feat: add ChatGPT Subscription provider (#2876)

* feat: Add ChatGPT Subscription support and related features

- Introduced a new provider option for ChatGPT Subscription in the endpoint selection UI.
- Implemented OAuth flow for ChatGPT Subscription sign-in, including polling for authorization status.
- Updated admin interface to handle ChatGPT Subscription, including disabling API key input and providing user guidance.
- Enhanced cost tracking logic to differentiate between subscription and non-subscription endpoints.
- Added new slash commands for managing skills, including listing, searching, and invoking skills.
- Implemented caching for skill catalog to optimize performance.
- Updated tests to cover new ChatGPT Subscription functionality and ensure proper endpoint probing.
- Refactored existing code to accommodate new features and improve maintainability.

* refactor: share provider device-flow setup

- reuse one device-flow backend for Copilot and ChatGPT Subscription
- add one frontend device-flow helper for Settings and /setup
- put GitHub Copilot back into Add Models, now as a dropdown option
- make provider selection just select; clicking Add starts sign-in
- stop ChatGPT Subscription setup from opening auth tabs automatically
- make /setup copilot and /setup chatgpt-subscription work from chat
- show ChatGPT Subscription in the /setup suggestions
- show the real error message when setup fails
- add focused tests for the shared flow and setup UI

* feat(chatgpt-subscription): harden credential lifecycle and streamline auth UX

Backend:
- Resolve runtime bearer for provider-auth endpoints at probe time via a
  shared _resolve_probe_key() that delegates to resolve_endpoint_runtime,
  applied across all probe/refresh call sites.
- Skip live completion probes and health pings for discovery-only providers
  (centralized behind _is_discovery_only_provider) — the Codex/Responses API
  has no such endpoints, so status is derived from cached models.
- Never persist the short lived ChatGPT bearer to the plaintext sessions
  table; proactively clear any stale bearer left by an earlier code path.
- Revoke orphaned ProviderAuthSession credentials when the last endpoint
  backing them is deleted (_delete_orphaned_provider_auth), surfaced via
  cleared_provider_auth in the delete response.

Frontend (admin.js):
- Auto-start the device-auth flow on provider selection so the authorization
  panel (code + Authorize) shows immediately instead of behind a "Sign in" click.
- Remove the redundant top button for device auth providers, move retry
  into the panel via an inline "Try again".
- Drop the self-evident hint text and add an execCommand clipboard fallback so
  Copy works in non-secure (HTTP/LAN) contexts.

* fix: harden chatgpt subscription provider

* chore: remove PR media from branch

* Fix chatgpt subscription recovery and token handling

---------

Co-authored-by: 5p00kyy <admin@5p00ky.dev>
This commit is contained in:
stocky789
2026-06-08 18:19:18 +10:00
committed by GitHub
parent ac94885c84
commit 1e0d9b92af
37 changed files with 3425 additions and 485 deletions
+70
View File
@@ -1109,6 +1109,35 @@ def setup_skills_routes(skills_manager: SkillsManager) -> APIRouter:
idx = skills_manager.index_for(owner=user)
return {"index": idx, "count": len(idx)}
@router.get("/slash-catalog")
async def get_slash_catalog(request: Request):
"""Return skills that are available as slash commands.
Mirrors the agent prompt's published-skill index so the UI never offers
a slash command the model would not normally be allowed to discover.
"""
user = _owner(request)
all_skills = {s.get("name"): s for s in skills_manager.load(owner=user)}
entries = []
for s in skills_manager.index_for(owner=user):
name = (s.get("name") or "").strip()
if not name:
continue
full = all_skills.get(name) or {}
category = (s.get("category") or full.get("category") or "general").strip() or "general"
entries.append({
"type": "skill",
"token": f"/{name}",
"name": name,
"category": f"Skills / {category}",
"help": s.get("description") or full.get("description") or "",
"usage": f"/{name} <request>",
"uses": int(full.get("uses") or 0),
"last_used": full.get("last_used"),
})
entries.sort(key=lambda row: row["name"])
return {"skills": entries, "count": len(entries)}
@router.get("/builtin")
async def list_builtin_skills(request: Request):
"""Read-only list of the agent's built-in tool capabilities (research,
@@ -1272,6 +1301,47 @@ def setup_skills_routes(skills_manager: SkillsManager) -> APIRouter:
_fire_skill_added(user)
return {"ok": True, "deduped": bool(entry.get("_deduped")), "skill": entry}
@router.post("/{skill_id}/invoke")
async def invoke_skill(request: Request, skill_id: str):
"""Build a skill-pinned prompt for slash-command invocation.
This is intentionally server-side so availability, ownership, and usage
accounting use the same rules as the SkillsManager.
"""
user = _owner(request)
try:
body = await request.json()
except Exception:
body = {}
request_text = (body.get("request") or "").strip() if isinstance(body, dict) else ""
invokable = {
s.get("name"): s for s in skills_manager.index_for(owner=user)
if (s.get("name") or "").strip()
}
match = invokable.get(skill_id)
if not match:
raise HTTPException(404, "Skill is not available for slash invocation")
name = match.get("name")
md = skills_manager.read_skill_md(name, owner=user)
if md is None:
raise HTTPException(404, "Skill source unavailable")
skills_manager.record_use(name, owner=user)
message = (
"Apply the skill below to my request, following its Procedure / Pitfalls / Verification.\n\n"
f"--- BEGIN SKILL ---\n{md}\n--- END SKILL ---\n\n"
+ (f"Request: {request_text}" if request_text else "Request: (use the skill as appropriate)")
)
return {
"ok": True,
"type": "skill",
"name": name,
"command": f"/{name}",
"message": message,
}
@router.get("/{skill_id}")
async def get_skill(request: Request, skill_id: str):
user = _owner(request)