fix: surface the response body on 4xx so 403s are diagnosable

Media downloads logged "HTTP Error 403:" with no reason. That string is
curl_cffi's raise_for_status() format, "HTTP Error {code}: {reason}", and
HTTP/2 carries no reason phrase — so the message said nothing, and
_make_request threw the response body away. The provider's JSON `detail`
is the only explanation available for a refused asset.

- base._make_request: end non-retryable statuses with a ProviderError
  carrying the body's detail/error/message (redacted, truncated to 300
  chars) instead of a bare raise_for_status().
- media: bucket 403 as `forbidden` in the run summary, separately from
  `download-error` — "the asset is gone" and "we were refused" are
  different problems.
- utils.redact_secrets: match secret key names per word. Exact matching
  let access_token, api_key, and session-token through into logged
  bodies; "keywords"/"monkey"/"tokenizer" stay intact.
- tests/test_config.py: test_defaults depended on the absence of a local
  .env — load_config() calls load_dotenv(override=False), which restored
  the variable the test had just deleted. Stub dotenv discovery.

305 tests pass.

CHANGELOG.md

@@ -3,6 +3,16 @@
 All notable changes to this project will be documented here.
 Format follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [Unreleased]
+
+### Fixed
+- **4xx errors now report why.** `_make_request` ended non-retryable statuses with `raise_for_status()`, whose curl_cffi message is `HTTP Error {code}: {reason}` — and HTTP/2 carries no reason phrase, so a refused request logged as bare `HTTP Error 403:` and the response body (the only explanation the provider gives) was discarded. The body's `detail`/`error`/`message` is now carried into the `ProviderError`, redacted and truncated. This is what made the media 403s on `GET /backend-api/files/{id}/download` undiagnosable.
+- **`redact_secrets` missed compound key names.** It matched keys exactly, so `access_token`, `api_key`, and `session-token` passed through un-redacted into debug-logged response bodies; matching now applies per word ("keywords", "monkey", "tokenizer" stay intact).
+- **`tests/test_config.py::TestSessionLimiterConfig::test_defaults` depended on the developer's `.env`.** `load_config()` calls `load_dotenv(override=False)`, which re-populated the variable the test had just deleted — so it passed only on a machine with no `.env`. The test now stubs dotenv discovery.
+
+### Changed
+- Media download failures are bucketed as `forbidden` (403 — the asset exists, we were refused) separately from `download-error`, so the run summary distinguishes it from `expired-or-missing` (404).
+
 ## [0.8.0] - 2026-07-06
 
 Focused on the Claude Code provider after the tool's on-disk layout changed and