klaude-code 1.2.21__tar.gz → 1.2.23__tar.gz

{klaude_code-1.2.21 → klaude_code-1.2.23}/PKG-INFO

@@ -1,10 +1,11 @@
 Metadata-Version: 2.3
 Name: klaude-code
-Version: 1.2.21
+Version: 1.2.23
 Summary: Add your description here
 Requires-Dist: anthropic>=0.66.0
 Requires-Dist: chardet>=5.2.0
 Requires-Dist: ddgs>=9.9.3
+Requires-Dist: diff-match-patch>=20241021
 Requires-Dist: openai>=1.102.0
 Requires-Dist: pillow>=12.0.0
 Requires-Dist: prompt-toolkit>=3.0.52
@@ -17,18 +18,23 @@ Requires-Dist: typer>=0.17.3
 Requires-Python: >=3.13
 Description-Content-Type: text/markdown
 
-# Minimal Code Agent CLI (Klaude Code)
-
-An minimal and opinionated code agent with multi-model support.
-
-## Key Features
-- **Adaptive Tooling**: Model-aware toolsets (Claude Code tools for Sonnet, Codex `apply_patch` for GPT-5.1/Codex).
-- **Multi-Provider Support**: Compatible with `anthropic-messages-api`,`openai-responses-api`, and `openai-compatible-api`(`openrouter-api`),  featuring interleaved thinking, OpenRouter's provider sorting etc.
-- **Structured Sub-Agent Output**: Main agent defines output JSON schema for sub-agents; sub-agents use `report_back` tool with constrained decoding to return schema-compliant structured data.
-- **Skill System**: Extensible support for loading Claude Skills.
-- **Session Management**: Robust context preservation with resumable sessions (`--continue`).
-- **Simple TUI**: Clean interface offering full visibility into model responses, reasoning and actions.
-- **Core Utilities**: Slash commands, sub-agents, image pasting, terminal notifications, file mentioning, and auto-theming.
+# Klaude Code
+
+Multi-model code agent CLI.
+
+## Features
+- **Multi-provider**: Anthropic, OpenAI Responses API, OpenRouter
+- **Keep reasoning item in context**: Interleaved thinking support
+- **Model-aware tools**: Claude Code tools for Sonnet, `apply_patch` for GPT-5/Codex
+- **Structured sub-agent output**: Define JSON schema, get schema-compliant responses via constrained decoding
+- **Recursive `@file` mentions**: Circular dependency protection, relative path resolution
+- **Reminders**: Cooldown-based todo tracking and instruction reinforcement
+- **External file sync**: Monitoring for external edits (linter, manual)
+- **Interrupt handling**: Ctrl+C preserves partial responses and synthesizes tool cancellation results
+- **Output truncation**: Large outputs saved to file system with snapshot links
+- **Skills**: Built-in + user + project Agent Skills (with implicit invocation by Skill tool or explicit invocation by typing `$`)
+- **Sessions**: Resumable with `--continue`
+- **Extras**: Slash commands, sub-agents, image paste, terminal notifications, auto-theming
 
 ## Installation
 

{klaude_code-1.2.21 → klaude_code-1.2.23}/README.md

@@ -1,15 +1,20 @@
-# Minimal Code Agent CLI (Klaude Code)
-
-An minimal and opinionated code agent with multi-model support.
-
-## Key Features
-- **Adaptive Tooling**: Model-aware toolsets (Claude Code tools for Sonnet, Codex `apply_patch` for GPT-5.1/Codex).
-- **Multi-Provider Support**: Compatible with `anthropic-messages-api`,`openai-responses-api`, and `openai-compatible-api`(`openrouter-api`),  featuring interleaved thinking, OpenRouter's provider sorting etc.
-- **Structured Sub-Agent Output**: Main agent defines output JSON schema for sub-agents; sub-agents use `report_back` tool with constrained decoding to return schema-compliant structured data.
-- **Skill System**: Extensible support for loading Claude Skills.
-- **Session Management**: Robust context preservation with resumable sessions (`--continue`).
-- **Simple TUI**: Clean interface offering full visibility into model responses, reasoning and actions.
-- **Core Utilities**: Slash commands, sub-agents, image pasting, terminal notifications, file mentioning, and auto-theming.
+# Klaude Code
+
+Multi-model code agent CLI.
+
+## Features
+- **Multi-provider**: Anthropic, OpenAI Responses API, OpenRouter
+- **Keep reasoning item in context**: Interleaved thinking support
+- **Model-aware tools**: Claude Code tools for Sonnet, `apply_patch` for GPT-5/Codex
+- **Structured sub-agent output**: Define JSON schema, get schema-compliant responses via constrained decoding
+- **Recursive `@file` mentions**: Circular dependency protection, relative path resolution
+- **Reminders**: Cooldown-based todo tracking and instruction reinforcement
+- **External file sync**: Monitoring for external edits (linter, manual)
+- **Interrupt handling**: Ctrl+C preserves partial responses and synthesizes tool cancellation results
+- **Output truncation**: Large outputs saved to file system with snapshot links
+- **Skills**: Built-in + user + project Agent Skills (with implicit invocation by Skill tool or explicit invocation by typing `$`)
+- **Sessions**: Resumable with `--continue`
+- **Extras**: Slash commands, sub-agents, image paste, terminal notifications, auto-theming
 
 ## Installation
 

{klaude_code-1.2.21 → klaude_code-1.2.23}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "klaude-code"
-version = "1.2.21"
+version = "1.2.23"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"
@@ -12,6 +12,7 @@ dependencies = [
     "anthropic>=0.66.0",
     "chardet>=5.2.0",
     "ddgs>=9.9.3",
+    "diff-match-patch>=20241021",
     "openai>=1.102.0",
     "pillow>=12.0.0",
     "prompt-toolkit>=3.0.52",
@@ -80,6 +81,7 @@ layers = [
     "klaude_code.cli",
     "klaude_code.ui",
     "klaude_code.core",
+    "klaude_code.skill",
     "klaude_code.command",
     "klaude_code.session",
     "klaude_code.config",

{klaude_code-1.2.21 → klaude_code-1.2.23}/src/klaude_code/cli/debug.py

@@ -1,6 +1,5 @@
 """Debug utilities for CLI."""
 
-import os
 import subprocess
 import sys
 from pathlib import Path
@@ -45,16 +44,15 @@ def resolve_debug_settings(flag: bool, raw_filters: str | None) -> tuple[bool, s
 def open_log_file_in_editor(path: Path) -> None:
     """Open the given log file in a text editor without blocking the CLI."""
 
-    editor = os.environ.get("EDITOR")
+    editor = ""
 
-    if not editor:
-        for cmd in ["open", "xdg-open", "code", "TextEdit", "notepad"]:
-            try:
-                subprocess.run(["which", cmd], check=True, capture_output=True)
-                editor = cmd
-                break
-            except (subprocess.CalledProcessError, FileNotFoundError):
-                continue
+    for cmd in ["code", "TextEdit", "notepad"]:
+        try:
+            subprocess.run(["which", cmd], check=True, capture_output=True)
+            editor = cmd
+            break
+        except (subprocess.CalledProcessError, FileNotFoundError):
+            continue
 
     if not editor:
         if sys.platform == "darwin":

{klaude_code-1.2.21 → klaude_code-1.2.23}/src/klaude_code/command/__init__.py

@@ -29,7 +29,6 @@ def ensure_commands_loaded() -> None:
     # Import and register commands in display order
     from .clear_cmd import ClearCommand
     from .debug_cmd import DebugCommand
-    from .diff_cmd import DiffCommand
     from .export_cmd import ExportCommand
     from .export_online_cmd import ExportOnlineCommand
     from .help_cmd import HelpCommand
@@ -48,7 +47,6 @@ def ensure_commands_loaded() -> None:
     register(ModelCommand())
     load_prompt_commands()
     register(StatusCommand())
-    register(DiffCommand())
     register(HelpCommand())
     register(ReleaseNotesCommand())
     register(TerminalSetupCommand())
@@ -63,7 +61,6 @@ def __getattr__(name: str) -> object:
     _commands_map = {
         "ClearCommand": "clear_cmd",
         "DebugCommand": "debug_cmd",
-        "DiffCommand": "diff_cmd",
         "ExportCommand": "export_cmd",
         "ExportOnlineCommand": "export_online_cmd",
         "HelpCommand": "help_cmd",

{klaude_code-1.2.21 → klaude_code-1.2.23}/src/klaude_code/command/status_cmd.py

@@ -22,7 +22,7 @@ def accumulate_session_usage(session: Session) -> AggregatedUsage:
     for item in session.conversation_history:
         if isinstance(item, model.TaskMetadataItem):
             task_count += 1
-            all_metadata.append(item.main)
+            all_metadata.append(item.main_agent)
             all_metadata.extend(item.sub_agent_task_metadata)
 
     # Aggregate by model+provider

{klaude_code-1.2.21 → klaude_code-1.2.23}/src/klaude_code/const/__init__.py

@@ -49,12 +49,9 @@ READ_CHAR_LIMIT_PER_LINE = 2000
 # Maximum number of lines to read from a file
 READ_GLOBAL_LINE_CAP = 2000
 
-# Maximum total characters to read
+# Maximum total characters to read (truncates beyond this limit)
 READ_MAX_CHARS = 50000
 
-# Maximum file size in KB for text files
-READ_MAX_KB = 256
-
 # Maximum image file size in bytes (4MB)
 READ_MAX_IMAGE_BYTES = 4 * 1024 * 1024
 
@@ -93,17 +90,23 @@ INVALID_TOOL_CALL_MAX_LENGTH = 500
 TRUNCATE_DISPLAY_MAX_LINE_LENGTH = 1000
 
 # Maximum lines for truncated display output
-TRUNCATE_DISPLAY_MAX_LINES = 20
+TRUNCATE_DISPLAY_MAX_LINES = 8
 
 # Maximum lines for sub-agent result display
-SUB_AGENT_RESULT_MAX_LINES = 12
+SUB_AGENT_RESULT_MAX_LINES = 20
 
 
 # UI refresh rate (frames per second) for debounced content streaming
 UI_REFRESH_RATE_FPS = 20
 
 # Number of lines to keep visible at bottom of markdown streaming window
-MARKDOWN_STREAM_LIVE_WINDOW = 20
+MARKDOWN_STREAM_LIVE_WINDOW = 6
+
+# Left margin (columns) to reserve when rendering markdown
+MARKDOWN_LEFT_MARGIN = 2
+
+# Right margin (columns) to reserve when rendering markdown
+MARKDOWN_RIGHT_MARGIN = 2
 
 # Status hint text shown after spinner status
 STATUS_HINT_TEXT = " (esc to interrupt)"

{klaude_code-1.2.21 → klaude_code-1.2.23}/src/klaude_code/core/manager/sub_agent_manager.py

@@ -89,7 +89,7 @@ Only the content passed to `report_back` will be returned to user.\
                     result = event.task_result
                 # Capture TaskMetadataEvent for metadata propagation
                 elif isinstance(event, events.TaskMetadataEvent):
-                    task_metadata = event.metadata.main
+                    task_metadata = event.metadata.main_agent
                 await self.emit_event(event)
             return SubAgentResult(
                 task_result=result,

{klaude_code-1.2.21 → klaude_code-1.2.23}/src/klaude_code/core/prompt.py

@@ -17,8 +17,9 @@ COMMAND_DESCRIPTIONS: dict[str, str] = {
 
 # Mapping from logical prompt keys to resource file paths under the core/prompt directory.
 PROMPT_FILES: dict[str, str] = {
-    "main_gpt_5_1": "prompts/prompt-codex-gpt-5-1.md",
+    "main_codex": "prompts/prompt-codex.md",
     "main_gpt_5_1_codex_max": "prompts/prompt-codex-gpt-5-1-codex-max.md",
+    "main_gpt_5_2_codex": "prompts/prompt-codex-gpt-5-2-codex.md",
     "main": "prompts/prompt-claude-code.md",
     "main_gemini": "prompts/prompt-gemini.md",  # https://ai.google.dev/gemini-api/docs/prompting-strategies?hl=zh-cn#agentic-si-template
 }
@@ -43,10 +44,12 @@ def _load_base_prompt(file_key: str) -> str:
 def _get_file_key(model_name: str, protocol: llm_param.LLMClientProtocol) -> str:
     """Determine which prompt file to use based on model."""
     match model_name:
+        case name if "gpt-5.2-codex" in name:
+            return "main_gpt_5_2_codex"
         case name if "gpt-5.1-codex-max" in name:
             return "main_gpt_5_1_codex_max"
         case name if "gpt-5" in name:
-            return "main_gpt_5_1"
+            return "main_codex"
         case name if "gemini" in name:
             return "main_gemini"
         case _:

klaude_code-1.2.23/src/klaude_code/core/prompts/prompt-codex-gpt-5-2-codex.md

@@ -0,0 +1,117 @@
+You are Codex, based on GPT-5. You are running as a coding agent in the Codex CLI on a user's computer.
+
+## General
+
+- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
+
+## Editing constraints
+
+- Default to ASCII when editing or creating files. Only introduce non-ASCII or other Unicode characters when there is a clear justification and the file already uses them.
+- Add succinct code comments that explain what is going on if code is not self-explanatory. You should not add comments like "Assigns the value to the variable", but a brief comment might be useful ahead of a complex code block that the user would otherwise have to spend time parsing out. Usage of these comments should be rare.
+- Try to use apply_patch for single file edits, but it is fine to explore other options to make the edit if it does not work well. Do not use apply_patch for changes that are auto-generated (i.e. generating package.json or running a lint or format command like gofmt) or when scripting is more efficient (such as search and replacing a string across a codebase).
+- You may be in a dirty git worktree.
+    * NEVER revert existing changes you did not make unless explicitly requested, since these changes were made by the user.
+    * If asked to make a commit or code edits and there are unrelated changes to your work or changes that you didn't make in those files, don't revert those changes.
+    * If the changes are in files you've touched recently, you should read carefully and understand how you can work with the changes rather than reverting them.
+    * If the changes are in unrelated files, just ignore them and don't revert them.
+- Do not amend a commit unless explicitly requested to do so.
+- While you are working, you might notice unexpected changes that you didn't make. If this happens, STOP IMMEDIATELY and ask the user how they would like to proceed.
+- **NEVER** use destructive commands like `git reset --hard` or `git checkout --` unless specifically requested or approved by the user.
+
+## Plan tool
+
+When using the planning tool:
+- Skip using the planning tool for straightforward tasks (roughly the easiest 25%).
+- Do not make single-step plans.
+- When you made a plan, update it after having performed one of the sub-tasks that you shared on the plan.
+
+## Codex CLI harness, sandboxing, and approvals
+
+The Codex CLI harness supports several different configurations for sandboxing and escalation approvals that the user can choose from.
+
+Filesystem sandboxing defines which files can be read or written. The options for `sandbox_mode` are:
+- **read-only**: The sandbox only permits reading files.
+- **workspace-write**: The sandbox permits reading files, and editing files in `cwd` and `writable_roots`. Editing files in other directories requires approval.
+- **danger-full-access**: No filesystem sandboxing - all commands are permitted.
+
+Network sandboxing defines whether network can be accessed without approval. Options for `network_access` are:
+- **restricted**: Requires approval
+- **enabled**: No approval needed
+
+Approvals are your mechanism to get user consent to run shell commands without the sandbox. Possible configuration options for `approval_policy` are
+- **untrusted**: The harness will escalate most commands for user approval, apart from a limited allowlist of safe "read" commands.
+- **on-failure**: The harness will allow all commands to run in the sandbox (if enabled), and failures will be escalated to the user for approval to run again without the sandbox.
+- **on-request**: Commands will be run in the sandbox by default, and you can specify in your tool call if you want to escalate a command to run without sandboxing. (Note that this mode is not always available. If it is, you'll see parameters for it in the `shell` command description.)
+- **never**: This is a non-interactive mode where you may NEVER ask the user for approval to run commands. Instead, you must always persist and work around constraints to solve the task for the user. You MUST do your utmost best to finish the task and validate your work before yielding. If this mode is paired with `danger-full-access`, take advantage of it to deliver the best outcome for the user. Further, in this mode, your default testing philosophy is overridden: Even if you don't see local patterns for testing, you may add tests and scripts to validate your work. Just remove them before yielding.
+
+When you are running with `approval_policy == on-request`, and sandboxing enabled, here are scenarios where you'll need to request approval:
+- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /var)
+- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.
+- You are running sandboxed and need to run a command that requires network access (e.g. installing packages)
+- If you run a command that is important to solving the user's query, but it fails because of sandboxing, rerun the command with approval. ALWAYS proceed to use the `sandbox_permissions` and `justification` parameters - do not message the user before requesting approval for the command.
+- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for
+- (for all of these, you should weigh alternative paths that do not require approval)
+
+When `sandbox_mode` is set to read-only, you'll need to request approval for any command that isn't a read.
+
+You will be told what filesystem sandboxing, network sandboxing, and approval mode are active in a developer or user message. If you are not told about this, assume that you are running with workspace-write, network sandboxing enabled, and approval on-failure.
+
+Although they introduce friction to the user because your work is paused until the user responds, you should leverage them when necessary to accomplish important work. If the completing the task requires escalated permissions, Do not let these settings or the sandbox deter you from attempting to accomplish the user's task unless it is set to "never", in which case never ask for approvals.
+
+When requesting approval to execute a command that will require escalated privileges:
+  - Provide the `sandbox_permissions` parameter with the value `"require_escalated"`
+  - Include a short, 1 sentence explanation for why you need escalated permissions in the justification parameter
+
+## Special user requests
+
+- If the user makes a simple request (such as asking for the time) which you can fulfill by running a terminal command (such as `date`), you should do so.
+- If the user asks for a "review", default to a code review mindset: prioritise identifying bugs, risks, behavioural regressions, and missing tests. Findings must be the primary focus of the response - keep summaries or overviews brief and only after enumerating the issues. Present findings first (ordered by severity with file/line references), follow with open questions or assumptions, and offer a change-summary only as a secondary detail. If no findings are discovered, state that explicitly and mention any residual risks or testing gaps.
+
+## Frontend tasks
+When doing frontend design tasks, avoid collapsing into "AI slop" or safe, average-looking layouts.
+Aim for interfaces that feel intentional, bold, and a bit surprising.
+- Typography: Use expressive, purposeful fonts and avoid default stacks (Inter, Roboto, Arial, system).
+- Color & Look: Choose a clear visual direction; define CSS variables; avoid purple-on-white defaults. No purple bias or dark mode bias.
+- Motion: Use a few meaningful animations (page-load, staggered reveals) instead of generic micro-motions.
+- Background: Don't rely on flat, single-color backgrounds; use gradients, shapes, or subtle patterns to build atmosphere.
+- Overall: Avoid boilerplate layouts and interchangeable UI patterns. Vary themes, type families, and visual languages across outputs.
+- Ensure the page loads properly on both desktop and mobile
+
+Exception: If working within an existing website or design system, preserve the established patterns, structure, and visual language.
+
+## Presenting your work and final message
+
+You are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.
+
+- Default: be very concise; friendly coding teammate tone.
+- Ask only when needed; suggest ideas; mirror the user's style.
+- For substantial work, summarize clearly; follow final‑answer formatting.
+- Skip heavy formatting for simple confirmations.
+- Don't dump large files you've written; reference paths only.
+- No "save/copy this file" - User is on the same machine.
+- Offer logical next steps (tests, commits, build) briefly; add verify steps if you couldn't do something.
+- For code changes:
+  * Lead with a quick explanation of the change, and then give more details on the context covering where and why a change was made. Do not start this explanation with "summary", just jump right in.
+  * If there are natural next steps the user may want to take, suggest them at the end of your response. Do not make suggestions if there are no natural next steps.
+  * When suggesting multiple options, use numeric lists for the suggestions so the user can quickly respond with a single number.
+- The user does not command execution outputs. When asked to show the output of a command (e.g. `git show`), relay the important details in your answer or summarize the key lines so the user understands the result.
+
+### Final answer structure and style guidelines
+
+- Plain text; CLI handles styling. Use structure only when it helps scanability.
+- Headers: optional; short Title Case (1-3 words) wrapped in **…**; no blank line before the first bullet; add only if they truly help.
+- Bullets: use - ; merge related points; keep to one line when possible; 4–6 per list ordered by importance; keep phrasing consistent.
+- Monospace: backticks for commands/paths/env vars/code ids and inline examples; use for literal keyword bullets; never combine with **.
+- Code samples or multi-line snippets should be wrapped in fenced code blocks; include an info string as often as possible.
+- Structure: group related bullets; order sections general → specific → supporting; for subsections, start with a bolded keyword bullet, then items; match complexity to the task.
+- Tone: collaborative, concise, factual; present tense, active voice; self‑contained; no "above/below"; parallel wording.
+- Don'ts: no nested bullets/hierarchies; no ANSI codes; don't cram unrelated keywords; keep keyword lists short—wrap/reformat if long; avoid naming formatting styles in answers.
+- Adaptation: code explanations → precise, structured with code refs; simple tasks → lead with outcome; big changes → logical walkthrough + rationale + next actions; casual one-offs → plain sentences, no headers/bullets.
+- File References: When referencing files in your response follow the below rules:
+  * Use inline code to make file paths clickable.
+  * Each reference should have a stand alone path. Even if it's the same file.
+  * Accepted: absolute, workspace‑relative, a/ or b/ diff prefixes, or bare filename/suffix.
+  * Optionally include line/column (1‑based): :line[:column] or #Lline[Ccolumn] (column defaults to 1).
+  * Do not use URIs like file://, vscode://, or https://.
+  * Do not provide range of lines
+  * Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\repo\project\main.rs:12:5

klaude_code-1.2.21/src/klaude_code/core/prompts/prompt-codex-gpt-5-1.md → klaude_code-1.2.23/src/klaude_code/core/prompts/prompt-codex.md

@@ -1,4 +1,4 @@
-You are GPT-5.1 running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.
+You are GPT-5.2 running in the Codex CLI, a terminal-based coding assistant. Codex CLI is an open source project led by OpenAI. You are expected to be precise, safe, and helpful.
 
 Your capabilities:
 
@@ -14,7 +14,7 @@ Within this context, Codex refers to the open-source agentic coding interface (n
 
 Your default personality and tone is concise, direct, and friendly. You communicate efficiently, always keeping the user clearly informed about ongoing actions without unnecessary detail. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.
 
-# AGENTS.md spec
+## AGENTS.md spec
 - Repos often contain AGENTS.md files. These files can appear anywhere within the repository.
 - These files are a way for humans to give you (the agent) instructions or tips for working within the container.
 - Some examples might be: coding conventions, info about how code is organized, or instructions for how to run or test code.
@@ -24,7 +24,7 @@ Your default personality and tone is concise, direct, and friendly. You communic
     - Instructions about code style, structure, naming, etc. apply only to code within the AGENTS.md file's scope, unless the file states otherwise.
     - More-deeply-nested AGENTS.md files take precedence in the case of conflicting instructions.
     - Direct system/developer/user instructions (as part of a prompt) take precedence over AGENTS.md instructions.
-- The contents of the AGENTS.md file at the root of the repo and any directories from the CWD up to the root will be automatically included with the developer message (if exist) and don't need to be re-read.
+- The contents of the AGENTS.md file at the root of the repo and any directories from the CWD up to the root are included with the developer message and don't need to be re-read. When working in a subdirectory of CWD, or a directory outside the CWD, check for any AGENTS.md files that may be applicable.
 
 ## Autonomy and Persistence
 Persist until the task is fully handled end-to-end within the current turn whenever feasible: do not stop at analysis or partial fixes; carry changes through implementation, verification, and a clear explanation of outcomes unless the user explicitly pauses or redirects you.
@@ -33,33 +33,6 @@ Unless the user explicitly asks for a plan, asks a question about the code, is b
 
 ## Responsiveness
 
-### User Updates Spec
-You'll work for stretches with tool calls — it's critical to keep the user updated as you work.
-
-Frequency & Length:
-- Send short updates (1–2 sentences) whenever there is a meaningful, important insight you need to share with the user to keep them informed.
-- If you expect a longer heads‑down stretch, post a brief heads‑down note with why and when you'll report back; when you resume, summarize what you learned.
-- Only the initial plan, plan updates, and final recap can be longer, with multiple bullets and paragraphs
-
-Tone:
-- Friendly, confident, senior-engineer energy. Positive, collaborative, humble; fix mistakes quickly.
-
-Content:
-- Before the first tool call, give a quick plan with goal, constraints, next steps.
-- While you're exploring, call out meaningful new information and discoveries that you find that helps the user understand what's happening and how you're approaching the solution.
-- If you change the plan (e.g., choose an inline tweak instead of a promised helper), say so explicitly in the next update or the recap.
-
-**Examples:**
-
-- “I’ve explored the repo; now checking the API route definitions.”
-- “Next, I’ll patch the config and update the related tests.”
-- “I’m about to scaffold the CLI commands and helper functions.”
-- “Ok cool, so I’ve wrapped my head around the repo. Now digging into the API routes.”
-- “Config’s looking tidy. Next up is patching helpers to keep things in sync.”
-- “Finished poking at the DB gateway. I will now chase down error handling.”
-- “Alright, build pipeline order is interesting. Checking how it reports failures.”
-- “Spotted a clever caching util; now hunting where it gets used.”
-
 ## Planning
 
 You have access to an `update_plan` tool which tracks steps and progress and renders them to the user. Using the tool helps demonstrate that you've understood the task and convey how you're approaching it. Plans can help to make complex, ambiguous, or multi-phase work clearer and more collaborative for the user. A good plan should break the task into meaningful, logically ordered steps that are easy to verify as you go.
@@ -142,7 +115,7 @@ You MUST adhere to the following criteria when solving queries:
 - Working on the repo(s) in the current environment is allowed, even if they are proprietary.
 - Analyzing code for vulnerabilities is allowed.
 - Showing user code and tool call details is allowed.
-- Use the `apply_patch` tool to edit files (NEVER try `applypatch` or `apply-patch`, only `apply_patch`).
+- Use the `apply_patch` tool to edit files (NEVER try `applypatch` or `apply-patch`, only `apply_patch`). This is a FREEFORM tool, so do not wrap the patch in JSON.
 
 If completing the user's task requires writing or modifying files, your code and final answer should follow these coding guidelines, though user instructions (i.e. AGENTS.md) may override these guidelines:
 
@@ -151,6 +124,7 @@ If completing the user's task requires writing or modifying files, your code and
 - Do not attempt to fix unrelated bugs or broken tests. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)
 - Update documentation as necessary.
 - Keep changes consistent with the style of the existing codebase. Changes should be minimal and focused on the task.
+- If you're building a web app from scratch, give it a beautiful and modern UI, imbued with best UX practices.
 - Use `git log` and `git blame` to search the history of the codebase if additional context is required.
 - NEVER add copyright or license headers unless specifically requested.
 - Do not waste tokens by re-reading files after calling `apply_patch` on them. The tool call will fail if it didn't work. The same goes for making folders, deleting folders, etc.
@@ -161,7 +135,7 @@ If completing the user's task requires writing or modifying files, your code and
 
 ## Validating your work
 
-If the codebase has tests or the ability to build or run, consider using them to verify changes once your work is complete.
+If the codebase has tests, or the ability to build or run tests, consider using them to verify changes once your work is complete.
 
 When testing, your philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests.
 
@@ -183,15 +157,7 @@ If you're operating in an existing codebase, you should make sure you do exactly
 
 You should use judicious initiative to decide on the right level of detail and complexity to deliver based on the user's needs. This means showing good judgment that you're capable of doing the right extras without gold-plating. This might be demonstrated by high-value, creative touches when scope of the task is vague; while being surgical and targeted when scope is tightly specified.
 
-## Sharing progress updates
-
-For especially longer tasks that you work on (i.e. requiring many tool calls, or a plan with multiple steps), you should provide progress updates back to the user at reasonable intervals. These updates should be structured as a concise sentence or two (no more than 8-10 words long) recapping progress so far in plain language: this update demonstrates your understanding of what needs to be done, progress so far (i.e. files explores, subtasks complete), and where you're going next.
-
-Before doing large chunks of work that may incur latency as experienced by the user (i.e. writing a new file), you should send a concise message to the user with an update indicating what you're about to do to ensure they know what you're spending time on. Don't start editing or writing large files before informing the user what you are doing and why.
-
-The messages you send before tool calls should describe what is immediately about to be done next in very concise language. If there was previous work done, this preamble message should also include a note about the work done so far to bring the user along.
-
-## Presenting your work and final message
+## Presenting your work 
 
 Your final message should read naturally, like an update from a concise teammate. For casual conversation, brainstorming tasks, or quick questions from the user, respond in a friendly, conversational tone. You should ask questions, suggest ideas, and adapt to the user’s style. If you've finished a large amount of work, when describing what you've done to the user, you should follow the final answer formatting guidelines to communicate substantive changes. You don't need to add structured formatting for one-word answers, greetings, or purely conversational exchanges.
 
@@ -282,7 +248,8 @@ For casual greetings, acknowledgements, or other one-off conversational messages
 When using the shell, you must adhere to the following guidelines:
 
 - When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
-- Read files in chunks with a max chunk size of 250 lines. Do not use python scripts to attempt to output larger chunks of a file. Command line output will be truncated after 10 kilobytes or 256 lines of output, regardless of the command used.
+- Do not use python scripts to attempt to output larger chunks of a file.
+- Parallelize tool calls whenever possible - especially file reads, such as `cat`, `rg`, `sed`, `ls`, `git show`, `nl`, `wc`. Use `multi_tool_use.parallel` to parallelize tool calls and only this.
 
 ## apply_patch
 

{klaude_code-1.2.21 → klaude_code-1.2.23}/src/klaude_code/core/reminders.py

@@ -1,3 +1,4 @@
+import hashlib
 import re
 import shlex
 from collections.abc import Awaitable, Callable
@@ -8,8 +9,10 @@ from pydantic import BaseModel
 
 from klaude_code import const
 from klaude_code.core.tool import BashTool, ReadTool, reset_tool_context, set_tool_context_from_session
+from klaude_code.core.tool.file._utils import hash_text_sha256
 from klaude_code.protocol import model, tools
 from klaude_code.session import Session
+from klaude_code.skill import get_skill
 
 type Reminder = Callable[[Session], Awaitable[model.DeveloperMessageItem | None]]
 
@@ -17,6 +20,9 @@ type Reminder = Callable[[Session], Awaitable[model.DeveloperMessageItem | None]
 # Match @ preceded by whitespace, start of line, or → (ReadTool line number arrow)
 AT_FILE_PATTERN = re.compile(r'(?:(?<!\S)|(?<=\u2192))@("(?P<quoted>[^\"]+)"|(?P<plain>\S+))')
 
+# Match $skill or ¥skill at the beginning of the first line
+SKILL_PATTERN = re.compile(r"^[$¥](?P<skill>\S+)")
+
 
 def get_last_new_user_input(session: Session) -> str | None:
     """Get last user input & developer message (CLAUDE.md) from conversation history. if there's a tool result after user input, return None"""
@@ -71,6 +77,21 @@ def get_at_patterns_with_source(session: Session) -> list[AtPatternSource]:
     return patterns
 
 
+def get_skill_from_user_input(session: Session) -> str | None:
+    """Get $skill reference from the first line of last user input."""
+    for item in reversed(session.conversation_history):
+        if isinstance(item, model.ToolResultItem):
+            return None
+        if isinstance(item, model.UserMessageItem):
+            content = item.content or ""
+            first_line = content.split("\n", 1)[0]
+            m = SKILL_PATTERN.match(first_line)
+            if m:
+                return m.group("skill")
+            return None
+    return None
+
+
 async def _load_at_file_recursive(
     session: Session,
     pattern: str,
@@ -262,7 +283,17 @@ async def file_changed_externally_reminder(
     if session.file_tracker and len(session.file_tracker) > 0:
         for path, status in session.file_tracker.items():
             try:
-                if Path(path).stat().st_mtime > status.mtime:
+                current_mtime = Path(path).stat().st_mtime
+
+                changed = False
+                if status.content_sha256 is not None:
+                    current_sha256 = _compute_file_content_sha256(path)
+                    changed = current_sha256 is not None and current_sha256 != status.content_sha256
+                else:
+                    # Backward-compat: old sessions only tracked mtime.
+                    changed = current_mtime != status.mtime
+
+                if changed:
                     context_token = set_tool_context_from_session(session)
                     try:
                         tool_result = await ReadTool.call_with_args(
@@ -299,6 +330,24 @@ async def file_changed_externally_reminder(
     return None
 
 
+def _compute_file_content_sha256(path: str) -> str | None:
+    """Compute SHA-256 for file content using the same decoding behavior as ReadTool."""
+
+    try:
+        suffix = Path(path).suffix.lower()
+        if suffix in {".png", ".jpg", ".jpeg", ".gif", ".webp"}:
+            with open(path, "rb") as f:
+                return hashlib.sha256(f.read()).hexdigest()
+
+        hasher = hashlib.sha256()
+        with open(path, encoding="utf-8", errors="replace") as f:
+            for line in f:
+                hasher.update(line.encode("utf-8"))
+        return hasher.hexdigest()
+    except (FileNotFoundError, IsADirectoryError, OSError, PermissionError, UnicodeDecodeError):
+        return None
+
+
 def get_memory_paths() -> list[tuple[Path, str]]:
     return [
         (
@@ -343,6 +392,36 @@ async def image_reminder(session: Session) -> model.DeveloperMessageItem | None:
     )
 
 
+async def skill_reminder(session: Session) -> model.DeveloperMessageItem | None:
+    """Load skill content when user references a skill with $skill syntax."""
+    skill_name = get_skill_from_user_input(session)
+    if not skill_name:
+        return None
+
+    # Get the skill from skill module
+    skill = get_skill(skill_name)
+    if not skill:
+        return None
+
+    # Get base directory from skill_path
+    base_dir = str(skill.skill_path.parent) if skill.skill_path else "unknown"
+
+    content = f"""<system-reminder>The user activated the "{skill.name}" skill. Here is the skill content:
+
+<skill>
+<name>{skill.name}</name>
+<base_dir>{base_dir}</base_dir>
+
+{skill.to_prompt()}
+</skill>
+</system-reminder>"""
+
+    return model.DeveloperMessageItem(
+        content=content,
+        skill_name=skill.name,
+    )
+
+
 def _is_memory_loaded(session: Session, path: str) -> bool:
     """Check if a memory file has already been loaded (tracked with is_memory=True)."""
     status = session.file_tracker.get(path)
@@ -355,7 +434,11 @@ def _mark_memory_loaded(session: Session, path: str) -> None:
         mtime = Path(path).stat().st_mtime
     except (OSError, FileNotFoundError):
         mtime = 0.0
-    session.file_tracker[path] = model.FileStatus(mtime=mtime, is_memory=True)
+    try:
+        content_sha256 = hash_text_sha256(Path(path).read_text(encoding="utf-8", errors="replace"))
+    except (OSError, FileNotFoundError, PermissionError, UnicodeDecodeError):
+        content_sha256 = None
+    session.file_tracker[path] = model.FileStatus(mtime=mtime, content_sha256=content_sha256, is_memory=True)
 
 
 async def memory_reminder(session: Session) -> model.DeveloperMessageItem | None:
@@ -476,6 +559,7 @@ ALL_REMINDERS = [
     last_path_memory_reminder,
     at_file_reader_reminder,
     image_reminder,
+    skill_reminder,
 ]
 
 
@@ -506,6 +590,7 @@ def load_agent_reminders(
             last_path_memory_reminder,
             file_changed_externally_reminder,
             image_reminder,
+            skill_reminder,
         ]
     )