fix(agents): remove hardcoded 2025 year from search query examples

Researcher agents were using literal "2025" in query template examples,
causing Claude to copy them verbatim instead of using the actual current
year. Changed to [current year] placeholder with explicit instruction to
check today's date.

Fixes #164

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Lex Christopherson
2026-01-19 14:26:58 -06:00
parent 694bd1510e
commit 6ad1d0a318
2 changed files with 9 additions and 9 deletions

View File

@@ -157,11 +157,11 @@ For finding what exists, community patterns, real-world usage.
- "How do people solve Y?"
- "Common mistakes with Z"
**Query templates (use current year):**
**Query templates:**
```
Stack discovery:
- "[technology] best practices 2025"
- "[technology] recommended libraries 2025"
- "[technology] best practices [current year]"
- "[technology] recommended libraries [current year]"
Pattern discovery:
- "how to build [type of thing] with [technology]"
@@ -173,7 +173,7 @@ Problem discovery:
```
**Best practices:**
- Include current year for freshness
- Always include the current year (check today's date) for freshness
- Use multiple query variations
- Cross-verify findings with authoritative sources
- Mark WebSearch-only findings as LOW confidence

View File

@@ -200,12 +200,12 @@ For finding what exists, community patterns, real-world usage.
- "Common mistakes with Z"
- Ecosystem surveys
**Query templates (use current year):**
**Query templates:**
```
Ecosystem discovery:
- "[technology] best practices 2025"
- "[technology] recommended libraries 2025"
- "[technology] vs [alternative] 2025"
- "[technology] best practices [current year]"
- "[technology] recommended libraries [current year]"
- "[technology] vs [alternative] [current year]"
Pattern discovery:
- "how to build [type of thing] with [technology]"
@@ -219,7 +219,7 @@ Problem discovery:
```
**Best practices:**
- Include current year for freshness
- Always include the current year (check today's date) for freshness
- Use multiple query variations
- Cross-verify findings with authoritative sources
- Mark WebSearch-only findings as LOW confidence