pi-cliproxyapi-provider 0.4.12 → 0.4.14

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -70,7 +70,7 @@ CLIPROXYAPI_AUTH_HEADER
70
70
  CLIPROXYAPI_MODELS_DEV_ENABLED
71
71
  ```
72
72
 
73
- Project config only supports metadata aliases. Connection and auth settings such as `baseUrl`, `providerName`, `authRequired`, `authHeader`, and `headers` must be set in global config or environment variables.
73
+ Project config supports metadata aliases and bounded per-model overrides. Connection and auth settings such as `baseUrl`, `providerName`, `authRequired`, `authHeader`, and `headers` must be set in global config or environment variables.
74
74
 
75
75
  ### GPT-5.6 context window
76
76
 
@@ -91,7 +91,22 @@ The same setting can be placed in project `.pi/settings.json`; project settings
91
91
  - `"canonical"` (default): advertise `272000` tokens and compact at Pi's conservative boundary.
92
92
  - `"full"`: advertise the models.dev context limit, allowing Pi to retain substantially more history before compaction.
93
93
 
94
- Use `"full"` only when the selected CLIProxyAPI route and upstream account actually support that limit. Requests above `272000` input tokens also use the higher models.dev context-pricing tier where one is defined. Run `/reload` after changing the setting so Pi rebuilds the provider model catalog.
94
+ Use `"full"` only when the selected CLIProxyAPI route and upstream account actually support that limit. Requests above `272000` input tokens also use the higher models.dev context-pricing tier where one is defined.
95
+
96
+ ### Model and display configuration
97
+
98
+ Run `/cliproxyapi config` in Pi TUI mode to edit every package-level `settings.json` value. The tabbed panel has `Connection`, `Models`, and `Display` sections; it controls the GPT-5.6 context-window mode and whether the model selector shows the published strict tool-schema capability.
99
+
100
+ ```json
101
+ {
102
+ "pi-cliproxyapi-provider": {
103
+ "gpt56ContextWindow": "canonical",
104
+ "showStrictMode": false
105
+ }
106
+ }
107
+ ```
108
+
109
+ `showStrictMode` defaults to `false` because the selector stays compact for normal use. Enable it when diagnosing tool-schema behavior; model details always show `Strict tool schema` explicitly. Saving through `/cliproxyapi config` reloads Pi. Select `Connection` to open the endpoint and authentication editor.
95
110
 
96
111
  ## Authenticate
97
112
 
@@ -122,6 +137,9 @@ export CLIPROXYAPI_API_KEY=your-key
122
137
  /cliproxyapi refresh models # refresh CLIProxyAPI availability only
123
138
  /cliproxyapi refresh metadata # refresh models.dev metadata only
124
139
  /cliproxyapi aliases # show unmatched model IDs for metadata aliases
140
+ /cliproxyapi models # inspect effective model settings and set bounded overrides
141
+ /cliproxyapi config # tabbed connection, model, and display configuration
142
+ /cliproxyapi config connection # open endpoint and authentication editor
125
143
  ```
126
144
 
127
145
  ## Metadata aliases
@@ -142,17 +160,33 @@ Add project aliases manually to:
142
160
  .pi/pi-cliproxyapi-provider/config.json
143
161
  ```
144
162
 
145
- Project config only reads `modelAliases`; other fields are ignored.
163
+ Project config reads `modelAliases` and `modelOverrides`; other fields are ignored.
146
164
 
147
165
  ```json
148
166
  {
149
167
  "modelAliases": {
150
168
  "claude-opus-4-6-thinking": "anthropic/claude-opus-4-6",
151
169
  "gpt-5.6-sol": "openai/gpt-5.6-sol"
170
+ },
171
+ "modelOverrides": {
172
+ "gpt-5.6-sol": {
173
+ "contextWindow": 512000,
174
+ "maxTokens": 32768
175
+ }
152
176
  }
153
177
  }
154
178
  ```
155
179
 
180
+ ## Model inspector and overrides
181
+
182
+ Run `/cliproxyapi models` in Pi TUI mode to inspect the models in the current CPA snapshot. The selector shows the effective API, reasoning mode, and context window. The detail view also shows input modalities, cost, thinking levels, and the compatibility values that Pi will publish.
183
+
184
+ Only `reasoning`, `contextWindow`, and `maxTokens` are editable. Values are constrained to safe presets; choose `auto` to remove an override and restore the derived value after reload. API routing and compatibility stay provider-owned: GPT-5.6/Codex models remain on `openai-responses`, while the CLIProxyAPI workaround publishes `supportsStrictMode: false`.
185
+
186
+ For CPA Responses requests, the extension also applies the Codex-compatible function-tool wire contract used by `pi-codex-conversion`: each function tool explicitly carries `strict: null`. This preserves optional tool arguments such as `interactive_shell.listBackground` without replacing CPA authentication, transport, discovery, or streaming with the ChatGPT-backed `openai-codex-responses` provider.
187
+
188
+ Saving writes to an existing project config when present, otherwise to the global provider config, then reloads Pi. Project overrides take precedence over global overrides field by field.
189
+
156
190
  ## Snapshots and startup
157
191
 
158
192
  ```text