pi-coralbricks-provider 1.0.7 → 1.0.8
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 +4 -4
- package/package.json +3 -2
package/README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# 🪸 pi-coralbricks-provider
|
|
4
4
|
|
|
5
|
-
**GLM 5.
|
|
5
|
+
**GLM 5.3, GLM 5.3 Flash, Kimi K3 & GPT-OSS 120B through [Coral Bricks](https://www.coralbricks.ai)**
|
|
6
6
|
|
|
7
7
|
_A [pi](https://github.com/earendil-works/pi-coding-agent) provider extension for Coral's OpenAI-compatible inference gateway — up to **1M context** on open models._
|
|
8
8
|
|
|
@@ -17,8 +17,8 @@ _A [pi](https://github.com/earendil-works/pi-coding-agent) provider extension fo
|
|
|
17
17
|
|
|
18
18
|
## Features
|
|
19
19
|
|
|
20
|
-
- **4 reasoning models** from Coral's
|
|
21
|
-
- **1M token context** on GLM and Kimi, with vision (image input) on Kimi K3
|
|
20
|
+
- **4 reasoning models** from Coral's live catalog — GLM 5.3 FP4, GLM 5.3 Flash, Kimi K3, and GPT-OSS 120B
|
|
21
|
+
- **1M token context** on GLM and Kimi, with vision (image input) on Kimi K3 and GLM 5.3 Flash
|
|
22
22
|
- **OpenAI-compatible API** — standard `/v1/chat/completions`, streaming, and tool calling
|
|
23
23
|
- **Per-family thinking levels** — zai-style `thinking` control for GLM (including a *real* off switch), `reasoning_effort` for Kimi K3 and GPT-OSS
|
|
24
24
|
- **Accurate cost tracking** — pricing mirrors Coral's published rates, and cached reads are **$0 on every model**, so pi's computed cost matches Coral's own `usage.cost` to the token
|
|
@@ -153,7 +153,7 @@ Coral's gateway follows the OpenAI Chat Completions API:
|
|
|
153
153
|
|
|
154
154
|
### Patch Overrides & Custom Models
|
|
155
155
|
|
|
156
|
-
- **`patch.json`** — per-model overrides applied on top of `models.json` (reasoning flags, pricing corrections, compat settings, thinking level maps). Currently
|
|
156
|
+
- **`patch.json`** — per-model overrides applied on top of `models.json` (reasoning flags, pricing corrections, compat settings, thinking level maps). Currently carries the GLM 5.3 Flash entry: reasoning, image input, its thinking level map and compat settings.
|
|
157
157
|
- **`custom-models.json`** — full model definitions for models Coral doesn't list. Merged after patch.
|
|
158
158
|
|
|
159
159
|
Merge order: `[live|cache|embedded] → patch.json → custom-models.json`
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pi-coralbricks-provider",
|
|
3
|
-
"version": "1.0.
|
|
4
|
-
"description": "CoralBricks provider extension for pi - Access GLM 5.
|
|
3
|
+
"version": "1.0.8",
|
|
4
|
+
"description": "CoralBricks provider extension for pi - Access GLM 5.3, GLM 5.3 Flash, Kimi K3, and GPT-OSS 120B through the Coral Inference API",
|
|
5
5
|
"author": "monotykamary",
|
|
6
6
|
"homepage": "https://github.com/monotykamary/pi-coralbricks-provider#readme",
|
|
7
7
|
"repository": {
|
|
@@ -21,6 +21,7 @@
|
|
|
21
21
|
"update-models": "node scripts/update-models.js"
|
|
22
22
|
},
|
|
23
23
|
"keywords": [
|
|
24
|
+
"pi-package",
|
|
24
25
|
"pi",
|
|
25
26
|
"extension",
|
|
26
27
|
"provider",
|