Add per-surface provider overrides and wiring

1 files changed, 23 insertions, 0 deletions

diff --git a/docs/configuration.md b/docs/configuration.md
index 6239a4c..6db7a27 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -21,6 +21,29 @@ Environment overrides
   - `HEXAI_OPENAI_MODEL`, `HEXAI_OPENAI_BASE_URL`, `HEXAI_OPENAI_TEMPERATURE`
   - `HEXAI_COPILOT_MODEL`, `HEXAI_COPILOT_BASE_URL`, `HEXAI_COPILOT_TEMPERATURE`
   - `HEXAI_OLLAMA_MODEL`, `HEXAI_OLLAMA_BASE_URL`, `HEXAI_OLLAMA_TEMPERATURE`
+  - Per-surface overrides: `HEXAI_MODEL_COMPLETION`, `HEXAI_MODEL_CODE_ACTION`, `HEXAI_MODEL_CHAT`, `HEXAI_MODEL_CLI`
+  - Per-surface temperatures: `HEXAI_TEMPERATURE_COMPLETION`, `HEXAI_TEMPERATURE_CODE_ACTION`, `HEXAI_TEMPERATURE_CHAT`, `HEXAI_TEMPERATURE_CLI`
+
+Per-surface models
+
+- Use the `[models]` table in `config.toml` to tailor individual entry points (completion, code actions, chat, CLI) without changing the global provider default.
+- Each key accepts either a string (shortcut) or a table with `model` / `temperature` fields, e.g.:
+
+  ```toml
+  [models]
+  completion = "gpt-4.1-mini"
+
+  [models.code_action]
+  model = "gpt-4o"
+  provider = "copilot"
+  temperature = 0.4
+
+  [models.cli]
+  model = "gpt-4.1"
+  provider = "openai"
+  ```
+
+- When a per-surface value is omitted, Hexai falls back to the provider’s configured default. Temperatures inherit from `coding_temperature` unless explicitly set, and OpenAI `gpt-5*` models automatically raise an unspecified coding temperature to `1.0` for exploratory behavior. Provider overrides support `"openai"`, `"copilot"`, or `"ollama"` and read the matching credential variables.
 
 Runtime reloads