Skip to content

Target effective-token terminology updates to AI credits in instruction docs#37432

Merged
pelikhan merged 5 commits into
mainfrom
copilot/update-instruction-files-ai-credits
Jun 6, 2026
Merged

Target effective-token terminology updates to AI credits in instruction docs#37432
pelikhan merged 5 commits into
mainfrom
copilot/update-instruction-files-ai-credits

Conversation

Copilot AI commented Jun 6, 2026

Copy link
Copy Markdown
Contributor

This updates instruction documentation to replace effective token(s) terminology with AI credits where applicable, while keeping general token wording unchanged.

  • Terminology migration (targeted)

    • Replaced only effective-token references with AI-credit terminology in:
      • .github/aw/experiments.md
      • .github/aw/syntax-agentic.md
      • .github/aw/token-optimization.md
    • Preserved general token terms (for example, token, token-usage, and token field names) where they are still the correct wording.
  • Guardrail wording alignment

    • Updated effective-token guardrail wording to AI-credit guardrail wording in optimization guidance for max-ai-credits / max-daily-ai-credits descriptions.

This is a documentation-only scope adjustment to keep terminology precise and consistent without broad token-term rewrites.

Copilot AI and others added 3 commits June 6, 2026 22:31
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
@pelikhan

pelikhan commented Jun 6, 2026

Copy link
Copy Markdown
Collaborator

@copilot only replace "effective tokens", leave "token" general term alone.

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot AI commented Jun 6, 2026

Copy link
Copy Markdown
Contributor Author

@copilot only replace "effective tokens", leave "token" general term alone.

Addressed in 4db368e.

I reverted the broad token-term rewrites and kept only targeted replacements for "effective token(s)" references.

Copilot AI changed the title Standardize instruction docs on AI credits and retire token-cost wording Target effective-token terminology updates to AI credits in instruction docs Jun 6, 2026

@pelikhan pelikhan left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@copilot typical range 100 to 2500

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot AI commented Jun 6, 2026

Copy link
Copy Markdown
Contributor Author

@copilot typical range 100 to 2500

Addressed in 308a9cc.

@pelikhan pelikhan marked this pull request as ready for review June 6, 2026 23:30
Copilot AI review requested due to automatic review settings June 6, 2026 23:30
@pelikhan pelikhan merged commit 15bc7e9 into main Jun 6, 2026
@pelikhan pelikhan deleted the copilot/update-instruction-files-ai-credits branch June 6, 2026 23:30

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR updates internal instruction documentation to replace “effective token(s)” terminology with “AI credits” in targeted places, aiming to keep cost/budget guidance consistent with current naming while leaving raw “token” terminology intact.

Changes:

  • Updated audit/comparison guidance to refer to AI credits in run diffs.
  • Updated experiment metric examples to reference AI credit counts.
  • Renamed and rewrote the guardrail section header/content to AI-credit terminology (with additional guidance text).
Show a summary per file
File Description
.github/aw/token-optimization.md Rewords audit/diff and guardrail sections to use AI-credit terminology and updates guidance text.
.github/aw/syntax-agentic.md Updates the inline description for token-weights to refer to AI credit computation.
.github/aw/experiments.md Updates example “Typical metrics” wording from effective tokens to AI credits.

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

  • Files reviewed: 3/3 changed files
  • Comments generated: 3

```

The diff highlights changes in effective tokens, tool calls, and safe outputs between runs. Equivalent via MCP: `audit` tool with `run_ids_or_urls: ["<base-run-id>", "<optimized-run-id>"]`.
The diff highlights changes in AI credits, tool calls, and safe outputs between runs. Equivalent via MCP: `audit` tool with `run_ids_or_urls: ["<base-run-id>", "<optimized-run-id>"]`.
## Technique 9 — Cap Spend with AI-Credit Guardrails

Two top-level frontmatter fields enforce ET budgets directly, independent of the techniques above. Both accept an integer or a `K`/`M` short-form string (e.g. `100M`, `500K`).
Two top-level frontmatter fields enforce ET budgets directly, independent of the techniques above. Both accept an integer or a `K`/`M` short-form string (e.g. `100M`, `500K`). Typical workflow range: `100` to `2500`.

- **`max-ai-credits:`** — Per-run ET budget enforced by the AWF firewall/API proxy (default `25000000`). The agent is steered to stay within budget; set a negative value to disable enforcement and steering.
- **`max-daily-ai-credits:`** — Per-user 24-hour guardrail. At activation, gh-aw sums the triggering user's ET across their runs of this workflow over the last 24 hours and blocks execution once the total exceeds the threshold. Enabled by default with a system default threshold; set `-1` to disable, or an explicit value to override the default.
- **`max-ai-credits:`** — Per-run AI credit budget enforced by the AWF firewall/API proxy (default `25000000`). The agent is steered to stay within budget; set a negative value to disable enforcement and steering.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants