SecretsUsedInArgOrEnv warning (docker#115)

* Start [2025-09-05 11:25:21]

* WIP [2025-09-05 11:26:06]

Don't shout at me

Signed-off-by: Djordje Lukic <djordje.lukic@docker.com>

More complete DMR support (docker#103)

The `dmr` provider now supports:

- Proper context length setup using `max_tokens`
- `temperature`, `top_p`, `frequency_penalty`, `presence_penalty` all
get mapped into the proper runtime flags based on the engine in use (for
now only `llama.cpp` mappings);
- Raw runtime flags to pass to the inference engine in use, via
`provider_opts:runtime_flags`

Configuration example supported with these changes:

```yaml
models:
  root:
    provider: dmr
    model: ai/qwen3:14B-Q6_K
    max_tokens: 32768
    temperature: 0.7
    top_p: 0.95
    frequency_penalty: 0.2
    presence_penalty: 0.1
    provider_opts:
      runtime_flags: |
        --batch-size 1024
        --ubatch-size 512
```

closes docker#71

Signed-off-by: Christopher Petito <chrisjpetito@gmail.com>

include env variables in taskfile

fix bug in cagent new

we were telling the llm to use the v0 models schema instead of v1 (type-> provider)

closes docker#86

Signed-off-by: Christopher Petito <chrisjpetito@gmail.com>

Minimal fix for better input support on windows

Signed-off-by: Christopher Petito <chrisjpetito@gmail.com>

Better wrapping of tool calls

Signed-off-by: David Gageot <david.gageot@docker.com>

Fix file search with patterns

Signed-off-by: David Gageot <david.gageot@docker.com>

Update README.md

More correct price calculation

Signed-off-by: David Gageot <david.gageot@docker.com>