chore(deps): bump LocalAGI to 7e0947d

Pick up the LocalAGI PRs merged after f2a2af4:
- per-collection embedding and reranker models, locked per collection
  so one agent's upload or rerank no longer stalls the others (#499)
- required_tool_before_finish: a tool the agent must call successfully
  before it may answer (#495)
- allowed_tools / excluded_tools per agent, applied to MCP tools too
  (#480)

Document the new agent settings. They show up in the single-node agent
form, which reads LocalAGI's config metadata; distributed mode keeps its
own field list and does not offer them yet.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-5-5 [Claude Code]
This commit is contained in:
Ettore Di Giacinto committed 2026-09-27 20:37:03 +00:00
1 parent 250d90aa2e
commit b7155a9d97
3 files changed
+7 -3

No files matched your search

+4
View File
@@ -188,6 +188,10 @@ Each agent has its own configuration that controls its behavior. Key settings in
- **Connectors** - external integrations (Slack, Discord, etc.)
- **Knowledge Base** - collections of documents for RAG
- **MCP Servers** - Model Context Protocol servers for additional tool access
- **Allowed / Excluded Tools** (`allowed_tools`, `excluded_tools`) - limit the tools the agent can see, including MCP tools. The agent always keeps its control actions (`send_message`, `stop`, `update_state`). If a tool is in both lists, it is excluded.
- **Required Tool Before Finish** (`required_tool_before_finish`) - a tool the agent must call successfully before it can give its final answer, for example a validation or policy check. `required_tool_before_finish_prompt` changes the reminder the model gets when it tries to finish early. `required_tool_before_finish_attempts` sets how many reminders it gets before the answer goes through anyway (default 3).
The tool lists and the required-tool settings are available only in single-node mode. The agent form in distributed mode does not show them yet.
The pool-level defaults (API URL, API key, models) can be set via environment variables. Individual agents can further override these in their configuration, allowing them to use different LLM providers (OpenAI, other LocalAI instances, etc.) on a per-agent basis.
+1 -1
View File
@@ -238,7 +238,7 @@ require (
github.com/kevinburke/ssh_config v1.2.0 // indirect
github.com/labstack/gommon v0.4.2 // indirect
github.com/mschoch/smat v0.2.0 // indirect
github.com/mudler/LocalAGI v0.0.0-20260927200938-f2a2af4e982c
github.com/mudler/LocalAGI v0.0.0-20260927202351-7e0947d7ebca
github.com/mudler/localrecall v0.6.5 // indirect
github.com/mudler/skillserver v0.0.7-0.20260520220837-a7317cbf9145
github.com/olekukonko/tablewriter v0.0.5 // indirect
+2 -2
View File
@@ -994,8 +994,8 @@ github.com/mr-tron/base58 v1.3.0 h1:K6Y13R2h+dku0wOqKtecgRnBUBPrZzLZy5aIj8lCcJI=
github.com/mr-tron/base58 v1.3.0/go.mod h1:2BuubE67DCSWwVfx37JWNG8emOC0sHEU4/HpcYgCLX8=
github.com/mschoch/smat v0.2.0 h1:8imxQsjDm8yFEAVBe7azKmKSgzSkZXDuKkSq9374khM=
github.com/mschoch/smat v0.2.0/go.mod h1:kc9mz7DoBKqDyiRL7VZN8KvXQMWeTaVnttLRXOlotKw=
github.com/mudler/LocalAGI v0.0.0-20260927200938-f2a2af4e982c h1:6dvy3mqvRge8Ddji4er30fhoAasQTBJSYwGs1xVVSr8=
github.com/mudler/LocalAGI v0.0.0-20260927200938-f2a2af4e982c/go.mod h1:nk6zt1s5ANgchJYTWGY1jfFPuITSn1gB5oHZ/uFeFDg=
github.com/mudler/LocalAGI v0.0.0-20260927202351-7e0947d7ebca h1:bHlzSuOc5cKvHGF21ZjFFUV7IlkS3wt9YkBsWtkcaC4=
github.com/mudler/LocalAGI v0.0.0-20260927202351-7e0947d7ebca/go.mod h1:nk6zt1s5ANgchJYTWGY1jfFPuITSn1gB5oHZ/uFeFDg=
github.com/mudler/cogito v0.11.1-0.20260721122412-6eece18a6bb6 h1:eYTR8od5HdaHlh9AKCkxkRoHs2/wmx24BF5qrUh2TRY=
github.com/mudler/cogito v0.11.1-0.20260721122412-6eece18a6bb6/go.mod h1:6sfja3lcu2nWRzEc0wwqGNu/eCG3EWgij+8s7xyUeQ4=
github.com/mudler/edgevpn v0.34.0 h1:qDrD/rCPFY/FdURbXudIZWihVKY4VOX3nMn3CcbeQEU=