diff options
| author | Paul Buetow <pbuetow@mimecast.com> | 2026-01-30 12:16:31 +0200 |
|---|---|---|
| committer | Paul Buetow <pbuetow@mimecast.com> | 2026-01-30 12:16:31 +0200 |
| commit | 3f1ab18cbc996c9467dae6d8deb2c26798aff30e (patch) | |
| tree | c1a6cdaad61a37bbdd70ddbe161c05aaf13d09ab /config.toml.example | |
| parent | d3e0edbe16459f07506f70611b639d0a0a7f054e (diff) | |
feat: add completion_wait_all config and fix Anthropic system messages
- Add completion_wait_all config option (default true) to wait for all
backends before returning results, or return first result immediately
- Fix Anthropic API: extract system messages to top-level system field
as required by Messages API (was causing 400 errors)
- Add anthropic case to server.go clientFor() for model overrides
Diffstat (limited to 'config.toml.example')
| -rw-r--r-- | config.toml.example | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/config.toml.example b/config.toml.example index 473e48c..ae8110a 100644 --- a/config.toml.example +++ b/config.toml.example @@ -20,6 +20,7 @@ log_preview_limit = 100 # chars shown in log previews completion_debounce_ms = 800 # idle ms before sending a request completion_throttle_ms = 0 # min ms between requests (0 disables) manual_invoke_min_prefix = 0 # required identifier chars for manual invoke +completion_wait_all = true # wait for all backends (true) or return first (false) [triggers] trigger_characters = [".", ":", "/", "_", " "] @@ -37,7 +38,7 @@ chat_prefixes = ["?", "!", ":", ";"] # single-character items # completion = "gpt-4o-mini" # chat = "gpt-4.1" -# Full array form for multiple entries +# Full array form for multiple entries (completions fan out to all; labels show provider:model). # [[models.completion]] # provider = "openai" # model = "gpt-4o-mini" |