "API usage: {prompt} prompt + {completion} completion = {total} tokens",
+  "cli.session_cache": "Cache: {hit}% hit ({cached} cached / {uncached} uncached)",
+  "cli.usage": "Show provider balance/usage (OpenRouter)",
+  "cli.usage_unsupported": "Provider \"{provider}\" does not expose an API balance. Only OpenRouter does; OpenCode Zen/Go show it in the web dashboard.",
+  "cli.usage_no_key": "No API key configured for the active provider.",
+  "cli.usage_error": "Failed to fetch balance: {error}",
+  "cli.usage_key_usage": "Key usage: {usage}",
+  "cli.usage_key_limit": "Key limit: {limit} · remaining {remaining}",
+  "cli.usage_balance": "Balance: {balance}",
+  "cli.usage_account": "Account: {credits} purchased · {used} used",
+  "cli.usage_empty": "No balance information returned.",
   "repl.ctrl_c_interrupt": "\n[Ctrl+C] Stopping agent... (press again to force)",
   "exec.stop_directive": "STOP. Step {stepId} (\"{description}\") took {iterations} iterations with no progress. DO NOT continue this step. Immediately call: plan update step={stepId} status=done (if code works despite warnings) OR plan update step={stepId} status=skipped note=\"reason\". Do NOT make any other tool calls before updating the plan.",
   "exec.test_runner_fail": "[test-runner] {framework}: {failed} test(s) FAILING, {passed} passing — do NOT mark verification steps as done while tests fail. Investigate the failures, fix the code, then re-run the tests.",

package/dist/i18n/ru.json

@@ -488,7 +488,9 @@
   "repl.provider_list": "Список настроенных провайдеров или горячая смена активного",
   "repl.provider_current": "Текущий провайдер",
   "repl.provider_set": "Провайдер установлен: {name}",
-  "repl.provider_usage": "/provider list — записи (* = активный, prio = порядок fallback) | /provider use <имя> — смена без перезапуска",
+  "repl.provider_usage": "/provider list — записи (* = активный, prio = порядок fallback) | /provider use <имя> — смена без перезапуска | /provider add <имя> [--url <url>] [--key <ключ>] [--priority <n>] [--context-window <n>] [--rpm <n>] [--parallel <n>] — добавить в конфиг",
+  "repl.provider_add_missing_value": "Нет значения для {flag}",
+  "repl.provider_switch_hint": "Переключитесь на него: /provider use {name}",
   "repl.model_list": "Список моделей активного провайдера или смена модели",
   "repl.model_current": "Текущая модель",
   "repl.model_set": "Модель установлена: {name}",
@@ -712,6 +714,25 @@
   "repl.cost": "Итого потрачено: {cost}",
   "repl.cost_breakdown": "По провайдерам: {breakdown}",
   "repl.tokens": "Потрачено токенов: {tokens}",
+  "repl.cache": "Кеш: {hit}% попаданий · сэкономлено {saved}",
+  "repl.cache_nosave": "Кеш: {hit}% попаданий",
+  "repl.prefix": "Префикс стабилен: {stable}% · сломалось: {cause}",
+  "cache.cause.system": "системный промпт",
+  "cache.cause.tools": "набор инструментов",
+  "cache.cause.history": "история",
+  "cache.cause.volatile": "волатильное содержимое",
+  "cache.cause.unknown": "неизвестно",
+  "cli.session_usage": "API-использование: {prompt} prompt + {completion} completion = {total} токенов",
+  "cli.session_cache": "Кеш: {hit}% попаданий ({cached} из кеша / {uncached} новых)",
+  "cli.usage": "Показать баланс/расход провайдера (OpenRouter)",
+  "cli.usage_unsupported": "Провайдер \"{provider}\" не отдаёт баланс по API. Это умеет только OpenRouter; OpenCode Zen/Go показывают его в веб-дашборде.",
+  "cli.usage_no_key": "Для активного провайдера не настроен API-ключ.",
+  "cli.usage_error": "Не удалось получить баланс: {error}",
+  "cli.usage_key_usage": "Расход по ключу: {usage}",
+  "cli.usage_key_limit": "Лимит ключа: {limit} · осталось {remaining}",
+  "cli.usage_balance": "Баланс: {balance}",
+  "cli.usage_account": "Аккаунт: куплено {credits} · израсходовано {used}",
+  "cli.usage_empty": "Провайдер не вернул данных о балансе.",
   "repl.ctrl_c_interrupt": "\n[Ctrl+C] Остановка агента... (ещё раз — принудительно)",
   "exec.stop_directive": "STOP. Step {stepId} (\"{description}\") took {iterations} iterations with no progress. DO NOT continue this step. Immediately call: plan update step={stepId} status=done (if code works despite warnings) OR plan update step={stepId} status=skipped note=\"reason\". Do NOT make any other tool calls before updating the plan.",
   "exec.test_runner_fail": "[test-runner] {framework}: {failed} test(s) FAILING, {passed} passing — do NOT mark verification steps as done while tests fail. Investigate the failures, fix the code, then re-run the tests.",