docs(triage): #85 Claude subscription backend — SKIP (ToS-prohibited) - #147
Merged
Conversation
Anthropic's compliance docs (updated 2026-02-19/20) state that using OAuth tokens from Free/Pro/Max accounts in any other product, tool, or service — including the Agent SDK — violates the Consumer Terms of Service; subscription OAuth is exclusive to Claude Code and claude.ai. It is enforced at the wire: since 2026-01-09 subscription OAuth tokens are rejected outside the official CLI, and subscriptions stopped covering third-party tools on 2026-04-04. NousResearch#85's design (a FastAPI OpenAI-compatible shim over claude-agent-sdk, re-exposing the subscription as a provider:custom + base_url endpoint) is exactly the prohibited pattern, so it is neither permitted nor technically viable. The sanctioned path is already present: the closed-loop agent backend drives the real `claude -p` CLI with CLAUDE_CODE_OAUTH_TOKEN; Claude inference for the GEPA roles stays on API-key billing via resolve_default_lm. Doc-only: review-log entry + row flipped to SKIP + already-covered note + snapshot in docs/upstream_pr_triage.md. No code change.
jramos
enabled auto-merge (squash)
June 29, 2026 03:43
jramos
added a commit
that referenced
this pull request
Jul 6, 2026
…ne new item (#150) Incremental upstream review. Backlog steady at 72 open; six new PRs #142-#147. Five already covered -> SKIP; one genuinely-new latent bug -> new action item. - NousResearch#142: 5 of 6 fixes are covered clusters (GEPA/DSPy-3.2 compat x3, validate-full). The 6th is real and new here: find_skill via Path.rglob('SKILL.md') skips symlinked skill dirs on Python <3.13 (skill_sources.py:63/67/80). Promoted to a CHERRY-PICK action item (recommended). - #143: our #102 — state.db read-only importer already shipped; only cross-platform discovery extras. SKIP. - #144/#145: Sunwo0u HSE sanitized evidence packets, report-only, no mechanism. SKIP. - #146: extraction cluster — our skill_text is a @Property over signature.instructions, so its 'dead input field' premise is upstream-only. SKIP. - #147: compat + material_diff reporting subsumed by our behavioral deploy gate. SKIP. Review-log entry + new action-item row + 2026-07-06 snapshot delta.
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
1 participant
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.
What
Resolves the triage action item for upstream NousResearch#85 ("Claude Code subscription backend — FastAPI OpenAI-compatible shim over
claude-agent-sdk"). Disposition flips from INVESTIGATE to SKIP (ToS-prohibited + server-side-blocked). No code change.Finding
The open question on the row was "verify
claude-agent-sdksubscription-auth still viable." It isn't — on two counts:provider:custom+base_urlOpenAI-compatible endpoint over the Agent SDK) is exactly the named pattern.The legitimate path is unaffected and already present: the closed-loop agent backend drives the real
claude -pCLI withCLAUDE_CODE_OAUTH_TOKEN(the sanctioned scripts/CI use of the official product, not a re-exposing shim). What #85 specifically wanted — cheap subscription inference for the GEPA optimizer/judge LM roles — is the prohibited part; Claude inference for evolution stays on API-key billing viaresolve_default_lm.Changes (doc-only)
docs/upstream_pr_triage.md— review-log entry, row Refactor prompt-section backends into a PromptBackend strategy (no behavior change) #85 flipped to SKIP ✅, updated the "Model providers" already-covered note (was "only Refactor prompt-section backends into a PromptBackend strategy (no behavior change) #85 is genuinely new"), and snapshot line.Sources