chore: bump to 1.3.0

Signed-off-by: disqualifier <dev@disqualifier.me>

README.md

@@ -11,19 +11,19 @@ and swap the HTTP client while inheriting everything else.
 `requirements.txt`:
 
 ```
-aioweb @ git+ssh://git@git.rethinkstudios.io/rethink-public/aioweb.git@v1.0.2
+aioweb @ git+ssh://git@git.rethinkstudios.io/rethink-public/aioweb.git@v1.3.0
 ```
 
 Direct:
 
 ```bash
-pip install "aioweb @ git+ssh://git@git.rethinkstudios.io/rethink-public/aioweb.git@v1.0.2"
+pip install "aioweb @ git+ssh://git@git.rethinkstudios.io/rethink-public/aioweb.git@v1.3.0"
 ```
 
 Requires `aiohttp` and `yarl` (pulled transitively), plus the sibling `commons` library
 (a private `git+ssh` package — the install needs access to the `rethink-public` org).
 
-Drop the `@v1.0.2` suffix from the line above to install the latest unpinned.
+Drop the `@v1.3.0` suffix from the line above to install the latest unpinned.
 
 ## Usage
 
@@ -150,6 +150,22 @@ Two changes can't be shimmed without re-introducing the bugs they fix:
 
 ## Changelog
 
+### v1.1.0
+
+- **Hang-guard on `request()` — a wedged backend can no longer park the loop forever.**
+  `request()` now wraps the backend call (`_raw_request`) in an outer `asyncio.wait_for`
+  deadline sized at the effective timeout **+ 5s slack** (`_HANG_GUARD_SLACK`). The
+  backend's own timeout still fires first in every healthy failure (slack, not
+  replacement); the envelope only trips when the backend's timer is dead — e.g. a
+  `curl_cffi` transfer that loses both its wakeup and its own enforcement in the same
+  failure — and its cancellation is what unwedges the orphaned transfer. The guard's
+  deadline is the per-call numeric `timeout` when given, else the session timeout
+  (`Session(timeout=...)`, default 10s); it composes cleanly with `request_with_retries`
+  (a wedge becomes one logged `ServerTimeoutError`, the next attempt proceeds, and an
+  exhausted retry returns a `FailureResponse` rather than hanging). **Opt-out:** a
+  session deliberately constructed unbounded (`Session(timeout=None)`) stays unguarded,
+  for genuinely long-lived calls (long-poll / streaming). Additive; no new knob.
+
 ### v0.1.13
 
 - **Session-default timeout no longer poisons pooled keep-alive connections.**

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "aioweb"
-version = "1.0.2"
+version = "1.3.0"
 description = "Async HTTP session wrapper over aiohttp — proxies, header overwrites, retries, previews. Config-free, installable."
 requires-python = ">=3.10"
 dependencies = [

src/aioweb/session.py

@@ -15,6 +15,7 @@ import warnings
 from http.cookies import SimpleCookie
 
 import aiohttp
+from multidict import CIMultiDict
 from yarl import URL
 from commons import aretry
 
@@ -63,6 +64,7 @@ log = logging.getLogger(__name__)
 DEFAULT_ATTEMPTS = 3
 DEFAULT_BACKOFF_BASE = 2.0
 RETRY_STATUSES = frozenset({429, 500, 502, 503, 504})
+_HANG_GUARD_SLACK = 5
 
 
 class ExtendedSession:
@@ -84,12 +86,15 @@ class ExtendedSession:
             kwargs: passed through to aiohttp.ClientSession
         """
         self.inject = inject
-        self.header_overwrites = overwrites or {}
-        self.domain_overwrites = domain_overwrites or {}
+        # copied, not aliased: a shared config dict must not be mutated by (or leak a
+        # clear_proxies() into) a sibling session
+        self.header_overwrites = dict(overwrites or {})
+        self.domain_overwrites = dict(domain_overwrites or {})
         self.ephemeral_headers = {}
-        self.proxies = proxies or {}
-        # own header layer, not aiohttp privates, so update_headers/clear_headers work
-        self._default_headers = dict(headers or {})
+        self.proxies = dict(proxies or {})
+        # own header layer, not aiohttp privates, so update_headers/clear_headers work;
+        # case-insensitive like HTTP header names
+        self._default_headers = CIMultiDict(headers or {})
         self._session_timeout = timeout
         self._session_kwargs = kwargs
         # aiohttp>=3.14 needs a running loop to build ClientSession; built lazily instead
@@ -138,8 +143,12 @@ class ExtendedSession:
         self.header_overwrites[header] = value
 
     def _apply_overwrites(self, request_headers):
-        """apply static overwrites and ephemeral headers to a request's headers"""
-        request_headers = dict(request_headers or {})
+        """apply static overwrites and ephemeral headers to a request's headers
+
+        header names match case-insensitively, so an overwrite replaces a `user-agent`
+        rather than sending it alongside a second `User-Agent`
+        """
+        request_headers = CIMultiDict(request_headers or {})
         # list()-snapshot so a concurrent mutation of the shared dicts can't raise
         # "dict changed size during iteration"
         for header, value in list(self.header_overwrites.items()):
@@ -152,7 +161,7 @@ class ExtendedSession:
                     request_headers.update(value)
                 else:
                     request_headers[header] = value
-        return request_headers
+        return dict(request_headers)
 
     def set_ephemeral(self, header, value_callable):
         """register a header generated fresh (via callable) for each request"""
@@ -261,7 +270,7 @@ class ExtendedSession:
         falling back to them.
         """
         proxies = self.proxies if proxies is None else proxies
-        scheme = url.split("://")[0]
+        scheme = URL(url).scheme
         return proxies.get(scheme)
 
     # -------------------------------------------------------------------------
@@ -352,7 +361,8 @@ class ExtendedSession:
         """
         url = self._apply_domain_overwrites(url)
         proxy = self._get_proxy(url, kwargs.pop("proxies", None))
-        merged = {**self._default_headers, **(kwargs.pop("headers", None) or {})}
+        merged = CIMultiDict(self._default_headers)
+        merged.update(kwargs.pop("headers", None) or {})
         headers = self._apply_overwrites(merged)
 
         timeout = kwargs.get("timeout")
@@ -420,11 +430,19 @@ class ExtendedSession:
             kwargs["proxy"] = resolved_proxy
         debug = kwargs.pop("debug", False)
 
-        merged = {**self._default_headers, **(kwargs.get("headers") or {})}
+        merged = CIMultiDict(self._default_headers)
+        merged.update(kwargs.get("headers") or {})
         kwargs["headers"] = self._apply_overwrites(merged)
         kwargs["headers"] = {str(k): str(v) for k, v in kwargs["headers"].items()}
 
         timeout = kwargs.get("timeout")
+        # the hang-guard deadline: a per-call timeout (a number, or a ClientTimeout's
+        # .total), else the session default. a timeout=None (omitted, or the explicit None
+        # request_with_retries passes) means "use the session bound" - so it guards on
+        # self._session_timeout, NOT unguarded. unguarded only when the caller asked for no
+        # bound: a session constructed with timeout=None (the documented long-poll/streaming
+        # opt-out), or a per-call ClientTimeout(total=None).
+        guard_secs = self._session_timeout if timeout is None else getattr(timeout, "total", timeout)
         if isinstance(timeout, (int, float)):
             kwargs["timeout"] = aiohttp.ClientTimeout(total=timeout)
         elif timeout is None and "timeout" in kwargs:
@@ -438,18 +456,32 @@ class ExtendedSession:
             log.info("sending request to: %s", url)
 
         try:
-            result = await self._raw_request(method, url, **kwargs)
+            # hang-guard: an outer asyncio deadline (session/curl timers can die in the
+            # same failure that parks the transfer - a backend that loses both wakeup and
+            # its own timeout enforcement would otherwise leave this await parked forever).
+            # the backend's own timeout still fires first in every healthy failure (slack,
+            # not replacement); wait_for only trips when the backend's enforcement is dead,
+            # and its cancellation is what unwedges the orphaned transfer.
+            if guard_secs is not None:
+                result = await asyncio.wait_for(
+                    self._raw_request(method, url, **kwargs), guard_secs + _HANG_GUARD_SLACK
+                )
+            else:
+                result = await self._raw_request(method, url, **kwargs)
             if debug and result.redirect_chain:
                 log.info("redirect chain: %s", result.redirect_chain)
             return result
         except asyncio.TimeoutError as error:
-            # not an aiohttp.ClientError subclass - wrap as ServerTimeoutError so
-            # callers get a typed failure and request_with_retries can label it a timeout
+            # not an aiohttp.ClientError subclass - wrap as ServerTimeoutError so callers
+            # get a typed failure and request_with_retries can label it a timeout. now also
+            # catches the hang-guard firing (asyncio.wait_for raises asyncio.TimeoutError).
             raise aiohttp.ServerTimeoutError(f"timeout for {url}: {error}") from error
-        except aiohttp.ClientError as error:
+        except aiohttp.ClientError:
             # re-raise the original subtype (not flattened) - request_with_retries still
-            # catches the base aiohttp.ClientError below and is unaffected
-            log.error("client error for %s: %s", url, error)
+            # catches the base aiohttp.ClientError below and is unaffected. no log here:
+            # this path RAISES, so the exception carries the failure (raise XOR log); on the
+            # retrying path commons.aretry emits the per-attempt WARNING and the terminal
+            # branch logs on exhaustion - logging here would double-report the same failure.
             raise
 
     async def request_with_retries(
@@ -483,7 +515,11 @@ class ExtendedSession:
                 headers=headers, proxies=proxies, timeout=timeout, debug=debug,
             )
             if response.status_code in retry_statuses:
-                log.warning("retryable status %s for %s", response.status_code, url)
+                # debug, not warning: this RAISES _RetryStatus to trigger a retry, so it must
+                # not also warn/error the same failure (raise XOR log). commons.aretry emits
+                # the per-attempt WARNING with the attempt count when it catches and retries;
+                # the terminal branch below logs on exhaustion.
+                log.debug("retryable status %s for %s", response.status_code, url)
                 raise _RetryStatus(response)
             return response
 
@@ -492,19 +528,25 @@ class ExtendedSession:
                 attempt, attempts=attempts, backoff=1.0, factor=backoff_base,
                 jitter=False, on=(Exception,),
             )
+        # terminal path: retries are exhausted and the failure is SWALLOWED into a falsy
+        # FailureResponse the caller branches on (the documented contract). rule 2 mandates a
+        # log on a swallow; level is WARNING because the lib recovered cleanly into a
+        # branchable value - the failing op is the caller's to escalate once it sees the falsy
+        # result, so the lib does not claim ERROR on the caller's behalf. all four branches are
+        # the same event class (exhausted retries) and stay at one uniform level.
         except _RetryStatus as exhausted:
-            log.error("all %d attempts failed for %s (last status %s)",
-                      attempts, url, exhausted.response.status_code)
+            log.warning("all %d attempts failed for %s (last status %s)",
+                        attempts, url, exhausted.response.status_code)
             return exhausted.response
         except asyncio.TimeoutError:
             # catch before ClientError so a timeout is labeled as such, not generic
-            log.error("all %d attempts timed out for %s", attempts, url)
+            log.warning("all %d attempts timed out for %s", attempts, url)
             return FailureResponse(reason="timeout", url=url)
         except aiohttp.ClientError as error:
-            log.error("all %d attempts failed for %s (client error: %s)", attempts, url, error)
+            log.warning("all %d attempts failed for %s (client error: %s)", attempts, url, error)
             return FailureResponse(reason=f"client error: {error}", url=url)
         except Exception as error:
-            log.error("all %d attempts failed for %s (unexpected: %s)", attempts, url, error)
+            log.warning("all %d attempts failed for %s (unexpected: %s)", attempts, url, error)
             return FailureResponse(reason=f"unexpected error: {error}", url=url)
 
     # -------------------------------------------------------------------------