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:
11 files changed
-55
No files matched your search
@@ -77,11 +77,6 @@ TOOLS AVAILABLE:
|
|||||||
|
|
||||||
You are reliable, adaptable, and genuinely helpful. You are the user's trusted first point of contact in the LibreFang Agent OS — capable of handling most tasks directly and smart enough to delegate when a specialist would do it better."""
|
You are reliable, adaptable, and genuinely helpful. You are the user's trusted first point of contact in the LibreFang Agent OS — capable of handling most tasks directly and smart enough to delegate when a specialist would do it better."""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 300000
|
max_llm_tokens_per_hour = 300000
|
||||||
max_concurrent_tools = 10
|
max_concurrent_tools = 10
|
||||||
|
|||||||
@@ -71,11 +71,6 @@ TOOLS AVAILABLE:
|
|||||||
|
|
||||||
You are patient, empathetic, and solutions-focused. You turn frustrated customers into satisfied advocates."""
|
You are patient, empathetic, and solutions-focused. You turn frustrated customers into satisfied advocates."""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 200000
|
max_llm_tokens_per_hour = 200000
|
||||||
max_concurrent_tools = 5
|
max_concurrent_tools = 5
|
||||||
|
|||||||
@@ -43,11 +43,6 @@ When designing pipelines:
|
|||||||
4. Blue-green or canary deployments
|
4. Blue-green or canary deployments
|
||||||
5. Automated rollback on failure"""
|
5. Automated rollback on failure"""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 150000
|
max_llm_tokens_per_hour = 150000
|
||||||
|
|
||||||
|
|||||||
@@ -42,11 +42,6 @@ Style guide:
|
|||||||
- Code examples for every non-trivial concept
|
- Code examples for every non-trivial concept
|
||||||
- Consistent formatting and structure"""
|
- Consistent formatting and structure"""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 200000
|
max_llm_tokens_per_hour = 200000
|
||||||
|
|
||||||
|
|||||||
@@ -63,11 +63,6 @@ TOOLS AVAILABLE:
|
|||||||
|
|
||||||
You are thorough, discreet, and efficient. You treat every email as an opportunity to communicate clearly and build professional relationships."""
|
You are thorough, discreet, and efficient. You treat every email as an opportunity to communicate clearly and build professional relationships."""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 150000
|
max_llm_tokens_per_hour = 150000
|
||||||
max_concurrent_tools = 5
|
max_concurrent_tools = 5
|
||||||
|
|||||||
@@ -66,11 +66,6 @@ TOOLS AVAILABLE:
|
|||||||
|
|
||||||
You are organized, detail-oriented, and relentlessly focused on accountability. You turn chaotic meetings into clear outcomes."""
|
You are organized, detail-oriented, and relentlessly focused on accountability. You turn chaotic meetings into clear outcomes."""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 150000
|
max_llm_tokens_per_hour = 150000
|
||||||
max_concurrent_tools = 5
|
max_concurrent_tools = 5
|
||||||
|
|||||||
@@ -46,11 +46,6 @@ Output format:
|
|||||||
### Milestones & Timeline
|
### Milestones & Timeline
|
||||||
### Open Questions"""
|
### Open Questions"""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 200000
|
max_llm_tokens_per_hour = 200000
|
||||||
|
|
||||||
|
|||||||
@@ -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."""
|
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]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 150000
|
max_llm_tokens_per_hour = 150000
|
||||||
max_concurrent_tools = 5
|
max_concurrent_tools = 5
|
||||||
|
|||||||
@@ -57,11 +57,6 @@ TOOLS AVAILABLE:
|
|||||||
|
|
||||||
You are strategic, persuasive, and detail-oriented. You help sales teams work smarter and close more deals."""
|
You are strategic, persuasive, and detail-oriented. You help sales teams work smarter and close more deals."""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 150000
|
max_llm_tokens_per_hour = 150000
|
||||||
max_concurrent_tools = 5
|
max_concurrent_tools = 5
|
||||||
|
|||||||
@@ -66,11 +66,6 @@ TOOLS AVAILABLE:
|
|||||||
|
|
||||||
You are creative, culturally aware, and strategically minded. You balance creativity with data-driven decision-making."""
|
You are creative, culturally aware, and strategically minded. You balance creativity with data-driven decision-making."""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 120000
|
max_llm_tokens_per_hour = 120000
|
||||||
max_concurrent_tools = 5
|
max_concurrent_tools = 5
|
||||||
|
|||||||
@@ -39,11 +39,6 @@ OUTPUT:
|
|||||||
- For short content (emails, messages, summaries), respond directly.
|
- For short content (emails, messages, summaries), respond directly.
|
||||||
- Adapt formatting to the target platform when specified."""
|
- Adapt formatting to the target platform when specified."""
|
||||||
|
|
||||||
[[fallback_models]]
|
|
||||||
provider = "default"
|
|
||||||
model = "gemini-2.0-flash"
|
|
||||||
api_key_env = "GEMINI_API_KEY"
|
|
||||||
|
|
||||||
[resources]
|
[resources]
|
||||||
max_llm_tokens_per_hour = 100000
|
max_llm_tokens_per_hour = 100000
|
||||||
|
|
||||||
|
|||||||
Reference in new issue
Block a user