GitHub retired MAI-Code-1-Flash across Copilot the same day it announced the change
GitHub deprecated MAI-Code-1-Flash on September 10, 2026, and the changelog entry carries that same date for both the announcement and the retirement. The model is gone from Copilot Chat, inline edits, ask mode, agent mode, and code completions. GitHub names MAI-Code-1.1-Flash as the suggested alternative and asks teams to update anything that calls the old model by name. On Copilot Enterprise the alternative does not show up until an administrator enables it in the model policies.
Deprecation notices usually come with a countdown. This one does not. The changelog entry for MAI-Code-1-Flash is dated September 10, 2026, and says the model was deprecated across all GitHub Copilot experiences that same day. The header above the entry reads as retired, with the same date beside it.
What the entry actually removes
The table in the entry holds one model, one date, and one alternative: MAI-Code-1-Flash goes, MAI-Code-1.1-Flash takes its place. The removal covers every place where Copilot answers, which GitHub lists as Copilot Chat, inline edits, ask and agent modes, and code completions. There is no surface left where the old name still resolves.
GitHub also says that removing the deprecated model requires no action, so nothing has to be uninstalled or cleaned up. What does need attention is anything that names the model explicitly: a script that passes a model id, a stored Copilot configuration, or an integration written against the old name.
On Enterprise the replacement is a policy decision
For Copilot Enterprise the substitution is not automatic. GitHub writes that administrators may need to enable access to the alternative through their model policies in Copilot settings, and spells out the check: open your individual Copilot settings and confirm that the policy is enabled for that specific model.
Only after that does MAI-Code-1.1-Flash appear in the Copilot Chat model selector, in VS Code and on the GitHub website. Until an administrator does it, a developer inside that organization sees a model that vanished and no replacement in the picker.
- The retirement covers Copilot Chat, inline edits, ask mode, agent mode, and code completions.
- MAI-Code-1.1-Flash is the alternative GitHub names in the entry itself.
- Enterprise access runs through the model policies in Copilot settings.
- GitHub points Enterprise customers with questions to their account manager.
What the entry leaves out
The entry does not describe what happens to a request that still asks for the retired model, so whether it errors, falls back, or gets rerouted is unstated. There is no grace period either, because the deprecation date is the publication date. The entry also skips what changed between the two versions, which is the comparison anyone would want before moving other automation over.
„Please update your workflows and integrations to use a supported model.“
Related
OpenClaw 2026.9.4 can undo a failed update, and its ready cloud workers bill until deleted
OpenClaw published version 2026.9.4 on September 11, 2026. A failed update can now restore the previous package, but only where schema and configuration checks show the rollback is safe, and database migrations still require a verified backup taken before the upgrade. The same release adds prepared cloud workers that keep costing provider money until they are deleted, with a default reserve of one per project or profile and a ceiling of four across the Gateway. Plugins move into a single workspace, and a host can now lock configuration through an environment variable.
OpenClawverified
Claude Code 2.1.268 closes several ways a deny rule failed to apply
The release published on September 10, 2026 is mostly a permissions release. Deny and ask rules did not apply to symlinked directories when a path was spelled by its real location, and a deny rule on a file could be stepped over by putting an unparseable command on the same line. Two separate fixes stop secrets from being printed into plugin and MCP output. The same build also repairs third-party endpoints, which had been failing every turn with HTTP 400 since 2.1.265.
Claude Code Releases (GitHub)verified
OpenAI turns the harness behind Codex into an Agents API
On September 10, 2026, OpenAI opened the Agents API in public beta, giving any developer the harness and infrastructure that already run Codex. One call creates an agent session with its task, model, tools and execution environment, and the compaction, tool search and subagent orchestration come with it. The same day, the GPT-Live-1 voice model reached the API at $0.05 per minute for the voice layer. For anyone building agents, the orchestration layer is now a purchased component rather than a written one.
OpenAIverified

