@easbot/agent 0.2.6 → 0.2.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +21 -21
- package/dist/assets/txt/agent/generate.txt +75 -75
- package/dist/assets/txt/agent/prompt/compaction.txt +54 -54
- package/dist/assets/txt/agent/prompt/summary.txt +12 -12
- package/dist/assets/txt/command/builtin/arch.txt +26 -26
- package/dist/assets/txt/command/builtin/init.txt +10 -10
- package/dist/assets/txt/command/builtin/review.txt +97 -97
- package/dist/assets/txt/context/prompt/build-switch.txt +5 -5
- package/dist/assets/txt/context/prompt/coder-plan.txt +69 -69
- package/dist/assets/txt/context/prompt/codex.txt +79 -79
- package/dist/assets/txt/context/prompt/default.txt +105 -105
- package/dist/assets/txt/context/prompt/gpt.txt +107 -107
- package/dist/assets/txt/context/prompt/kimi.txt +95 -95
- package/dist/assets/txt/context/prompt/max-steps.txt +15 -15
- package/dist/assets/txt/context/prompt/plan-reminder-anthropic.txt +67 -67
- package/dist/assets/txt/context/prompt/plan.txt +27 -27
- package/dist/assets/txt/context/template/BOOTSTRAP.txt +238 -238
- package/dist/assets/txt/context/template/CONTEXT.txt +51 -51
- package/dist/assets/txt/model/graph-summary.txt +54 -54
- package/dist/assets/txt/model/graph.txt +85 -85
- package/dist/assets/txt/model/rerank.txt +42 -42
- package/dist/assets/txt/model/summary.txt +52 -52
- package/dist/assets/txt/session/prompt/build-switch.txt +5 -5
- package/dist/assets/txt/session/prompt/codex.txt +79 -79
- package/dist/assets/txt/session/prompt/default.txt +105 -105
- package/dist/assets/txt/session/prompt/gpt.txt +107 -107
- package/dist/assets/txt/session/prompt/kimi.txt +95 -95
- package/dist/assets/txt/session/prompt/max-steps.txt +15 -15
- package/dist/assets/txt/session/prompt/plan-reminder-anthropic.txt +67 -67
- package/dist/assets/txt/session/prompt/plan.txt +26 -26
- package/dist/assets/txt/tool/apply_patch.txt +53 -53
- package/dist/assets/txt/tool/batch.txt +23 -23
- package/dist/assets/txt/tool/edit.txt +10 -10
- package/dist/assets/txt/tool/glob.txt +6 -6
- package/dist/assets/txt/tool/grep.txt +8 -8
- package/dist/assets/txt/tool/ls.txt +6 -6
- package/dist/assets/txt/tool/lsp.txt +19 -19
- package/dist/assets/txt/tool/multiedit.txt +43 -43
- package/dist/assets/txt/tool/pty_manage.txt +60 -60
- package/dist/assets/txt/tool/question.txt +33 -33
- package/dist/assets/txt/tool/read.txt +14 -14
- package/dist/assets/txt/tool/todo.txt +124 -124
- package/dist/assets/txt/tool/webfetch.txt +13 -13
- package/dist/assets/txt/tool/websearch.txt +14 -14
- package/dist/assets/txt/tool/write.txt +8 -8
- package/dist/cli.cjs +1 -1
- package/dist/cli.mjs +1 -1
- package/dist/index.cjs +1 -1
- package/dist/index.mjs +1 -1
- package/package.json +12 -12
|
@@ -1,13 +1,13 @@
|
|
|
1
|
-
- Fetches content from a specified URL
|
|
2
|
-
- Takes a URL and optional format as input
|
|
3
|
-
- Fetches the URL content, converts to requested format (markdown by default)
|
|
4
|
-
- Returns the content in the specified format
|
|
5
|
-
- Use this tool when you need to retrieve and analyze web content
|
|
6
|
-
|
|
7
|
-
Usage notes:
|
|
8
|
-
- IMPORTANT: if another tool is present that offers better web fetching capabilities, is more targeted to the task, or has fewer restrictions, prefer using that tool instead of this one.
|
|
9
|
-
- The URL must be a fully-formed valid URL
|
|
10
|
-
- HTTP URLs will be automatically upgraded to HTTPS
|
|
11
|
-
- Format options: "markdown" (default), "text", or "html"
|
|
12
|
-
- This tool is read-only and does not modify any files
|
|
13
|
-
- Results may be summarized if the content is very large
|
|
1
|
+
- Fetches content from a specified URL
|
|
2
|
+
- Takes a URL and optional format as input
|
|
3
|
+
- Fetches the URL content, converts to requested format (markdown by default)
|
|
4
|
+
- Returns the content in the specified format
|
|
5
|
+
- Use this tool when you need to retrieve and analyze web content
|
|
6
|
+
|
|
7
|
+
Usage notes:
|
|
8
|
+
- IMPORTANT: if another tool is present that offers better web fetching capabilities, is more targeted to the task, or has fewer restrictions, prefer using that tool instead of this one.
|
|
9
|
+
- The URL must be a fully-formed valid URL
|
|
10
|
+
- HTTP URLs will be automatically upgraded to HTTPS
|
|
11
|
+
- Format options: "markdown" (default), "text", or "html"
|
|
12
|
+
- This tool is read-only and does not modify any files
|
|
13
|
+
- Results may be summarized if the content is very large
|
|
@@ -1,14 +1,14 @@
|
|
|
1
|
-
- Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs
|
|
2
|
-
- Provides up-to-date information for current events and recent data
|
|
3
|
-
- Supports configurable result counts and returns the content from the most relevant websites
|
|
4
|
-
- Use this tool for accessing information beyond knowledge cutoff
|
|
5
|
-
- Searches are performed automatically within a single API call
|
|
6
|
-
|
|
7
|
-
Usage notes:
|
|
8
|
-
- Supports live crawling modes: 'fallback' (backup if cached unavailable) or 'preferred' (prioritize live crawling)
|
|
9
|
-
- Search types: 'auto' (balanced), 'fast' (quick results), 'deep' (comprehensive search)
|
|
10
|
-
- Configurable context length for optimal LLM integration
|
|
11
|
-
- Domain filtering and advanced search options available
|
|
12
|
-
|
|
13
|
-
The current year is {{year}}. You MUST use this year when searching for recent information or current events
|
|
14
|
-
- Example: If the current year is 2026 and the user asks for "latest AI news", search for "AI news 2026", NOT "AI news 2025"
|
|
1
|
+
- Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs
|
|
2
|
+
- Provides up-to-date information for current events and recent data
|
|
3
|
+
- Supports configurable result counts and returns the content from the most relevant websites
|
|
4
|
+
- Use this tool for accessing information beyond knowledge cutoff
|
|
5
|
+
- Searches are performed automatically within a single API call
|
|
6
|
+
|
|
7
|
+
Usage notes:
|
|
8
|
+
- Supports live crawling modes: 'fallback' (backup if cached unavailable) or 'preferred' (prioritize live crawling)
|
|
9
|
+
- Search types: 'auto' (balanced), 'fast' (quick results), 'deep' (comprehensive search)
|
|
10
|
+
- Configurable context length for optimal LLM integration
|
|
11
|
+
- Domain filtering and advanced search options available
|
|
12
|
+
|
|
13
|
+
The current year is {{year}}. You MUST use this year when searching for recent information or current events
|
|
14
|
+
- Example: If the current year is 2026 and the user asks for "latest AI news", search for "AI news 2026", NOT "AI news 2025"
|
|
@@ -1,8 +1,8 @@
|
|
|
1
|
-
Writes a file to the local filesystem.
|
|
2
|
-
|
|
3
|
-
Usage:
|
|
4
|
-
- This tool will overwrite the existing file if there is one at the provided path.
|
|
5
|
-
- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.
|
|
6
|
-
- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.
|
|
7
|
-
- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.
|
|
8
|
-
- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.
|
|
1
|
+
Writes a file to the local filesystem.
|
|
2
|
+
|
|
3
|
+
Usage:
|
|
4
|
+
- This tool will overwrite the existing file if there is one at the provided path.
|
|
5
|
+
- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.
|
|
6
|
+
- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.
|
|
7
|
+
- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.
|
|
8
|
+
- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.
|