klaude-code 2.27.0__tar.gz → 2.29.0__tar.gz

klaude_code-2.27.0/README.md → klaude_code-2.29.0/PKG-INFO

@@ -1,3 +1,30 @@
+Metadata-Version: 2.3
+Name: klaude-code
+Version: 2.29.0
+Summary: Minimal code agent CLI
+Requires-Dist: anthropic[bedrock]>=0.66.0
+Requires-Dist: chardet>=5.2.0,<6
+Requires-Dist: diff-match-patch>=20241021
+Requires-Dist: filelock>=3.20.3
+Requires-Dist: fastapi
+Requires-Dist: google-genai>=1.56.0
+Requires-Dist: httpx[socks]>=0.28.1
+Requires-Dist: markdown-it-py>=4.0.0
+Requires-Dist: openai>=2.24.0
+Requires-Dist: prompt-toolkit>=3.0.52
+Requires-Dist: pydantic>=2.11.7
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: rich>=14.1.0
+Requires-Dist: socksio>=1.0.0
+Requires-Dist: sse-starlette
+Requires-Dist: trafilatura>=2.0.0
+Requires-Dist: typer>=0.17.3
+Requires-Dist: uvicorn
+Requires-Dist: readability-lxml>=0.8.4.1
+Requires-Dist: pillow>=12.2.0
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+
 # Klaude Code
 
 Minimal code agent CLI.
@@ -107,9 +134,14 @@ klaude
 
 On first run, you'll be prompted to select a model. Your choice is saved as `main_model`.
 
-You can also configure fallback lists for helper models:
+You can also configure fallback lists for the main model and helper models:
 
 ```yaml
+main_model:
+  - gpt-5.5
+  - gpt-5.4
+  - opus
+
 fast_model:
   - haiku
   - gemini-flash
@@ -120,7 +152,9 @@ compact_model:
   - haiku
 ```
 
-Klaude tries these entries in order and uses the first available model. `fast_model` is used for session-title generation; `compact_model` is used for compact/helper tasks.
+Klaude expands each entry into concrete provider candidates in `provider_list` order, then falls through to the next model in the list. For example, `gpt-5.4` will try available providers such as `gpt-5.4@openai`, `gpt-5.4@github-copilot`, and `gpt-5.4@openrouter` before moving to the next model. Runtime fallback is used for non-retryable provider/model failures such as quota, billing, permission, or model-unavailable errors. `fast_model` is used for session-title generation; `compact_model` is used for compact/helper tasks.
+
+When you switch models with `/model`, Klaude updates `main_model` without discarding the fallback chain: the selected model is moved to the front if it already exists, or inserted at the front otherwise.
 
 #### Built-in Providers
 
@@ -196,7 +230,10 @@ You can add custom models to built-in providers or define new ones. Configuratio
 
 ```yaml
 # ~/.klaude/klaude-config.yaml
-main_model: opus
+main_model:
+  - gpt-5.5
+  - gpt-5.4
+  - opus
 
 fast_model:
   - haiku
@@ -236,7 +273,8 @@ provider_list:
 - **Merging**: If `provider_name` matches a built-in provider, settings like `protocol` and `api_key` are inherited.
 - **Overriding**: Use the same `model_name` as a built-in model to override its parameters.
 - **Environment Variables**: Use `${VAR_NAME}` syntax for secrets.
-- **Model Preference Lists**: `fast_model` and `compact_model` accept either a single string or a list of model selectors. When you provide a list, Klaude tries them in order and picks the first available one.
+- **Model Preference Lists**: `main_model`, `fast_model`, and `compact_model` accept either a single string or a list of model selectors. When you provide a list, Klaude first tries matching providers in `provider_list` order for each selector, then moves to the next selector.
+- **Updating Defaults**: `/model` keeps saving the selected model back to `main_model`, but preserves fallback order by moving or inserting the selected model at the front of the list.
 
 ##### Sub-agent Model Configuration
 
@@ -307,7 +345,7 @@ Inside the interactive session (`klaude`), use these commands to streamline your
 - `/refresh-terminal` - Refresh terminal display.
 - `/web` - Switch to web UI mode.
 - `/new` - Start a new session (clears context).
-- `/model` - Switch the active LLM during the session.
+- `/model` - Switch the active LLM and update `main_model` in config while preserving fallback order (the selected model is moved/inserted to the front).
 - `/sub-agent-model` - Configure sub-agent models at runtime.
 - `/thinking` - Change thinking/reasoning level.
 - `/status` - Show session usage statistics (cost, tokens, model breakdown).

klaude_code-2.27.0/PKG-INFO → klaude_code-2.29.0/README.md

@@ -1,28 +1,3 @@
-Metadata-Version: 2.3
-Name: klaude-code
-Version: 2.27.0
-Summary: Minimal code agent CLI
-Requires-Dist: anthropic[bedrock]>=0.66.0
-Requires-Dist: chardet>=5.2.0,<6
-Requires-Dist: diff-match-patch>=20241021
-Requires-Dist: filelock>=3.20.3
-Requires-Dist: fastapi
-Requires-Dist: google-genai>=1.56.0
-Requires-Dist: markdown-it-py>=4.0.0
-Requires-Dist: openai>=2.24.0
-Requires-Dist: prompt-toolkit>=3.0.52
-Requires-Dist: pydantic>=2.11.7
-Requires-Dist: python-socks>=2.8.1
-Requires-Dist: pyyaml>=6.0.2
-Requires-Dist: rich>=14.1.0
-Requires-Dist: sse-starlette
-Requires-Dist: trafilatura>=2.0.0
-Requires-Dist: typer>=0.17.3
-Requires-Dist: uvicorn
-Requires-Dist: readability-lxml>=0.8.4.1
-Requires-Python: >=3.13
-Description-Content-Type: text/markdown
-
 # Klaude Code
 
 Minimal code agent CLI.
@@ -132,9 +107,14 @@ klaude
 
 On first run, you'll be prompted to select a model. Your choice is saved as `main_model`.
 
-You can also configure fallback lists for helper models:
+You can also configure fallback lists for the main model and helper models:
 
 ```yaml
+main_model:
+  - gpt-5.5
+  - gpt-5.4
+  - opus
+
 fast_model:
   - haiku
   - gemini-flash
@@ -145,7 +125,9 @@ compact_model:
   - haiku
 ```
 
-Klaude tries these entries in order and uses the first available model. `fast_model` is used for session-title generation; `compact_model` is used for compact/helper tasks.
+Klaude expands each entry into concrete provider candidates in `provider_list` order, then falls through to the next model in the list. For example, `gpt-5.4` will try available providers such as `gpt-5.4@openai`, `gpt-5.4@github-copilot`, and `gpt-5.4@openrouter` before moving to the next model. Runtime fallback is used for non-retryable provider/model failures such as quota, billing, permission, or model-unavailable errors. `fast_model` is used for session-title generation; `compact_model` is used for compact/helper tasks.
+
+When you switch models with `/model`, Klaude updates `main_model` without discarding the fallback chain: the selected model is moved to the front if it already exists, or inserted at the front otherwise.
 
 #### Built-in Providers
 
@@ -221,7 +203,10 @@ You can add custom models to built-in providers or define new ones. Configuratio
 
 ```yaml
 # ~/.klaude/klaude-config.yaml
-main_model: opus
+main_model:
+  - gpt-5.5
+  - gpt-5.4
+  - opus
 
 fast_model:
   - haiku
@@ -261,7 +246,8 @@ provider_list:
 - **Merging**: If `provider_name` matches a built-in provider, settings like `protocol` and `api_key` are inherited.
 - **Overriding**: Use the same `model_name` as a built-in model to override its parameters.
 - **Environment Variables**: Use `${VAR_NAME}` syntax for secrets.
-- **Model Preference Lists**: `fast_model` and `compact_model` accept either a single string or a list of model selectors. When you provide a list, Klaude tries them in order and picks the first available one.
+- **Model Preference Lists**: `main_model`, `fast_model`, and `compact_model` accept either a single string or a list of model selectors. When you provide a list, Klaude first tries matching providers in `provider_list` order for each selector, then moves to the next selector.
+- **Updating Defaults**: `/model` keeps saving the selected model back to `main_model`, but preserves fallback order by moving or inserting the selected model at the front of the list.
 
 ##### Sub-agent Model Configuration
 
@@ -332,7 +318,7 @@ Inside the interactive session (`klaude`), use these commands to streamline your
 - `/refresh-terminal` - Refresh terminal display.
 - `/web` - Switch to web UI mode.
 - `/new` - Start a new session (clears context).
-- `/model` - Switch the active LLM during the session.
+- `/model` - Switch the active LLM and update `main_model` in config while preserving fallback order (the selected model is moved/inserted to the front).
 - `/sub-agent-model` - Configure sub-agent models at runtime.
 - `/thinking` - Change thinking/reasoning level.
 - `/status` - Show session usage statistics (cost, tokens, model breakdown).

{klaude_code-2.27.0 → klaude_code-2.29.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "klaude-code"
-version = "2.27.0"
+version = "2.29.0"
 description = "Minimal code agent CLI"
 readme = "README.md"
 requires-python = ">=3.13"
@@ -15,18 +15,20 @@ dependencies = [
     "filelock>=3.20.3",
     "fastapi",
     "google-genai>=1.56.0",
+    "httpx[socks]>=0.28.1",
     "markdown-it-py>=4.0.0",
     "openai>=2.24.0",
     "prompt-toolkit>=3.0.52",
     "pydantic>=2.11.7",
-    "python-socks>=2.8.1",
     "pyyaml>=6.0.2",
     "rich>=14.1.0",
+    "socksio>=1.0.0",
     "sse-starlette",
     "trafilatura>=2.0.0",
     "typer>=0.17.3",
     "uvicorn",
     "readability-lxml>=0.8.4.1",
+    "pillow>=12.2.0",
 ]
 
 [project.scripts]

{klaude_code-2.27.0 → klaude_code-2.29.0}/src/klaude_code/agent/agent.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from collections.abc import AsyncGenerator, Awaitable, Callable, Iterable
 
-from klaude_code.agent.agent_profile import AgentProfile
+from klaude_code.agent.agent_profile import AgentProfile, ModelProfileProvider
 from klaude_code.agent.task import SessionContext, TaskExecutionContext, TaskExecutor
 from klaude_code.llm import LLMClientABC
 from klaude_code.log import DebugType, log_debug
@@ -32,14 +32,17 @@ class Agent:
             ]
             | None
         ) = None,
+        model_profile_provider: ModelProfileProvider | None = None,
     ):
         self.session: Session = session
         self.profile: AgentProfile = profile
         self.compact_llm_client: LLMClientABC | None = compact_llm_client
         self._current_task: TaskExecutor | None = None
+        self._follow_up_queue: list[UserInputPayload] = [item.model_copy(deep=True) for item in session.follow_up_queue]
         self._last_interrupt_show_notice = True
         self._last_interrupt_prefill_text: str | None = None
         self.request_user_interaction = request_user_interaction
+        self._model_profile_provider = model_profile_provider
         if not self.session.model_name:
             self.session.model_name = profile.llm_client.model_name
 
@@ -52,6 +55,37 @@ class Agent:
         self._last_interrupt_prefill_text = None
         return text
 
+    def follow_up(self, user_input: UserInputPayload) -> int:
+        """Queue a user message to run after the active task completes."""
+
+        self._follow_up_queue.append(user_input)
+        self.session.set_follow_up_queue(self._follow_up_queue)
+        return len(self._follow_up_queue)
+
+    def follow_up_count(self) -> int:
+        return len(self._follow_up_queue)
+
+    def follow_up_snapshot(self) -> tuple[UserInputPayload, ...]:
+        return tuple(self._follow_up_queue)
+
+    def pop_all_follow_up(self) -> tuple[UserInputPayload, ...]:
+        messages = tuple(self._follow_up_queue)
+        self._follow_up_queue.clear()
+        self.session.set_follow_up_queue(self._follow_up_queue)
+        return messages
+
+    def peek_next_follow_up(self) -> UserInputPayload | None:
+        if not self._follow_up_queue:
+            return None
+        return self._follow_up_queue[0]
+
+    def pop_next_follow_up(self) -> UserInputPayload | None:
+        if not self._follow_up_queue:
+            return None
+        message = self._follow_up_queue.pop(0)
+        self.session.set_follow_up_queue(self._follow_up_queue)
+        return message
+
     def on_interrupt(self) -> Iterable[events.Event]:
         """Handle an interrupt by emitting best-effort cleanup events.
 
@@ -98,6 +132,7 @@ class Agent:
             tool_registry=tool_registry,
             sub_agent_state=self.session.sub_agent_state,
             compact_llm_client=self.compact_llm_client,
+            apply_llm_client_change=self._apply_llm_client_change,
         )
 
         task = TaskExecutor(context)
@@ -127,6 +162,26 @@ class Agent:
         self.profile = profile
         self.session.model_name = profile.llm_client.model_name
 
+    def _apply_llm_client_change(self, llm_client: LLMClientABC) -> AgentProfile:
+        if self._model_profile_provider is None:
+            profile = AgentProfile(
+                llm_client=llm_client,
+                system_prompt=self.profile.system_prompt,
+                tools=self.profile.tools,
+                attachments=self.profile.attachments,
+            )
+        else:
+            sub_agent_type = None
+            if self.session.sub_agent_state is not None and not self.session.sub_agent_state.fork_context:
+                sub_agent_type = self.session.sub_agent_state.sub_agent_type
+            profile = self._model_profile_provider.build_profile(
+                llm_client,
+                sub_agent_type,
+                work_dir=self.session.work_dir,
+            )
+        self.set_model_profile(profile)
+        return profile
+
     def get_llm_client(self) -> LLMClientABC:
         return self.profile.llm_client
 

{klaude_code-2.27.0 → klaude_code-2.29.0}/src/klaude_code/agent/agent_profile.py

@@ -44,7 +44,7 @@ MAIN_AGENT_COMMON_BASE_TOOLS: list[str] = [tools.BASH, tools.READ]
 MAIN_AGENT_GPT5_DIFF_TOOLS: list[str] = [tools.APPLY_PATCH, tools.TODO_WRITE]
 MAIN_AGENT_NON_GPT5_DIFF_TOOLS: list[str] = [tools.EDIT, tools.WRITE, tools.TODO_WRITE]
 MAIN_AGENT_COMMON_TOOLS: list[str] = [
-    tools.HANDOFF,
+    # tools.HANDOFF,
     tools.AGENT,
     tools.WEB_FETCH,
     tools.WEB_SEARCH,

klaude_code-2.29.0/src/klaude_code/agent/attachments/__init__.py

@@ -0,0 +1,46 @@
+"""Agent attachment package.
+
+Shared helpers for <system-reminder> content produced by attachments live here.
+Each concrete attachment (files, memory, skills, …) is responsible for
+truncating its own output; these helpers provide a consistent Read-tool-style
+notice so the agent always knows how to fetch the full content.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class LineTruncationResult:
+    """Outcome of :func:`truncate_text_by_lines`."""
+
+    text: str
+    total_lines: int
+    kept_lines: int
+    truncated: bool
+
+    @property
+    def hidden_lines(self) -> int:
+        return max(0, self.total_lines - self.kept_lines)
+
+
+def truncate_text_by_lines(text: str, *, max_lines: int) -> LineTruncationResult:
+    """Keep the first ``max_lines`` lines; report total/hidden line counts.
+
+    The trailing newline (if any) is preserved only when the text was not
+    truncated, matching Read tool behaviour where a truncated view never
+    ends with a bare newline before the notice.
+    """
+    if max_lines <= 0:
+        return LineTruncationResult(
+            text="", total_lines=text.count("\n") + (1 if text else 0), kept_lines=0, truncated=bool(text)
+        )
+
+    lines = text.splitlines()
+    total = len(lines)
+    if total <= max_lines:
+        return LineTruncationResult(text=text, total_lines=total, kept_lines=total, truncated=False)
+
+    kept = "\n".join(lines[:max_lines])
+    return LineTruncationResult(text=kept, total_lines=total, kept_lines=max_lines, truncated=True)

{klaude_code-2.27.0 → klaude_code-2.29.0}/src/klaude_code/agent/attachments/files.py

@@ -5,13 +5,17 @@ import re
 import shlex
 from pathlib import Path
 
+from klaude_code.const import ATTACHMENT_DIFF_MAX_LINES, ATTACHMENT_DIFF_SOURCE_MAX_BYTES
 from klaude_code.prompts.attachments import (
     FILE_ALREADY_IN_CONTEXT_TEMPLATE,
+    FILE_CHANGED_DIFF_SKIPPED_TEMPLATE,
+    FILE_CHANGED_DIFF_TRUNCATED_TEMPLATE,
     FILE_CHANGED_EXTERNALLY_TEMPLATE,
     PASTE_FILE_HINT_TEMPLATE,
     TOOL_RESULT_TEMPLATE,
 )
 from klaude_code.protocol import message, tools
+from klaude_code.protocol.input_syntax import AT_FILE_PATTERN
 from klaude_code.protocol.models import (
     AtFileImagesUIItem,
     AtFileOp,
@@ -28,6 +32,7 @@ from klaude_code.session import Session
 from klaude_code.skill.loader import discover_skills_near_paths
 from klaude_code.tool import BashTool, ReadTool
 
+from . import truncate_text_by_lines
 from .memory import Memory, discover_memory_files_near_paths, format_memory_content
 from .skills import build_dynamic_skill_listing_attachment
 from .state import (
@@ -57,18 +62,6 @@ def _fmt_paste_file_hint(pasted_files: dict[str, str]) -> str:
     return PASTE_FILE_HINT_TEMPLATE.format(mapping=mapping)
 
 
-# Match @ preceded by whitespace, start of line, or -> (ReadTool line number arrow)
-# Supports optional line range suffix: @file.txt#L10-20 or @file.txt#L10.
-_AT_PLAIN_STOP_CHARS = (
-    r"\u3000-\u303f"
-    r"\uff01-\uff0f"
-    r"\uff1a-\uff20"
-    r"\uff3b-\uff40"
-    r"\uff5b-\uff65"
-)
-AT_FILE_PATTERN = re.compile(rf'(?:(?<!\S)|(?<=\u2192))@("(?P<quoted>[^"]+)"|(?P<plain>[^\s{_AT_PLAIN_STOP_CHARS}]+))')
-
-
 class AtFileRef:
     """Parsed @file reference with optional line range."""
 
@@ -120,7 +113,7 @@ async def _load_at_file(
     ref: AtFileRef,
     at_ops: list[AtFileOp],
     formatted_blocks: list[str],
-    collected_images: list[message.ImageURLPart],
+    collected_images: list[message.ImageURLPart | message.ImageFilePart],
     collected_image_paths: list[str],
     discovered_memories: list[Memory],
     skill_discovery_paths: list[str],
@@ -141,7 +134,7 @@ async def _load_at_file(
             limit = ref.line_end - ref.line_start + 1
         args = ReadTool.ReadArguments(file_path=path_str, offset=offset, limit=limit)
         tool_result = await ReadTool.call_with_args(args, tool_context)
-        images = [part for part in tool_result.parts if isinstance(part, message.ImageURLPart)]
+        images = [part for part in tool_result.parts if isinstance(part, (message.ImageURLPart, message.ImageFilePart))]
 
         formatted_blocks.append(
             _fmt_tool_result(tools.READ, args.model_dump_json(exclude_none=True), tool_result.output_text)
@@ -210,7 +203,7 @@ async def at_file_reader_attachment(session: Session) -> message.DeveloperMessag
 
     at_ops: list[AtFileOp] = []
     formatted_blocks: list[str] = []
-    collected_images: list[message.ImageURLPart] = []
+    collected_images: list[message.ImageURLPart | message.ImageFilePart] = []
     collected_image_paths: list[str] = []
     discovered_memories: list[Memory] = []
     skill_discovery_paths: list[str] = []
@@ -254,7 +247,27 @@ async def at_file_reader_attachment(session: Session) -> message.DeveloperMessag
     )
 
 
-def _compute_diff_snippet(old_content: str, new_content: str) -> str:
+def _compute_diff_snippet(old_content: str, new_content: str, file_path: str) -> str:
+    """Render a small unified-style diff, capped so it cannot blow up context.
+
+    Guards (see ``const.ATTACHMENT_DIFF_*``):
+
+    * If ``old_content + new_content`` already exceeds the source size limit,
+      skip ``difflib`` entirely. Large HTML/minified blobs produce diffs that
+      approach ``2x`` the source, which in past sessions pushed the next turn
+      past the 1M-token ceiling even after a successful compaction.
+    * After the diff is built, keep only the first ``ATTACHMENT_DIFF_MAX_LINES``
+      lines and append a Read-tool-style notice, mirroring how the Read tool
+      truncates long files.
+    """
+    combined_size_bytes = len(old_content.encode("utf-8")) + len(new_content.encode("utf-8"))
+    if combined_size_bytes > ATTACHMENT_DIFF_SOURCE_MAX_BYTES:
+        return FILE_CHANGED_DIFF_SKIPPED_TEMPLATE.format(
+            total_bytes=combined_size_bytes,
+            limit_bytes=ATTACHMENT_DIFF_SOURCE_MAX_BYTES,
+            file_path=file_path,
+        )
+
     old_lines = old_content.splitlines(keepends=True)
     new_lines = new_content.splitlines(keepends=True)
 
@@ -280,7 +293,15 @@ def _compute_diff_snippet(old_content: str, new_content: str) -> str:
                     diff_lines.append(f"  {line_no:>6}+\t{line.rstrip()}")
         diff_lines.append("  ------")
 
-    return "\n".join(diff_lines).rstrip("\n -")
+    rendered = "\n".join(diff_lines).rstrip("\n -")
+    truncation = truncate_text_by_lines(rendered, max_lines=ATTACHMENT_DIFF_MAX_LINES)
+    if truncation.truncated:
+        return truncation.text + FILE_CHANGED_DIFF_TRUNCATED_TEMPLATE.format(
+            hidden_lines=truncation.hidden_lines,
+            total_lines=truncation.total_lines,
+            file_path=file_path,
+        )
+    return truncation.text
 
 
 async def file_changed_externally_attachment(session: Session) -> message.DeveloperMessage | None:
@@ -316,7 +337,7 @@ async def file_changed_externally_attachment(session: Session) -> message.Develo
             if new_status is None or new_status.cached_content is None:
                 continue
 
-            snippet = _compute_diff_snippet(old_content, new_status.cached_content)
+            snippet = _compute_diff_snippet(old_content, new_status.cached_content, path)
             if not snippet:
                 continue
             changed_files.append((path, snippet))
@@ -377,7 +398,15 @@ async def paste_file_attachment(session: Session) -> message.DeveloperMessage |
     for item in reversed(session.conversation_history):
         if isinstance(item, message.ToolResultMessage):
             return None
-        if isinstance(item, message.UserMessage) and item.pasted_files:
+        if (
+            isinstance(item, message.DeveloperMessage)
+            and item.ui_extra is not None
+            and any(isinstance(ui_item, PasteFilesUIItem) for ui_item in item.ui_extra.items)
+        ):
+            return None
+        if isinstance(item, message.UserMessage):
+            if not item.pasted_files:
+                return None
             return message.DeveloperMessage(
                 parts=message.text_parts_from_str(
                     f"<system-reminder>{_fmt_paste_file_hint(item.pasted_files)}\n</system-reminder>"

{klaude_code-2.27.0 → klaude_code-2.29.0}/src/klaude_code/agent/attachments/memory.py

@@ -5,11 +5,18 @@ from pathlib import Path
 
 from pydantic import BaseModel
 
-from klaude_code.const import ProjectPaths, find_git_repo_root, project_key_from_path
+from klaude_code.const import (
+    ATTACHMENT_MEMORY_MAX_BYTES_PER_FILE,
+    ATTACHMENT_MEMORY_MAX_LINES,
+    ProjectPaths,
+    find_git_repo_root,
+    project_key_from_path,
+)
 from klaude_code.prompts.attachments import (
     AUTO_MEMORY_HINT_TEMPLATE,
     AUTO_MEMORY_INSTRUCTION,
     DISCOVERED_MEMORY_INSTRUCTION,
+    MEMORY_FILE_BYTE_TRUNCATED_TEMPLATE,
     MEMORY_FILE_TRUNCATED_TEMPLATE,
     MEMORY_HEADER,
     MEMORY_TRUNCATED_TEMPLATE,
@@ -20,13 +27,16 @@ from klaude_code.protocol import message
 from klaude_code.protocol.models import DeveloperUIExtra, DeveloperUIItem, MemoryFileLoaded, MemoryLoadedUIItem
 from klaude_code.session import Session
 
+from . import truncate_text_by_lines
 from .state import is_memory_loaded, mark_memory_loaded
 
 MEMORY_FILE_NAMES = ["AGENTS.md", "CLAUDE.md", "AGENT.md"]
 
 AUTO_MEMORY_FILE = "MEMORY.md"
-AUTO_MEMORY_MAX_LINES = 200
-MEMORY_MAX_BYTES_PER_FILE = 4096
+# Kept as module-level aliases for backwards compatibility with existing tests
+# and callers. See src/klaude_code/const.py for the canonical values.
+AUTO_MEMORY_MAX_LINES = ATTACHMENT_MEMORY_MAX_LINES
+MEMORY_MAX_BYTES_PER_FILE = ATTACHMENT_MEMORY_MAX_BYTES_PER_FILE
 MEMORY_MAX_SESSION_BYTES = 60 * 1024
 
 
@@ -131,23 +141,31 @@ def format_memories_attachment(memories: list[Memory], include_header: bool = Tr
 
 
 def truncate_memory_content(text: str, path: str) -> str:
-    """Truncate memory content to the shared per-file limits used by attachments."""
+    """Truncate memory content to the first :data:`AUTO_MEMORY_MAX_LINES` lines.
 
-    lines = text.splitlines()
-    truncated = False
+    Mirrors Read tool behaviour: show a bounded prefix and tell the agent how
+    to fetch the rest. A generous byte cap still applies as a last-resort
+    guard against pathologically long single lines (e.g. minified JSON).
+    """
+    truncation = truncate_text_by_lines(text, max_lines=AUTO_MEMORY_MAX_LINES)
+    result = truncation.text
 
-    if len(lines) > AUTO_MEMORY_MAX_LINES:
-        lines = lines[:AUTO_MEMORY_MAX_LINES]
-        truncated = True
-
-    result = "\n".join(lines)
     if len(result.encode("utf-8")) > MEMORY_MAX_BYTES_PER_FILE:
         encoded = result.encode("utf-8")[:MEMORY_MAX_BYTES_PER_FILE]
         result = encoded.decode("utf-8", errors="ignore")
-        truncated = True
-
-    if truncated:
-        result += MEMORY_FILE_TRUNCATED_TEMPLATE.format(max_bytes=MEMORY_MAX_BYTES_PER_FILE, path=path)
+        total_lines = truncation.total_lines or len(text.splitlines())
+        return result + MEMORY_FILE_BYTE_TRUNCATED_TEMPLATE.format(
+            max_bytes=MEMORY_MAX_BYTES_PER_FILE,
+            total_lines=total_lines,
+            path=path,
+        )
+
+    if truncation.truncated:
+        return result + MEMORY_FILE_TRUNCATED_TEMPLATE.format(
+            max_lines=AUTO_MEMORY_MAX_LINES,
+            total_lines=truncation.total_lines,
+            path=path,
+        )
     return result