Merge pull request #100 from ndycode/fix/issue-98-model-catalog-docs

Clarify modern model catalog counts and variant presets

Author: ndycode

README.md

@@ -35,6 +35,10 @@ What the installer does:
 - normalizes the plugin entry to `"oc-chatgpt-multi-auth"`
 - clears the cached plugin copy so OpenCode reinstalls the latest package
 
+By default, the installer now writes a full catalog config that includes both:
+- modern base model entries such as `gpt-5.4` for `--variant` workflows
+- explicit preset entries such as `gpt-5.4-high` so the shipped catalog is visible directly in model pickers
+
 ## Example Usage
 
 ```bash
@@ -96,10 +100,10 @@ See [Architecture](docs/development/ARCHITECTURE.md) for implementation details.
 
 Use the quick-start path above for the fastest setup. For full setup, local development installs, legacy OpenCode support, and verification steps, see [Getting Started](docs/getting-started.md).
 
-If you are on OpenCode `v1.0.209` or earlier, use:
+If you prefer the compact variant-only config on OpenCode `v1.0.210+`, use:
 
 ```bash
-npx -y oc-chatgpt-multi-auth@latest --legacy
+npx -y oc-chatgpt-multi-auth@latest --modern
 ```
 
 ## Configuration

config/README.md

@@ -9,6 +9,8 @@ This directory contains the official OpenCode config templates for the ChatGPT C
 | [`opencode-modern.json`](./opencode-modern.json) | **v1.0.210+** | Variant-based config: 9 base models with 34 total presets |
 | [`opencode-legacy.json`](./opencode-legacy.json) | **v1.0.209 and below** | Legacy explicit entries: 34 individual model definitions |
 
+The installer currently uses a merged full-catalog mode by default so users get both the modern base entries and the explicit preset entries without having to hand-edit `opencode.json`.
+
 ## Quick pick
 
 If your OpenCode version is v1.0.210 or newer:

docs/configuration.md

@@ -46,10 +46,11 @@ controls how much thinking the model does.
 | `gpt-5.1-codex-mini` | medium, high |
 | `gpt-5.1` | none, low, medium, high |
 
-the shipped config templates include 7 base model families and 26 shipped presets overall (26 modern variants or 26 legacy explicit entries). add `gpt-5.4-pro` and/or `gpt-5.3-codex-spark` manually only for entitled workspaces.
-for context sizing, shipped templates use:
-- `gpt-5.4`, `gpt-5.4-mini`, and `gpt-5.4-pro`: `context=1000000`, `output=128000`
-- other shipped families: `context=272000`, `output=128000`
+The shipped config templates include 9 base model families and 34 shipped presets overall (34 modern variants or 34 legacy explicit entries). On OpenCode `v1.0.210+`, those 34 presets intentionally appear as 9 base model entries plus `--variant` values. `gpt-5.4-pro` ships in the templates but may still be entitlement-gated at runtime, while `gpt-5.3-codex-spark` remains a manual add-on for entitled workspaces only.
+For context sizing, shipped templates use:
+- `gpt-5.4` and `gpt-5.4-pro`: `context=1050000`, `output=128000`
+- `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5-codex`, `gpt-5.1-codex`, `gpt-5.1-codex-max`, and `gpt-5.1-codex-mini`: `context=400000`, `output=128000`
+- `gpt-5.1`: `context=272000`, `output=128000`
 
 model normalization aliases:
 - legacy `gpt-5`, `gpt-5-mini`, `gpt-5-nano` map to `gpt-5.4` (not to `gpt-5.4-mini`)

docs/development/CONFIG_FLOW.md

@@ -47,7 +47,7 @@ That file controls plugin behavior such as retry policy, beginner safe mode, fal
 
 `scripts/install-opencode-codex-auth.js` performs these steps:
 
-1. Load the selected template (`config/opencode-modern.json` by default, `config/opencode-legacy.json` with `--legacy`).
+1. Load the selected template set (`full` by default, `config/opencode-modern.json` with `--modern`, `config/opencode-legacy.json` with `--legacy`).
 2. Back up an existing `~/.config/opencode/opencode.json`.
 3. Normalize the plugin list so it ends with plain `oc-chatgpt-multi-auth`.
 4. Replace `provider.openai` with the selected shipped template block.
@@ -56,20 +56,32 @@ That file controls plugin behavior such as retry policy, beginner safe mode, fal
 Important detail:
 
 - The installer intentionally writes the plugin entry as `oc-chatgpt-multi-auth`, not `oc-chatgpt-multi-auth@latest`.
+- The default `full` install mode merges the modern base-model template with the explicit legacy preset entries so users can access `--variant` workflows and still see the full shipped preset catalog directly.
 
 ## Shipped Template Structure
 
 ### Modern template
 
-`config/opencode-modern.json` is the default for OpenCode `v1.0.210+`.
+`config/opencode-modern.json` is the compact variant-based template for OpenCode `v1.0.210+`.
 
 It currently ships:
 
-- 7 base model families
-- 26 total variants
-- `gpt-5.4` and `gpt-5.4-mini` at 1,000,000 context / 128,000 output
+- 9 base model families
+- 34 total variants
+- `gpt-5.4` and `gpt-5.4-pro` at 1,050,000 context / 128,000 output
+- `gpt-5.4-mini`, `gpt-5.4-nano`, and Codex families at 400,000 context / 128,000 output
+- `gpt-5.1` at 272,000 context / 128,000 output
 - `store: false` plus `include: ["reasoning.encrypted_content"]`
 
+### Full installer mode
+
+The default installer mode combines:
+
+- the 9 modern base model entries from `config/opencode-modern.json`
+- the 34 explicit preset entries from `config/opencode-legacy.json`
+
+That hybrid install mode is what fixes the "only 9 models" complaint without removing `--variant` support.
+
 Example shape:
 
 ```json
@@ -110,7 +122,7 @@ opencode run "task" --model=openai/gpt-5.4 --variant=high
 
 It currently ships:
 
-- 26 explicit model entries
+- 34 explicit model entries
 - separate model IDs such as `gpt-5.4-high` and `gpt-5.4-mini-xhigh`
 - the same OpenAI provider defaults (`store: false`, `reasoning.encrypted_content`)
 

docs/getting-started.md

@@ -29,7 +29,17 @@ opencode run "Explain this repository" --model=openai/gpt-5.4 --variant=medium
 
 The installer updates `~/.config/opencode/opencode.json`, backs up the previous config, normalizes the plugin entry to `oc-chatgpt-multi-auth`, and clears the cached plugin copy so OpenCode reinstalls the latest package.
 
-If you are on OpenCode `v1.0.209` or earlier, use:
+By default, the installer writes a full catalog config so you get both:
+- modern base model entries such as `gpt-5.4` for `--variant` workflows
+- explicit preset entries such as `gpt-5.4-high` so the full shipped catalog is visible directly in pickers
+
+If you prefer the compact variant-only config on OpenCode `v1.0.210+`, use:
+
+```bash
+npx -y oc-chatgpt-multi-auth@latest --modern
+```
+
+If you explicitly want the older explicit-only layout, use:
 
 ```bash
 npx -y oc-chatgpt-multi-auth@latest --legacy
@@ -101,9 +111,11 @@ The repository ships two supported templates:
 | `v1.0.209` and earlier | [`config/opencode-legacy.json`](../config/opencode-legacy.json) |
 
 The templates include the supported GPT-5/Codex families, required `store: false` handling, and `reasoning.encrypted_content` for multi-turn sessions.
-Current templates expose 7 shipped base model families and 26 shipped presets overall (26 modern variants or 26 legacy explicit entries), including `gpt-5.4-mini`.
+Current templates expose 9 shipped base model families and 34 shipped presets overall (34 modern variants or 34 legacy explicit entries).
+
+On OpenCode `v1.0.210+`, the modern template intentionally shows 9 base model entries because the additional presets are selected through `--variant` instead of separate model keys.
 
-Optional model IDs such as `gpt-5.4-pro` or entitlement-gated Spark variants should be added manually only when your workspace supports them.
+`gpt-5.4-pro` ships in the templates but can still be entitlement-gated by your workspace. Add entitlement-gated Spark variants manually only when your workspace supports them.
 
 ## Verify the Setup