mirror of
https://github.com/docker/docker-agent.git
synced 2026-11-04 18:30:09 +00:00
- examples/vercel.yaml: correct openai/gpt-4.1 (which moved backward from the pre-sweep openai/gpt-5) to openai/gpt-5.6-sol, matching every other vercel+openai reference touched by this PR (DefaultModels['vercel'], docs/providers/vercel, docs/providers/custom). - examples/custom_provider.yaml: bump the two leftover shorthand model refs (my_gateway/gpt-4o-mini, my_anthropic/claude-sonnet-4-5) that were missed in the same file, and rename gateway_gpt4o -> gateway_gpt so the key no longer encodes a stale model generation. - Rename model keys that encoded a now-stale generation in their own name after only the value was bumped: examples/lifecycle.yaml (openai/gpt-4o-mini -> openai/gpt-5.6-terra, updating the agent reference too), examples/alloy.yaml (gpt-4o -> gpt), examples/rag.yaml (gpt-5-minimal -> gpt-minimal), examples/multi-code.yaml (gpt4o -> gpt), examples/image_text_extractor.yaml (gpt4_vision -> gpt_vision), examples/thinking_budget.yaml (claude-4-5-sonnet-* -> claude-4-6-sonnet-*, claude-opus-4-6-* -> claude-opus-4-8-*, claude-opus-4-7-summarized -> claude-opus-4-8-summarized, including the cross-referencing comment), docs/providers/google/index.md (gemini-3-pro/gemini-3-flash -> gemini-pro/gemini-flash). - Fix minor markdown table column misalignment in docs/providers/baseten and docs/providers/github-copilot introduced by the previous commit. Refs #4137.
46 lines
1.5 KiB
YAML
46 lines
1.5 KiB
YAML
agents:
|
|
root:
|
|
model: openai/gpt-5.6-terra
|
|
description: An example agent that demonstrates per-toolset lifecycle policies.
|
|
instruction: |
|
|
Use the configured tools to answer questions.
|
|
toolsets:
|
|
# 1. Strict profile: marks gopls as critical so a future eager-startup
|
|
# phase will refuse to start the agent if it can't come up. Today
|
|
# the agent still boots without it and surfaces a warning.
|
|
- type: lsp
|
|
command: gopls
|
|
file_types: [".go"]
|
|
lifecycle:
|
|
profile: strict # required=true (informational), no auto-restart
|
|
startup_timeout: 30s # informational; not yet enforced
|
|
|
|
# 2. Resilient profile (the default if 'lifecycle' is omitted).
|
|
# Auto-restart with exponential backoff and a higher restart budget.
|
|
- type: mcp
|
|
ref: docker:context7
|
|
lifecycle:
|
|
profile: resilient
|
|
max_restarts: 10
|
|
backoff:
|
|
initial: 500ms
|
|
max: 1m
|
|
multiplier: 2
|
|
jitter: 0.2
|
|
|
|
# 3. Best-effort profile: single attempt, no restart, optional.
|
|
# Good for experimental MCPs whose flakiness shouldn't amplify into a
|
|
# restart loop.
|
|
- type: mcp
|
|
ref: docker:openbnb-airbnb
|
|
lifecycle:
|
|
profile: best-effort
|
|
|
|
models:
|
|
openai/gpt-5.6-terra:
|
|
provider: openai
|
|
model: gpt-5.6-terra
|
|
|
|
metadata:
|
|
description: Demonstrates per-toolset lifecycle profiles (strict / resilient / best-effort)
|