From f9b5c9372d72e4d9c6f924f21bd0518047b07faf Mon Sep 17 00:00:00 2001
From: Ed_ <edwardgz@gmail.com>
Date: Thu, 11 Jun 2026 02:02:56 -0400
Subject: [PATCH] feat(grok,llama): add to PROVIDERS; add 11 pricing entries (3
 Grok + 8 Llama)

Side concerns for Phase 3:

1. PROVIDERS: src/models.py:56 now includes 'grok' and 'llama' alongside
   the 6 existing vendors. Centralized registry; gui_2.py and
   app_controller.py import from here. State tasks t3.5 and t3.16
   were scoped to gui_2.py/app_controller.py but the actual change
   is at the centralized registry, per the project's single-source-of-
   truth pattern (per src/models.py module docstring and the Phase 5
   audit script audit_no_models_config_io.py which enforces that
   PROVIDERS lives in models.py).

2. cost_tracker.py: added 11 regex pricing entries (3 Grok + 8 Llama):

   Grok (per xAI public pricing):
   - grok-2: 2.00 / 10.00
   - grok-2-vision: 2.00 / 10.00
   - grok-beta: 5.00 / 15.00

   Llama (per Grok's consultation: pricing varies by backend; registry
   entries represent the most common case):
   - llama-3.1-8b-instant: 0.05 / 0.08 (Groq)
   - llama-3.1-70b-versatile: 0.59 / 0.79 (Groq)
   - llama-3.1-405b-reasoning: 3.00 / 3.00 (OpenRouter avg)
   - llama-3.2-1b-preview: 0.04 / 0.04
   - llama-3.2-3b-preview: 0.06 / 0.06
   - llama-3.2-11b-vision-preview: 0.18 / 0.18
   - llama-3.2-90b-vision-preview: 0.90 / 0.90
   - llama-3.3-70b-specdec: 0.59 / 0.79 (Groq)

   (all per 1M tokens, USD; matches the structure of existing entries;
   note: 'llama-3.1', 'llama-3.2', 'llama-3.3' are regex patterns to
   allow future model variants in the same family.)

   Spot check:
   - estimate_cost('grok-2', 1000, 500) = 0.007 (= 0.002 + 0.005)
   - estimate_cost('llama-3.3-70b-specdec', 1000, 500) = 0.000985

3. SKIPPED t3.4 and t3.15 (credentials templates): no
   credentials_template.toml exists in the project (Phase 2 established
   this). The user maintains their own credentials.toml directly.

4. t3.6 and t3.17 (Grok/Llama models in capability registry) were
   completed in Phase 1's initial population of 22 entries
   (commit 6be04bc). Grok has 4 entries (1 wildcard + 3 models);
   Llama has 9 entries (1 wildcard + 8 models). Grok-2-vision has
   vision=True; Llama 3.2-11b/90b vision variants have vision=True.

Verification: 38/38 tests pass in batch.
---
 src/cost_tracker.py | 11 +++++++++++
 src/models.py       |  2 +-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/src/cost_tracker.py b/src/cost_tracker.py
index 3b59720b..5016f7be 100644
--- a/src/cost_tracker.py
+++ b/src/cost_tracker.py
@@ -50,6 +50,17 @@ MODEL_PRICING = [
  (r"qwen-vl-plus", {"input_per_mtok": 0.21, "output_per_mtok": 0.63}),
  (r"qwen-vl-max", {"input_per_mtok": 0.50, "output_per_mtok": 1.50}),
  (r"qwen-audio", {"input_per_mtok": 0.10, "output_per_mtok": 0.30}),
+ (r"grok-2", {"input_per_mtok": 2.00, "output_per_mtok": 10.00}),
+ (r"grok-2-vision", {"input_per_mtok": 2.00, "output_per_mtok": 10.00}),
+ (r"grok-beta", {"input_per_mtok": 5.00, "output_per_mtok": 15.00}),
+ (r"llama-3\.1-8b-instant", {"input_per_mtok": 0.05, "output_per_mtok": 0.08}),
+ (r"llama-3\.1-70b-versatile", {"input_per_mtok": 0.59, "output_per_mtok": 0.79}),
+ (r"llama-3\.1-405b-reasoning", {"input_per_mtok": 3.00, "output_per_mtok": 3.00}),
+ (r"llama-3\.2-1b-preview", {"input_per_mtok": 0.04, "output_per_mtok": 0.04}),
+ (r"llama-3\.2-3b-preview", {"input_per_mtok": 0.06, "output_per_mtok": 0.06}),
+ (r"llama-3\.2-11b-vision-preview", {"input_per_mtok": 0.18, "output_per_mtok": 0.18}),
+ (r"llama-3\.2-90b-vision-preview", {"input_per_mtok": 0.90, "output_per_mtok": 0.90}),
+ (r"llama-3\.3-70b-specdec", {"input_per_mtok": 0.59, "output_per_mtok": 0.79}),
 ]
 
 def estimate_cost(model: str, input_tokens: int, output_tokens: int) -> float:
diff --git a/src/models.py b/src/models.py
index 0db0795f..53735156 100644
--- a/src/models.py
+++ b/src/models.py
@@ -53,7 +53,7 @@ from src.paths      import get_config_path
 
 #region: Constants
 
-PROVIDERS: List[str] = ["gemini", "anthropic", "gemini_cli", "deepseek", "minimax", "qwen"]
+PROVIDERS: List[str] = ["gemini", "anthropic", "gemini_cli", "deepseek", "minimax", "qwen", "grok", "llama"]
 
 AGENT_TOOL_NAMES: List[str] = [
  "run_powershell",