Target effective-token terminology updates to AI credits in instruction docs#37432
Merged
Conversation
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>
Copilot created this pull request from a session on behalf of
pelikhan
June 6, 2026 22:37
View session
Collaborator
|
@copilot only replace "effective tokens", leave "token" general term alone. |
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Contributor
Author
Addressed in 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
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Contributor
Author
Addressed in |
Contributor
There was a problem hiding this comment.
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. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This updates instruction documentation to replace effective token(s) terminology with AI credits where applicable, while keeping general token wording unchanged.
Terminology migration (targeted)
.github/aw/experiments.md.github/aw/syntax-agentic.md.github/aw/token-optimization.mdtoken,token-usage, and token field names) where they are still the correct wording.Guardrail wording alignment
max-ai-credits/max-daily-ai-creditsdescriptions.This is a documentation-only scope adjustment to keep terminology precise and consistent without broad token-term rewrites.