mirror/QodeAssist
1
0
Fork 0
mirror of https://github.com/Palm1r/QodeAssist.git synced 2026-06-30 01:59:11 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add more agents configs

Browse Source
This commit is contained in:
Petr Mironychev
2026-06-29 10:05:16 +02:00
parent 747dfb540e
commit 70c6d30a72
31 changed files with 287 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/creating-agents.md
View File

@@ -143,18 +143,18 @@ needs:
|---|---|
| `Claude Base Chat` | Claude, Anthropic Messages (`/v1/messages`) |
| `OpenAI Base Chat` | OpenAI, Chat Completions (`/chat/completions`) |
| `OpenAI Responses Base` | OpenAI, Responses API (`/responses`) |
| `OpenAI Base Responses` | OpenAI, Responses API (`/responses`) |
| `Google Base Chat` | Google AI, Gemini `generateContent` |
| `Ollama Base Chat` | Ollama, native `/api/chat` |
| `Ollama FIM Base` | Ollama, native `/api/generate` fill-in-the-middle |
| `Ollama Base FIM` | Ollama, native `/api/generate` fill-in-the-middle |
For any OpenAI-compatible provider (Mistral, OpenRouter, LM Studio, llama.cpp,
DeepSeek, …) extend `OpenAI Base Chat` and override `provider_instance`.
Each bundled concrete agent (`Claude Sonnet Chat`, `Claude Code Completion`,
`OpenAI Chat Completions`, `OpenAI Responses Chat`, `Google Chat`,
`Ollama Chat`, `Ollama FIM`) is itself a thin delta over one of these bases and
works as a parent too — `extends = "Claude Sonnet Chat"` inherits everything including
Each bundled concrete agent (`Claude Chat — Sonnet`, `Claude Completion`,
`OpenAI Chat`, `OpenAI Chat — Responses`, `Google Chat`,
`Ollama Chat — Simple`, `Ollama Completion — FIM`) is itself a thin delta over one of these bases and
works as a parent too — `extends = "Claude Chat — Sonnet"` inherits everything including
the model.
## `[body]` — the request, literally

25
docs/ollama-configuration.md
View File

@@ -28,6 +28,31 @@ ollama run qwen2.5-coder:32b
You're all set! QodeAssist is now ready to use in Qt Creator.
## Which models do I actually need?
You do **not** need a separate model for every agent. Each bundled Ollama agent
names a *default* model only as an example — you can point any agent at a model
you already have via its settings → **Change…** (a per-agent override; it does not
edit the bundled agent). **Seeing a model name on an agent is not a reason to
download it.**
The defaults cluster into a tiny set, so one or two pulls cover everyday use:
| Pull this | Unlocks |
|---|---|
| `qwen2.5-coder:7b` | Ollama Chat — Simple · Ollama Completion — FIM · Ollama Completion — Chat-style · Ollama Quick Refactor |
| `qwen3.5:9b` (or `:4b` on ~8 GB) | Ollama Chat — Thinking · Ollama Compression — 16/32 GB (`:4b` → Compression — 8 GB) |
Optional specialists — pull only if you want that capability:
| Pull this | For |
|---|---|
| `gemma4:12b` | Ollama Chat — Gemma 4 — agentic chat with vision + native reasoning |
| `theqtcompany/codellama-7b-qml` | Ollama Completion — QML (Qt) — Qt's QML-specific completion model |
Rule of thumb: pick the agent for the job, then either pull its named model **or**
swap it (Change…) for one you already have.
## Extended Thinking Mode
Ollama supports extended thinking mode for models that are capable of deep reasoning (such as DeepSeek-R1, QwQ, and similar reasoning models). This mode allows the model to show its step-by-step reasoning process before providing the final answer.