diff --git a/CHANGELOG.md b/CHANGELOG.md index b8e790b84..2f7124e2f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,6 +11,8 @@ Only write entries that are worth mentioning to users. ## Unreleased +- Core: Add `compaction_trigger_ratio` config option (default `0.85`) to control when auto-compaction triggers — compaction now fires when context usage reaches the configured ratio or when remaining space falls below `reserved_context_size`, whichever comes first +- Core: Support custom instructions in `/compact` command (e.g., `/compact keep database discussions`) to guide what the compaction preserves - Web: Add URL action parameters (`?action=create` to open create-session dialog, `?action=create-in-dir&workDir=xxx` to create a session directly) for external integrations, and support Cmd/Ctrl+Click on new-session buttons to open session creation in a new browser tab - Web: Add todo list display in prompt toolbar — shows task progress with expandable panel when the `SetTodoList` tool is active - ACP: Add authentication check for session operations with `AUTH_REQUIRED` error responses for terminal-based login flow diff --git a/docs/en/configuration/config-files.md b/docs/en/configuration/config-files.md index 4bff0a29a..e61bb97e5 100644 --- a/docs/en/configuration/config-files.md +++ b/docs/en/configuration/config-files.md @@ -57,6 +57,7 @@ max_steps_per_turn = 100 max_retries_per_step = 3 max_ralph_iterations = 0 reserved_context_size = 50000 +compaction_trigger_ratio = 0.85 [services.moonshot_search] base_url = "https://api.kimi.com/coding/v1/search" @@ -123,6 +124,7 @@ capabilities = ["thinking", "image_in"] | `max_retries_per_step` | `integer` | `3` | Maximum retries per step | | `max_ralph_iterations` | `integer` | `0` | Extra iterations after each user message; `0` disables; `-1` is unlimited | | `reserved_context_size` | `integer` | `50000` | Reserved token count for LLM response generation; auto-compaction triggers when `context_tokens + reserved_context_size >= max_context_size` | +| `compaction_trigger_ratio` | `float` | `0.85` | Context usage ratio threshold for auto-compaction (0.5–0.99); auto-compaction triggers when `context_tokens >= max_context_size * compaction_trigger_ratio`, whichever condition is met first with `reserved_context_size` | ### `services` diff --git a/docs/en/customization/wire-mode.md b/docs/en/customization/wire-mode.md index 80837e535..31481e092 100644 --- a/docs/en/customization/wire-mode.md +++ b/docs/en/customization/wire-mode.md @@ -73,7 +73,7 @@ interface JSONRPCError { Added in Wire 1.1. Legacy clients can skip this request and send `prompt` directly. ::: -- **Direction**: client → agent +- **Direction**: Client → Agent - **Type**: Request (requires response) Optional handshake request for negotiating protocol version, submitting external tool definitions, and retrieving the slash command list. @@ -330,7 +330,7 @@ If no turn is in progress: ### `event` -- **Direction**: agent → client +- **Direction**: Agent → Client - **Type**: Notification (no response needed) Events emitted by the agent during a turn. No `id` field, client doesn't need to respond. @@ -351,7 +351,7 @@ interface EventParams { ### `request` -- **Direction**: agent → client +- **Direction**: Agent → Client - **Type**: Request (requires response) Requests from the agent to the client, used for approval confirmation or external tool calls. The client must respond before the agent can continue execution. diff --git a/docs/en/guides/interaction.md b/docs/en/guides/interaction.md index f76b90027..432af4390 100644 --- a/docs/en/guides/interaction.md +++ b/docs/en/guides/interaction.md @@ -87,7 +87,7 @@ Each question supports 2–4 predefined options, and the AI will set appropriate The AI only uses this tool when your choice genuinely affects subsequent actions. For decisions that can be inferred from context, the AI will decide on its own and continue execution. ::: -## Approvals +## Approvals and confirmations When the AI needs to perform operations that may have an impact (such as modifying files or running commands), Kimi Code CLI will request your confirmation. diff --git a/docs/en/guides/sessions.md b/docs/en/guides/sessions.md index 7e8653477..acab88d48 100644 --- a/docs/en/guides/sessions.md +++ b/docs/en/guides/sessions.md @@ -72,6 +72,12 @@ Enter `/compact` to have the AI summarize the current conversation and replace t /compact ``` +You can also append custom instructions after the command to tell the AI what content to prioritize preserving during compaction: + +``` +/compact keep the database-related discussion +``` + Compacting preserves key information while reducing token consumption. This is useful when the conversation is long but you still want to retain some context. ::: tip diff --git a/docs/en/reference/kimi-web.md b/docs/en/reference/kimi-web.md index 9a14ab55d..5af099b42 100644 --- a/docs/en/reference/kimi-web.md +++ b/docs/en/reference/kimi-web.md @@ -186,6 +186,7 @@ Web UI provides a unified prompt toolbar above the input box, displaying various - **Activity status**: Shows the current agent state (processing, waiting for approval, etc.) - **Message queue**: Queue follow-up messages while the AI is processing; queued messages are sent automatically when the current response completes - **File changes**: Detects Git repository status, showing the number of new, modified, and deleted files (including untracked files). Click to view a detailed list of changes +- **Todo list**: When the `SetTodoList` tool is active, shows task progress with support for expanding to view the detailed list ::: info Changed Git diff status bar added in version 1.5. Activity status indicator added in version 1.9. Version 1.10 unified it into the prompt toolbar. Version 1.11 moved the context usage indicator to the prompt toolbar. diff --git a/docs/en/reference/slash-commands.md b/docs/en/reference/slash-commands.md index c843e6e5e..7f8afbfb8 100644 --- a/docs/en/reference/slash-commands.md +++ b/docs/en/reference/slash-commands.md @@ -63,7 +63,7 @@ This command is only available when using the default configuration file. If a c ### `/editor` -Set the default external editor. When called without arguments, displays an interactive selection interface; you can also specify the editor command directly, e.g., `/editor vim`. After configuration, pressing `Ctrl-O` will open this editor to edit the current input content. See [Keyboard shortcuts](./keyboard.md#external-editor) for details. +Set the external editor. When called without arguments, displays an interactive selection interface; you can also specify the editor command directly, e.g., `/editor vim`. After configuration, pressing `Ctrl-O` will open this editor to edit the current input content. See [Keyboard shortcuts](./keyboard.md#external-editor) for details. ### `/reload` @@ -82,7 +82,7 @@ Debug information is displayed in a pager, press `q` to exit. Display API usage and quota information, showing quota usage with progress bars and remaining percentages. -Aliases: `/status` +Alias: `/status` ::: tip This command only works with the Kimi Code platform. @@ -118,7 +118,7 @@ Alias: `/reset` ### `/compact` -Manually compact the context to reduce token usage. +Manually compact the context to reduce token usage. You can append custom instructions after the command to tell the AI which information to prioritize preserving during compaction, e.g., `/compact preserve database-related discussions`. When the context is too long, Kimi Code CLI will automatically trigger compaction. This command allows manually triggering the compaction process. diff --git a/docs/en/release-notes/changelog.md b/docs/en/release-notes/changelog.md index 5176941a6..687b06ab4 100644 --- a/docs/en/release-notes/changelog.md +++ b/docs/en/release-notes/changelog.md @@ -4,6 +4,8 @@ This page documents the changes in each Kimi Code CLI release. ## Unreleased +- Core: Add `compaction_trigger_ratio` config option (default `0.85`) to control when auto-compaction triggers — compaction now fires when context usage reaches the configured ratio or when remaining space falls below `reserved_context_size`, whichever comes first +- Core: Support custom instructions in `/compact` command (e.g., `/compact keep database discussions`) to guide what the compaction preserves - Web: Add URL action parameters (`?action=create` to open create-session dialog, `?action=create-in-dir&workDir=xxx` to create a session directly) for external integrations, and support Cmd/Ctrl+Click on new-session buttons to open session creation in a new browser tab - Web: Add todo list display in prompt toolbar — shows task progress with expandable panel when the `SetTodoList` tool is active - ACP: Add authentication check for session operations with `AUTH_REQUIRED` error responses for terminal-based login flow diff --git a/docs/zh/configuration/config-files.md b/docs/zh/configuration/config-files.md index ea79f2446..5bc963151 100644 --- a/docs/zh/configuration/config-files.md +++ b/docs/zh/configuration/config-files.md @@ -57,6 +57,7 @@ max_steps_per_turn = 100 max_retries_per_step = 3 max_ralph_iterations = 0 reserved_context_size = 50000 +compaction_trigger_ratio = 0.85 [services.moonshot_search] base_url = "https://api.kimi.com/coding/v1/search" @@ -123,6 +124,7 @@ capabilities = ["thinking", "image_in"] | `max_retries_per_step` | `integer` | `3` | 单步最大重试次数 | | `max_ralph_iterations` | `integer` | `0` | 每个 User 消息后额外自动迭代次数；`0` 表示关闭；`-1` 表示无限 | | `reserved_context_size` | `integer` | `50000` | 预留给 LLM 响应生成的 token 数量；当 `context_tokens + reserved_context_size >= max_context_size` 时自动触发压缩 | +| `compaction_trigger_ratio` | `float` | `0.85` | 触发自动压缩的上下文使用率阈值（0.5–0.99）；当 `context_tokens >= max_context_size * compaction_trigger_ratio` 时自动触发压缩，与 `reserved_context_size` 条件取先触发者 | ### `services` diff --git a/docs/zh/guides/sessions.md b/docs/zh/guides/sessions.md index e4a933303..2e3e397a0 100644 --- a/docs/zh/guides/sessions.md +++ b/docs/zh/guides/sessions.md @@ -72,6 +72,12 @@ kimi --session abc123 /compact ``` +你也可以在命令后附带自定义指引，告诉 AI 在压缩时优先保留哪些内容： + +``` +/compact 保留数据库相关的讨论 +``` + 压缩会保留关键信息，同时减少 token 消耗。这在对话很长但你还想保留一些上下文时很有用。 ::: tip 提示 diff --git a/docs/zh/reference/kimi-web.md b/docs/zh/reference/kimi-web.md index 98917a3bd..2eea48daa 100644 --- a/docs/zh/reference/kimi-web.md +++ b/docs/zh/reference/kimi-web.md @@ -186,6 +186,7 @@ Web UI 在输入框上方提供统一的提示工具栏，以可折叠标签页 - **活动状态**：显示 Agent 当前状态（处理中、等待审批等） - **消息队列**：在 AI 处理过程中可以排队发送后续消息，待当前回复完成后自动发送 - **文件变更**：检测 Git 仓库状态，显示新增、修改和删除的文件数量（包含未跟踪文件），点击可查看详细的变更列表 +- **待办事项**：当 `SetTodoList` 工具处于活动状态时，显示任务进度，支持展开查看详细列表 ::: info 变更 Git diff 状态栏新增于 1.5 版本。1.9 版本添加了活动状态指示器。1.10 版本将其统一为提示工具栏。1.11 版本将上下文用量指示器移至提示工具栏。 diff --git a/docs/zh/reference/slash-commands.md b/docs/zh/reference/slash-commands.md index c3bd85881..d3fe2ad34 100644 --- a/docs/zh/reference/slash-commands.md +++ b/docs/zh/reference/slash-commands.md @@ -118,7 +118,7 @@ ### `/compact` -手动压缩上下文，减少 token 使用。 +手动压缩上下文，减少 token 使用。可以在命令后附带自定义指引，告诉 AI 在压缩时优先保留哪些信息，例如 `/compact 保留数据库相关的讨论`。 当上下文过长时，Kimi Code CLI 会自动触发压缩。此命令可手动触发压缩过程。 diff --git a/docs/zh/release-notes/changelog.md b/docs/zh/release-notes/changelog.md index 401bacefb..e72938127 100644 --- a/docs/zh/release-notes/changelog.md +++ b/docs/zh/release-notes/changelog.md @@ -4,6 +4,8 @@ ## 未发布 +- Core：新增 `compaction_trigger_ratio` 配置项（默认 `0.85`），用于控制自动压缩的触发时机——当上下文用量达到配置比例或剩余空间低于 `reserved_context_size` 时触发压缩，以先满足的条件为准 +- Core：`/compact` 命令支持自定义指令（如 `/compact keep database discussions`），可指导压缩时重点保留的内容 - Web：新增 URL 操作参数（`?action=create` 打开创建会话对话框，`?action=create-in-dir&workDir=xxx` 直接创建会话）用于外部集成，支持 Cmd/Ctrl+点击新建会话按钮在新标签页中打开会话创建 - Web：在提示输入工具栏中添加待办列表显示——当 `SetTodoList` 工具激活时，显示任务进度并支持展开面板查看详情 - ACP：为会话操作添加认证检查，未认证时返回 `AUTH_REQUIRED` 错误响应，支持终端登录流程 diff --git a/src/kimi_cli/config.py b/src/kimi_cli/config.py index 6bd6b44cb..fff8d4604 100644 --- a/src/kimi_cli/config.py +++ b/src/kimi_cli/config.py @@ -80,7 +80,12 @@ class LoopControl(BaseModel): """Extra iterations after the first turn in Ralph mode. Use -1 for unlimited.""" reserved_context_size: int = Field(default=50_000, ge=1000) """Reserved token count for LLM response generation. Auto-compaction triggers when - context_tokens + reserved_context_size >= max_context_size. Default is 50000.""" + either context_tokens + reserved_context_size >= max_context_size or + context_tokens >= max_context_size * compaction_trigger_ratio. Default is 50000.""" + compaction_trigger_ratio: float = Field(default=0.85, ge=0.5, le=0.99) + """Context usage ratio threshold for auto-compaction. Default is 0.85 (85%). + Auto-compaction triggers when context_tokens >= max_context_size * compaction_trigger_ratio + or when context_tokens + reserved_context_size >= max_context_size.""" class MoonshotSearchConfig(BaseModel): diff --git a/src/kimi_cli/soul/compaction.py b/src/kimi_cli/soul/compaction.py index fcd8543d2..a68033d9b 100644 --- a/src/kimi_cli/soul/compaction.py +++ b/src/kimi_cli/soul/compaction.py @@ -53,15 +53,37 @@ def _estimate_text_tokens(messages: Sequence[Message]) -> int: return total_chars // 4 +def should_auto_compact( + token_count: int, + max_context_size: int, + *, + trigger_ratio: float, + reserved_context_size: int, +) -> bool: + """Determine whether auto-compaction should be triggered. + + Returns True when either condition is met (whichever fires first): + - Ratio-based: token_count >= max_context_size * trigger_ratio + - Reserved-based: token_count + reserved_context_size >= max_context_size + """ + return ( + token_count >= max_context_size * trigger_ratio + or token_count + reserved_context_size >= max_context_size + ) + + @runtime_checkable class Compaction(Protocol): - async def compact(self, messages: Sequence[Message], llm: LLM) -> CompactionResult: + async def compact( + self, messages: Sequence[Message], llm: LLM, *, custom_instruction: str = "" + ) -> CompactionResult: """ Compact a sequence of messages into a new sequence of messages. Args: messages (Sequence[Message]): The messages to compact. llm (LLM): The LLM to use for compaction. + custom_instruction: Optional user instruction to guide compaction focus. Returns: CompactionResult: The compacted messages and token usage from the compaction LLM call. @@ -82,8 +104,10 @@ class SimpleCompaction: def __init__(self, max_preserved_messages: int = 2) -> None: self.max_preserved_messages = max_preserved_messages - async def compact(self, messages: Sequence[Message], llm: LLM) -> CompactionResult: - compact_message, to_preserve = self.prepare(messages) + async def compact( + self, messages: Sequence[Message], llm: LLM, *, custom_instruction: str = "" + ) -> CompactionResult: + compact_message, to_preserve = self.prepare(messages, custom_instruction=custom_instruction) if compact_message is None: return CompactionResult(messages=to_preserve, usage=None) @@ -118,7 +142,9 @@ class PrepareResult(NamedTuple): compact_message: Message | None to_preserve: Sequence[Message] - def prepare(self, messages: Sequence[Message]) -> PrepareResult: + def prepare( + self, messages: Sequence[Message], *, custom_instruction: str = "" + ) -> PrepareResult: if not messages or self.max_preserved_messages <= 0: return self.PrepareResult(compact_message=None, to_preserve=messages) @@ -151,5 +177,13 @@ def prepare(self, messages: Sequence[Message]) -> PrepareResult: compact_message.content.extend( part for part in msg.content if not isinstance(part, ThinkPart) ) - compact_message.content.append(TextPart(text="\n" + prompts.COMPACT)) + prompt_text = "\n" + prompts.COMPACT + if custom_instruction: + prompt_text += ( + "\n\n**User's Custom Compaction Instruction:**\n" + "The user has specifically requested the following focus during compaction. " + "You MUST prioritize this instruction above the default compression priorities:\n" + f"{custom_instruction}" + ) + compact_message.content.append(TextPart(text=prompt_text)) return self.PrepareResult(compact_message=compact_message, to_preserve=to_preserve) diff --git a/src/kimi_cli/soul/kimisoul.py b/src/kimi_cli/soul/kimisoul.py index 63557af77..5dbf5d5bd 100644 --- a/src/kimi_cli/soul/kimisoul.py +++ b/src/kimi_cli/soul/kimisoul.py @@ -32,7 +32,7 @@ wire_send, ) from kimi_cli.soul.agent import Agent, Runtime -from kimi_cli.soul.compaction import CompactionResult, SimpleCompaction +from kimi_cli.soul.compaction import CompactionResult, SimpleCompaction, should_auto_compact from kimi_cli.soul.context import Context from kimi_cli.soul.message import check_message, system, tool_result_to_message from kimi_cli.soul.slash import registry as soul_slash_registry @@ -392,8 +392,12 @@ async def _pipe_approval_to_wire(): step_outcome: StepOutcome | None = None try: # compact the context if needed - reserved = self._loop_control.reserved_context_size - if self._context.token_count + reserved >= self._runtime.llm.max_context_size: + if should_auto_compact( + self._context.token_count, + self._runtime.llm.max_context_size, + trigger_ratio=self._loop_control.compaction_trigger_ratio, + reserved_context_size=self._loop_control.reserved_context_size, + ): logger.info("Context too long, compacting...") await self.compact_context() @@ -544,7 +548,7 @@ async def _grow_context(self, result: StepResult, tool_results: list[ToolResult] await self._context.append_message(tool_messages) # token count of tool results are not available yet - async def compact_context(self) -> None: + async def compact_context(self, custom_instruction: str = "") -> None: """ Compact the context. @@ -558,7 +562,9 @@ async def compact_context(self) -> None: async def _run_compaction_once() -> CompactionResult: if self._runtime.llm is None: raise LLMNotSet() - return await self._compaction.compact(self._context.history, self._runtime.llm) + return await self._compaction.compact( + self._context.history, self._runtime.llm, custom_instruction=custom_instruction + ) @tenacity.retry( retry=retry_if_exception(self._is_retryable_error), diff --git a/src/kimi_cli/soul/slash.py b/src/kimi_cli/soul/slash.py index 35b703642..635d5a624 100644 --- a/src/kimi_cli/soul/slash.py +++ b/src/kimi_cli/soul/slash.py @@ -51,13 +51,13 @@ async def init(soul: KimiSoul, args: str): @registry.command async def compact(soul: KimiSoul, args: str): - """Compact the context""" + """Compact the context (optionally with a custom focus, e.g. /compact keep db discussions)""" if soul.context.n_checkpoints == 0: wire_send(TextPart(text="The context is empty.")) return logger.info("Running `/compact`") - await soul.compact_context() + await soul.compact_context(custom_instruction=args.strip()) wire_send(TextPart(text="The context has been compacted.")) wire_send(StatusUpdate(context_usage=soul.status.context_usage)) diff --git a/tests/core/test_config.py b/tests/core/test_config.py index 83e8fd442..f7892a9c2 100644 --- a/tests/core/test_config.py +++ b/tests/core/test_config.py @@ -32,6 +32,7 @@ def test_default_config_dump(): "max_retries_per_step": 3, "max_ralph_iterations": 0, "reserved_context_size": 50000, + "compaction_trigger_ratio": 0.85, }, "services": {"moonshot_search": None, "moonshot_fetch": None}, "mcp": {"client": {"tool_call_timeout_ms": 60000}}, @@ -92,3 +93,23 @@ def test_load_config_max_steps_per_run(): def test_load_config_reserved_context_size_too_low(): with pytest.raises(ConfigError, match="reserved_context_size"): load_config_from_string('{"loop_control": {"reserved_context_size": 500}}') + + +def test_load_config_compaction_trigger_ratio(): + config = load_config_from_string('{"loop_control": {"compaction_trigger_ratio": 0.8}}') + assert config.loop_control.compaction_trigger_ratio == 0.8 + + +def test_load_config_compaction_trigger_ratio_default(): + config = load_config_from_string("{}") + assert config.loop_control.compaction_trigger_ratio == 0.85 + + +def test_load_config_compaction_trigger_ratio_too_low(): + with pytest.raises(ConfigError, match="compaction_trigger_ratio"): + load_config_from_string('{"loop_control": {"compaction_trigger_ratio": 0.3}}') + + +def test_load_config_compaction_trigger_ratio_too_high(): + with pytest.raises(ConfigError, match="compaction_trigger_ratio"): + load_config_from_string('{"loop_control": {"compaction_trigger_ratio": 1.0}}') diff --git a/tests/core/test_simple_compaction.py b/tests/core/test_simple_compaction.py index bc0732aea..40473d7d9 100644 --- a/tests/core/test_simple_compaction.py +++ b/tests/core/test_simple_compaction.py @@ -5,7 +5,7 @@ from kosong.message import Message import kimi_cli.prompts as prompts -from kimi_cli.soul.compaction import CompactionResult, SimpleCompaction +from kimi_cli.soul.compaction import CompactionResult, SimpleCompaction, should_auto_compact from kimi_cli.wire.types import TextPart, ThinkPart @@ -126,3 +126,90 @@ def test_estimated_token_count_empty_messages(): """Empty message list should return 0.""" result = CompactionResult(messages=[], usage=None) assert result.estimated_token_count == 0 + + +def test_prepare_appends_custom_instruction(): + messages = [ + Message(role="user", content=[TextPart(text="Old question")]), + Message(role="assistant", content=[TextPart(text="Old answer")]), + Message(role="user", content=[TextPart(text="Latest question")]), + Message(role="assistant", content=[TextPart(text="Latest answer")]), + ] + + result = SimpleCompaction(max_preserved_messages=2).prepare( + messages, custom_instruction="Preserve all discussions about the database" + ) + + assert result.compact_message is not None + parts = result.compact_message.content + last_part = parts[-1] + assert isinstance(last_part, TextPart) + # Custom instruction should be merged into the same TextPart as the COMPACT prompt + assert last_part.text.startswith("\n" + prompts.COMPACT) + assert "User's Custom Compaction Instruction" in last_part.text + assert "Preserve all discussions about the database" in last_part.text + + +def test_prepare_without_custom_instruction_unchanged(): + """When no custom_instruction is given, the compact message should end with the COMPACT prompt.""" + messages = [ + Message(role="user", content=[TextPart(text="Old question")]), + Message(role="assistant", content=[TextPart(text="Old answer")]), + Message(role="user", content=[TextPart(text="Latest question")]), + Message(role="assistant", content=[TextPart(text="Latest answer")]), + ] + + result = SimpleCompaction(max_preserved_messages=2).prepare(messages) + + assert result.compact_message is not None + parts = result.compact_message.content + last_part = parts[-1] + assert isinstance(last_part, TextPart) + assert last_part.text == "\n" + prompts.COMPACT + + +# --- should_auto_compact tests --- + + +class TestShouldAutoCompact: + """Test the auto-compaction trigger logic across different model context sizes.""" + + def test_200k_model_triggers_by_reserved(self): + """200K model with default config: reserved (50K) fires first at 150K (75%).""" + # At 150K tokens: ratio check = 150K >= 170K (False), reserved check = 200K >= 200K (True) + assert should_auto_compact( + 150_000, 200_000, trigger_ratio=0.85, reserved_context_size=50_000 + ) + + def test_200k_model_below_threshold(self): + """200K model: 140K tokens should NOT trigger (below both thresholds).""" + assert not should_auto_compact( + 140_000, 200_000, trigger_ratio=0.85, reserved_context_size=50_000 + ) + + def test_1m_model_triggers_by_ratio(self): + """1M model with default config: ratio (85%) fires first at 850K.""" + # At 850K tokens: ratio check = 850K >= 850K (True) + assert should_auto_compact( + 850_000, 1_000_000, trigger_ratio=0.85, reserved_context_size=50_000 + ) + + def test_1m_model_below_ratio_threshold(self): + """1M model: 840K tokens should NOT trigger (below 85% ratio, well above reserved).""" + assert not should_auto_compact( + 840_000, 1_000_000, trigger_ratio=0.85, reserved_context_size=50_000 + ) + + def test_custom_ratio_triggers_earlier(self): + """Custom ratio=0.7 triggers at 70% of context.""" + # 200K * 0.7 = 140K + assert should_auto_compact( + 140_000, 200_000, trigger_ratio=0.7, reserved_context_size=50_000 + ) + assert not should_auto_compact( + 139_999, 200_000, trigger_ratio=0.7, reserved_context_size=50_000 + ) + + def test_zero_tokens_never_triggers(self): + """Empty context should never trigger compaction.""" + assert not should_auto_compact(0, 200_000, trigger_ratio=0.85, reserved_context_size=50_000) diff --git a/tests_e2e/test_wire_protocol.py b/tests_e2e/test_wire_protocol.py index 7110c813a..18f35c901 100644 --- a/tests_e2e/test_wire_protocol.py +++ b/tests_e2e/test_wire_protocol.py @@ -49,7 +49,11 @@ def test_initialize_handshake(tmp_path) -> None: "description": "Analyze the codebase and generate an `AGENTS.md` file", "aliases": [], }, - {"name": "compact", "description": "Compact the context", "aliases": []}, + { + "name": "compact", + "description": "Compact the context (optionally with a custom focus, e.g. /compact keep db discussions)", + "aliases": [], + }, {"name": "clear", "description": "Clear the context", "aliases": ["reset"]}, { "name": "yolo", @@ -117,7 +121,11 @@ def test_initialize_external_tool_conflict(tmp_path) -> None: "description": "Analyze the codebase and generate an `AGENTS.md` file", "aliases": [], }, - {"name": "compact", "description": "Compact the context", "aliases": []}, + { + "name": "compact", + "description": "Compact the context (optionally with a custom focus, e.g. /compact keep db discussions)", + "aliases": [], + }, {"name": "clear", "description": "Clear the context", "aliases": ["reset"]}, { "name": "yolo",