From 9792eb93131d97221a5125693a01c5339b59688d Mon Sep 17 00:00:00 2001 From: corticalstack Date: Wed, 27 May 2026 14:28:25 +0200 Subject: [PATCH 1/2] fix(05,12): raise o3-deep-research TPM capacity from 10 to 200 The original SKU capacity of 10 (= 10K TPM) throttled multi-step deep-research runs with 429 errors before completion. Raised to 200 (= 200K TPM) in both Bicep files that define the deployment: - 05-foundry-project-pattern-setup/05-02-deploy-foundry-core-gateway/main.bicep - 12-foundry-iq-deep-research/main.bicep The new value stays well under the Norway East o3-DeepResearch subscription quota (limit 3000). Existing live deployments must be updated separately, either by a fresh bicep apply or via: az cognitiveservices account deployment update \ -g rg-foundry-core-{suffix} -n aif-research-{suffix} \ --deployment-name o3-deep-research --sku-capacity 200 --- .../05-02-deploy-foundry-core-gateway/main.bicep | 5 ++++- 12-foundry-iq-deep-research/main.bicep | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/05-foundry-project-pattern-setup/05-02-deploy-foundry-core-gateway/main.bicep b/05-foundry-project-pattern-setup/05-02-deploy-foundry-core-gateway/main.bicep index bd7c372..714d99d 100644 --- a/05-foundry-project-pattern-setup/05-02-deploy-foundry-core-gateway/main.bicep +++ b/05-foundry-project-pattern-setup/05-02-deploy-foundry-core-gateway/main.bicep @@ -120,7 +120,10 @@ resource researchHub 'Microsoft.CognitiveServices/accounts@2025-04-01-preview' = resource researchModel 'Microsoft.CognitiveServices/accounts/deployments@2025-04-01-preview' = { parent: researchHub name: 'o3-deep-research' - sku: { name: 'GlobalStandard', capacity: 10 } + // Capacity is K-TPM. 10 was too low - multi-step deep-research runs hit + // 429 throttling before completing. 200 gives realistic headroom while + // staying well under the Norway East o3-DeepResearch subscription quota. + sku: { name: 'GlobalStandard', capacity: 200 } properties: { model: { name: 'o3-deep-research' diff --git a/12-foundry-iq-deep-research/main.bicep b/12-foundry-iq-deep-research/main.bicep index eb4ae51..7444360 100644 --- a/12-foundry-iq-deep-research/main.bicep +++ b/12-foundry-iq-deep-research/main.bicep @@ -54,7 +54,10 @@ resource researchHub 'Microsoft.CognitiveServices/accounts@2025-04-01-preview' = resource researchModel 'Microsoft.CognitiveServices/accounts/deployments@2025-04-01-preview' = { parent: researchHub name: 'o3-deep-research' - sku: { name: 'GlobalStandard', capacity: 10 } + // Capacity is K-TPM. 10 was too low - multi-step deep-research runs hit + // 429 throttling before completing. 200 gives realistic headroom while + // staying well under the Norway East o3-DeepResearch subscription quota. + sku: { name: 'GlobalStandard', capacity: 200 } properties: { model: { name: 'o3-deep-research' From df62cb33f42b836d720f8afef5acf13cac28cc56 Mon Sep 17 00:00:00 2001 From: corticalstack Date: Wed, 27 May 2026 14:28:25 +0200 Subject: [PATCH 2/2] chore: bump version to 0.8.5 and add release notes --- CHANGELOG.md | 6 ++++++ pyproject.toml | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index de7a854..4a0b115 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## [0.8.5] - 2026-05-27 + +### Fixed + +- Raised the `o3-deep-research` model deployment capacity from 10 (10K TPM) to 200 (200K TPM) in both `05-foundry-project-pattern-setup/05-02-deploy-foundry-core-gateway/main.bicep` and `12-foundry-iq-deep-research/main.bicep`. The original 10K cap throttled multi-step deep-research runs with 429 errors before completion. 200K stays well under the Norway East `o3-DeepResearch` subscription quota (3000). Existing live deployments must be updated separately (`az cognitiveservices account deployment update --sku-capacity 200`) or via a fresh Bicep apply. + ## [0.8.4] - 2026-05-27 ### Fixed diff --git a/pyproject.toml b/pyproject.toml index ad85cc2..03cd9d9 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "awesome-foundry-nextgen" -version = "0.8.4" +version = "0.8.5" description = "Hands-on labs for Microsoft Foundry — Azure's unified PaaS for enterprise AI" requires-python = ">=3.11" dependencies = [