chore(agents): drop GEMINI_API_KEY fallback from generic templates (#68)

These 11 templates are the general-purpose ones that don't depend on any
particular model at the primary level (`[model] provider = "default"`).
They also ship a secondary `[[fallback_models]]` block pointing at
`gemini-2.0-flash` with `api_key_env = "GEMINI_API_KEY"`.

That default hurts everyone who doesn't happen to have `$GEMINI_API_KEY`
set — every agent boot logs `WARN Fallback driver 'gemini' failed to
init: Missing API key`, once per turn per agent. The templates that
actually intend to use Gemini as their primary model (analyst, coder,
researcher, code-reviewer, debugger, legal-assistant, data-scientist,
academic-researcher, test-engineer) are left untouched — those
declare Gemini in `[model]`, which is an intentional design choice, not
a hidden fallback.

Users who want a Gemini fallback chain for generic agents can add
`[[fallback_models]]` themselves in `~/.librefang/workspaces/agents/...`
once they've set `$GEMINI_API_KEY`.

Removed from:
  assistant, customer-support, devops-lead, doc-writer, email-assistant,
  meeting-assistant, planner, recruiter, sales-assistant, social-media,
  writer
This commit is contained in:
Evan authored and GitHub committed 2026-04-21 20:10:09 +09:00
1 parent 1ecca29fee
commit 28ea31b073
11 files changed
-55

No files matched your search

-5
View File
@@ -64,11 +64,6 @@ TOOLS AVAILABLE:
You are thorough, fair, and people-oriented. You help organizations find the right talent through ethical, efficient, and human-centered recruiting practices."""
[[fallback_models]]
provider = "default"
model = "gemini-2.0-flash"
api_key_env = "GEMINI_API_KEY"
[resources]
max_llm_tokens_per_hour = 150000
max_concurrent_tools = 5