Skip to main content

AI Launch Profile

GitHub Copilot AI Agent Session Limits

GitHub added public-preview AI credit session limits to Copilot CLI and the GitHub Copilot SDK on July 1, 2026.

GitHub Copilot AI Credit Session Limits official source image

At a glance

Launch Snapshot

Company
GitHub
Launch date
July 1, 2026
Launch type
Major Update
Category
AI Coding Tools
Audience
Automation Teams, Developers, Engineering Teams, Enterprise Platform Teams
Pricing
GitHub says session limits require Copilot CLI 1.0.66 or later or Copilot SDK 1.0.5 or later and are available in public preview for Individual, Business, and Enterprise plans. The limit is a soft cap because a response already in progress can finish after the threshold is crossed; current plan pricing and AI credit terms remain authoritative.
Free plan
Not publicly confirmed
API
Yes
Open weights/source
No

Verification & Sources

Evidence state
Recheck due
Source links
3
Freshness
Needs recheck: checked July 9, 2026
Last updated
July 9, 2026
What this evidence state means
Definition
The claim was previously checked, but its review window expired or a material change may have invalidated it.
Required provenance
The prior evidence and check date are retained, together with the expiry or change signal that triggered recheck.
Owner
Kingy freshness queue owner and assigned editorial reviewer
Freshness rule
This is already outside its freshness rule. It must not be presented as current until reviewed against current evidence.
Disputes and corrections
Use “Suggest a correction” on the record. Kingy editorial reviews the cited evidence, records material corrections, and changes or removes the state when it is not supported.
Suggest a correction

Form submissions, correction notes, score details, URLs, and analytics events may be stored for editorial review, spam prevention, product improvement, and follow-up. Do not submit secrets, unreleased financials, private customer data, or regulated personal data through these forms.

Kingy Launch Score

7.0 / 10 · Solid

One earned credibility score, computed from cited evidence — not a placeholder. How the Kingy Launch Score works

Why this score

  • Source & verification 8.0/10 — The changelog announcement, dedicated session-limit documentation, and the plans page — dated first-party sources with tool versions specified. github.blog
  • Product evidence 7.0/10 — A public-preview capability shipped in Copilot CLI and the SDK with an API and how-to documentation. docs.github.com
  • Significance & novelty 6.0/10 — Per-session credit boundaries for unattended and long-running agent work — practical governance for autonomous runs. github.blog
  • Traction signals not scored — insufficient sourced evidence
  • Offer clarity 6.5/10 — Available in public preview for Individual, Business, and Enterprise plans, with the soft-cap behavior documented. github.com

Evidence checked 2026-07-10

Kingy AI Take

GitHub added public-preview AI credit session limits to Copilot CLI and the SDK, putting a task-level boundary around model, subagent, and background usage in unattended runs (github.blog). Developers, Automation Teams, and Enterprise Platform Teams running long agent sessions get a documented cost control across Individual, Business, and Enterprise plans. The record notes the limit is a soft cap — an in-flight response can finish past the threshold — so leave headroom in your budgets.

Who it is for

Developers, automation teams, engineering leaders, and enterprise platform teams that need per-session controls for unattended or long-running Copilot agent work.

Editorial submissions and sponsor-fit reviews are separate. Payment does not influence Kingy scores, verdicts, rankings, evidence labels, or publication decisions.