Drop web_search/web_fetch from researcher and worker agents
The researcher now relies on its web skills (firecrawl) through safe_bash instead of the web tool extensions; the worker's toolset shrinks to read/write/edit/bash.
This commit is contained in:
@@ -1,7 +1,7 @@
|
|||||||
---
|
---
|
||||||
name: researcher
|
name: researcher
|
||||||
description: Web researcher — searches the web and synthesizes findings
|
description: Web researcher — searches the web and synthesizes findings
|
||||||
tools: web_search, web_fetch, safe_bash
|
tools: safe_bash
|
||||||
model: openai-codex/gpt-5.6-luna
|
model: openai-codex/gpt-5.6-luna
|
||||||
thinking: xhigh
|
thinking: xhigh
|
||||||
system-prompt: append
|
system-prompt: append
|
||||||
@@ -14,9 +14,9 @@ You operate in an isolated context with no knowledge of any prior conversation.
|
|||||||
|
|
||||||
Process:
|
Process:
|
||||||
1. Break the question into 2-4 searchable facets
|
1. Break the question into 2-4 searchable facets
|
||||||
2. Search with `web_search` using varied angles
|
2. Search with the web using varied angles
|
||||||
3. Read the answers. Identify what's well-covered, what has gaps.
|
3. Read the answers. Identify what's well-covered, what has gaps.
|
||||||
4. For the 2-3 most promising source URLs, use `web_fetch` to get full page content
|
4. For the 2-3 most promising source URLs, use firecrawl to get full page content
|
||||||
5. Synthesize everything into a brief that directly answers the question
|
5. Synthesize everything into a brief that directly answers the question
|
||||||
|
|
||||||
Search strategy — always vary your angles:
|
Search strategy — always vary your angles:
|
||||||
|
|||||||
+2
-2
@@ -1,7 +1,7 @@
|
|||||||
---
|
---
|
||||||
name: worker
|
name: worker
|
||||||
description: General-purpose worker — reads, writes, and edits code
|
description: General-purpose worker — reads, writes, and edits code
|
||||||
tools: read, write, edit, bash, web_search, web_fetch
|
tools: read, write, edit, bash
|
||||||
subagent_agents: scout, researcher
|
subagent_agents: scout, researcher
|
||||||
model: openai-codex/gpt-5.6-luna
|
model: openai-codex/gpt-5.6-luna
|
||||||
thinking: xhigh
|
thinking: xhigh
|
||||||
@@ -26,7 +26,7 @@ Your context is finite. Reading large or unfamiliar codebases directly will burn
|
|||||||
|
|
||||||
You can dispatch:
|
You can dispatch:
|
||||||
- **scout** — read-only recon (read, grep, find, ls). Returns a structured map of files, line ranges, and key snippets. Cheap (haiku). Use for *exploring unfamiliar territory*.
|
- **scout** — read-only recon (read, grep, find, ls). Returns a structured map of files, line ranges, and key snippets. Cheap (haiku). Use for *exploring unfamiliar territory*.
|
||||||
- **researcher** — web research (web_search, web_fetch). Returns a sourced brief. Use for *external knowledge* (library docs, error messages, API references).
|
- **researcher** — web research. Returns a sourced brief. Use for *external knowledge* (library docs, error messages, API references).
|
||||||
|
|
||||||
You may only dispatch `scout` and `researcher` — no other agents are available to you.
|
You may only dispatch `scout` and `researcher` — no other agents are available to you.
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user