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
+107 -13
View File
@@ -283,6 +283,7 @@ _HOST_TO_CURATED = (
("fireworks.ai", "fireworks"),
("googleapis.com", "google"),
("x.ai", "xai"),
("openrouter.ai", "openrouter"),
("ollama.com", "ollama"),
("opencode.ai/zen/go", "opencode-go"),
@@ -493,6 +494,8 @@ _NON_CHAT_EXACT_PREFIXES = (
def _is_chat_model(model_id: str) -> bool:
"""Return True if the model ID looks like a chat/completions-capable model."""
mid = model_id.lower()
if mid in {"gpt-5.1-codex"}:
return True
for prefix in _NON_CHAT_PREFIXES:
if mid.startswith(prefix):
return False
@@ -505,9 +508,67 @@ def _is_chat_model(model_id: str) -> bool:
return True
def _probe_single_model(base: str, api_key: str, model_id: str, timeout: int = 10, with_tools: bool = False) -> dict:
def _delete_orphaned_provider_auth(db, auth_id: Optional[str], exclude_ep_id: Optional[str] = None) -> bool:
"""Delete a ProviderAuthSession once no endpoint still references it.
Subscription providers (e.g. ChatGPT Subscription) keep their refresh token
in ProviderAuthSession rather than ModelEndpoint.api_key. When the last
endpoint backed by that auth row is removed, the stored credentials should
be cleared instead of lingering. Returns True if a row was deleted.
``exclude_ep_id`` drops the endpoint currently being deleted from the
reference count so it does not keep its own auth alive.
"""
if not auth_id:
return False
from core.database import ProviderAuthSession
still_referenced = db.query(ModelEndpoint.id).filter(
ModelEndpoint.provider_auth_id == auth_id,
ModelEndpoint.id != exclude_ep_id,
).first()
if still_referenced is not None:
return False
auth_row = db.query(ProviderAuthSession).filter(ProviderAuthSession.id == auth_id).first()
if auth_row is None:
return False
db.delete(auth_row)
return True
def _is_discovery_only_provider(provider: str) -> bool:
"""Provider that only supports model discovery, not live probing.
ChatGPT Subscription speaks the Responses/Codex API and has no
chat-completions or general health endpoint, so completion probes and
reachability pings are skipped — status is derived from cached models.
"""
return provider == "chatgpt-subscription"
def _resolve_probe_key(ep) -> Optional[str]:
"""API key/bearer to probe an endpoint with.
Delegates to ``resolve_endpoint_runtime``, which already returns the static
``ModelEndpoint.api_key`` for keyed endpoints and resolves (and refreshes)
the runtime bearer for session-backed providers (e.g. ChatGPT Subscription).
Returns None if resolution fails (e.g. re-auth required) so probing skips
rather than raising. Reads only already-loaded scalar attributes of ``ep``.
"""
try:
from src.endpoint_resolver import resolve_endpoint_runtime
_base, key = resolve_endpoint_runtime(ep, owner=getattr(ep, "owner", None))
return key
except Exception as e:
logger.warning("Probe key resolution failed for %s: %s", getattr(ep, "id", "?"), e)
return None
def _probe_single_model(base: str, api_key: Optional[str], model_id: str, timeout: int = 10, with_tools: bool = False) -> dict:
"""Send a realistic completion request to a single model. Returns {status, latency_ms, error?}."""
provider = _detect_provider(base)
if _is_discovery_only_provider(provider):
# Responses/Codex API, not chat-completions: a completion probe would
# 400 and the re-probe flow would then hide every model. Discovery-only.
return {"status": "ok", "latency_ms": 0, "skipped": True}
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Say OK"},
@@ -621,6 +682,11 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
For Anthropic, queries their /v1/models API, falling back to hardcoded list."""
from src.endpoint_resolver import resolve_url
base = resolve_url(_normalize_base(base_url))
if _detect_provider(base) == "chatgpt-subscription":
from src.chatgpt_subscription import fetch_available_models
if api_key:
return fetch_available_models(api_key, timeout=timeout)
return []
if _detect_provider(base) == "anthropic":
# Try Anthropic's /v1/models endpoint first
url = build_models_url(base)
@@ -647,6 +713,10 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
logger.warning(f"Anthropic /v1/models failed, using hardcoded list: {e}")
return list(ANTHROPIC_MODELS)
url = build_models_url(base)
if not url:
curated_key = _match_provider_curated(base, None)
fallback = _PROVIDER_CURATED.get(curated_key) if curated_key else None
return list(fallback or [])
headers = build_headers(api_key, base)
try:
r = httpx.get(url, headers=headers, timeout=timeout, verify=llm_verify())
@@ -998,6 +1068,17 @@ def setup_model_routes(model_discovery):
ok, info = _should_refresh_endpoint(ep, now, force=force)
if not ok:
continue
if getattr(ep, "provider_auth_id", None):
try:
from src.endpoint_resolver import resolve_endpoint_runtime
info["base"], info["api_key"] = resolve_endpoint_runtime(
ep,
owner=getattr(ep, "owner", None),
)
info["key"] = _refresh_key(info["base"], info["api_key"])
except Exception as e:
logger.warning("Skipping model refresh for %s: could not resolve provider auth: %s", getattr(ep, "name", ep.id), e)
continue
groups.setdefault(info["key"], {
"base": info["base"],
"api_key": info["api_key"],
@@ -1266,12 +1347,20 @@ def setup_model_routes(model_discovery):
"endpoint_kind": kind,
}
try:
t0 = _time.time()
ping = _ping_endpoint(base, ep.api_key, timeout=1.5)
entry["latency_ms"] = round((_time.time() - t0) * 1000)
entry["status"] = "online" if ping.get("reachable") or cached_count else "offline"
entry["error"] = ping.get("error")
entry["model_count"] = cached_count or (len(ANTHROPIC_MODELS) if provider == "anthropic" else 0)
if _is_discovery_only_provider(provider):
# No general health endpoint — an unauthenticated GET just
# 401s. Report status from cached models instead of pinging.
entry["latency_ms"] = None
entry["status"] = "online" if cached_count else "offline"
entry["error"] = None
entry["model_count"] = cached_count
else:
t0 = _time.time()
ping = _ping_endpoint(base, ep.api_key, timeout=1.5)
entry["latency_ms"] = round((_time.time() - t0) * 1000)
entry["status"] = "online" if ping.get("reachable") or cached_count else "offline"
entry["error"] = ping.get("error")
entry["model_count"] = cached_count or (len(ANTHROPIC_MODELS) if provider == "anthropic" else 0)
except Exception as e:
entry["latency_ms"] = None
entry["status"] = "online" if cached_count else "offline"
@@ -1304,7 +1393,7 @@ def setup_model_routes(model_discovery):
if ep_id and ep_id not in endpoints_cache:
ep = db.query(ModelEndpoint).filter(ModelEndpoint.id == ep_id).first()
if ep:
endpoints_cache[ep_id] = {"base_url": ep.base_url, "api_key": ep.api_key}
endpoints_cache[ep_id] = {"base_url": ep.base_url, "api_key": _resolve_probe_key(ep)}
ep_data = endpoints_cache.get(ep_id)
if not ep_data:
# Try to find by base_url from the model's endpoint field
@@ -1343,7 +1432,7 @@ def setup_model_routes(model_discovery):
"id": ep.id,
"name": ep.name,
"base_url": ep.base_url,
"api_key": ep.api_key,
"api_key": _resolve_probe_key(ep),
})
finally:
db.close()
@@ -1432,12 +1521,14 @@ def setup_model_routes(model_discovery):
# Endpoint counts as reachable if it has any model — including
# admin-pinned IDs that a probe would never surface.
status = "online" if (all_models or pinned) else "offline"
base = _normalize_base(r.base_url)
ping = None
if not all_models and not pinned and r.is_enabled:
# Discovery-only providers have no health endpoint — an
# unauthenticated ping just 401s, so don't bother.
if not all_models and not pinned and r.is_enabled and not _is_discovery_only_provider(_detect_provider(base)):
ping = _ping_endpoint(r.base_url, r.api_key, timeout=1.0)
if ping.get("reachable"):
status = "empty"
base = _normalize_base(r.base_url)
kind = _effective_endpoint_kind(r, base)
results.append({
"id": r.id,
@@ -1713,7 +1804,7 @@ def setup_model_routes(model_discovery):
ep = db.query(ModelEndpoint).filter(ModelEndpoint.id == ep_id).first()
if not ep:
raise HTTPException(404, "Endpoint not found")
ep_data = {"id": ep.id, "name": ep.name, "base_url": ep.base_url, "api_key": ep.api_key}
ep_data = {"id": ep.id, "name": ep.name, "base_url": ep.base_url, "api_key": _resolve_probe_key(ep)}
finally:
db.close()
@@ -1777,7 +1868,7 @@ def setup_model_routes(model_discovery):
category = _classify_endpoint(base, kind)
timeout = _manual_refresh_timeout(ep, category, refresh_timeout)
try:
probed = _probe_endpoint(base, ep.api_key, timeout=timeout)
probed = _probe_endpoint(base, _resolve_probe_key(ep), timeout=timeout)
except Exception as exc:
logger.warning("Manual model refresh failed for endpoint %s at %s: %s", ep_id, base, exc)
probed = []
@@ -2116,7 +2207,9 @@ def setup_model_routes(model_discovery):
cleared_user_preferences = _clear_user_prefs_for_endpoint(ep_id)
cleared_sessions = _clear_sessions_for_endpoint(db, ep.base_url)
cleared_loaded_sessions = _clear_loaded_sessions_for_endpoint(ep.base_url)
auth_id = getattr(ep, "provider_auth_id", None)
db.delete(ep)
cleared_provider_auth = _delete_orphaned_provider_auth(db, auth_id, exclude_ep_id=ep_id)
db.commit()
_invalidate_models_cache()
_local_probe_cache["data"] = None
@@ -2126,6 +2219,7 @@ def setup_model_routes(model_discovery):
"cleared_user_preferences": cleared_user_preferences,
"cleared_sessions": cleared_sessions,
"cleared_loaded_sessions": cleared_loaded_sessions,
"cleared_provider_auth": cleared_provider_auth,
}
finally:
db.close()