GITHUB COPILOT: GPT-5.1 CODEX PREVIEW, SPACES SHARING, AND MODEL RETIREMENTS
GitHub Copilot added a public preview of GPT-5.1-Codex-Max across web, IDE, mobile, and CLI (Enterprise/Business must enable it), made Spaces shareable publicly...
GitHub Copilot added a public preview of GPT-5.1-Codex-Max across web, IDE, mobile, and CLI (Enterprise/Business must enable it), made Spaces shareable publicly or per-user with a code-viewer add-to-Space flow, and refined the VS model picker. Older OpenAI/Anthropic/Google models were retired with suggested replacements, agents gained mission control and skills with broader IDE coverage, and knowledge bases fully sunset in favor of Spaces.
Model retirements can break pinned workflows or subtly change outputs, so orgs need a migration plan.
Spaces enable reusable, access-controlled context that can improve code-gen relevance for teams.
-
terminal
Benchmark GPT-5.1-Codex-Max vs your current default on representative repo tasks (generation, refactor, test scaffolding).
-
terminal
Validate Spaces grounding by attaching key design/docs from the code viewer and measuring response accuracy on real tickets.
Legacy codebase integration strategies...
- 01.
Migrate old knowledge bases to Spaces and verify permissions mirror repo access; replace any hardcoded KB links in scripts/docs.
- 02.
Audit Copilot model usage and pin recommended replacements before deprecations impact CI bots, code-review helpers, or chat workflows.
Fresh architecture paradigms...
- 01.
Adopt Spaces as the canonical context layer and design agent skills with mission control from day one for repeatable tasks.
- 02.
Standardize model selection via org policy and allow opt-in teams to trial GPT-5.1-Codex-Max behind a feature flag.