hermes-agent/tests
Andre Kurait a8e89cbbf6
fix(bedrock): resolve context length via static table before custom-endpoint probe
## Problem

`get_model_context_length()` in `agent/model_metadata.py` had a resolution
order bug that caused every Bedrock model to fall back to the 128K default
context length instead of reaching the static Bedrock table (200K for
Claude, etc.).

The root cause: `bedrock-runtime.<region>.amazonaws.com` is not listed in
`_URL_TO_PROVIDER`, so `_is_known_provider_base_url()` returned False.
The resolution order then ran the custom-endpoint probe (step 2) *before*
the Bedrock branch (step 4b), which:

  1. Treated Bedrock as a custom endpoint (via `_is_custom_endpoint`).
  2. Called `fetch_endpoint_model_metadata()` → `GET /models` on the
     bedrock-runtime URL (Bedrock doesn't serve this shape).
  3. Fell through to `return DEFAULT_FALLBACK_CONTEXT` (128K) at the
     "probe-down" branch — never reaching the Bedrock static table.

Result: users on Bedrock saw 128K context for Claude models that
actually support 200K on Bedrock, causing premature auto-compression.

## Fix

Promote the Bedrock branch from step 4b to step 1b, so it runs *before*
the custom-endpoint probe at step 2. The static table in
`bedrock_adapter.py::get_bedrock_context_length()` is the authoritative
source for Bedrock (the ListFoundationModels API doesn't expose context
window sizes), so there's no reason to probe `/models` first.

The original step 4b is replaced with a one-line breadcrumb comment
pointing to the new location, to make the resolution-order docstring
accurate.

## Changes

- `agent/model_metadata.py`
  - Add step 1b: Bedrock static-table branch (unchanged predicate, moved).
  - Remove dead step 4b block, replace with breadcrumb comment.
  - Update resolution-order docstring to include step 1b.

- `tests/agent/test_model_metadata.py`
  - New `TestBedrockContextResolution` class (3 tests):
    - `test_bedrock_provider_returns_static_table_before_probe`:
      confirms `provider="bedrock"` hits the static table and does NOT
      call `fetch_endpoint_model_metadata` (regression guard).
    - `test_bedrock_url_without_provider_hint`: confirms the
      `bedrock-runtime.*.amazonaws.com` host match works without an
      explicit `provider=` hint.
    - `test_non_bedrock_url_still_probes`: confirms the probe still
      fires for genuinely-custom endpoints (no over-reach).

## Testing

  pytest tests/agent/test_model_metadata.py -q
  # 83 passed in 1.95s (3 new + 80 existing)

## Risk

Very low.

- Predicate is identical to the original step 4b — no behaviour change
  for non-Bedrock paths.
- Original step 4b was dead code for the user-facing case (always hit
  the 128K fallback first), so removing it cannot regress behaviour.
- Bedrock path now short-circuits before any network I/O — faster too.
- `ImportError` fall-through preserved so users without `boto3`
  installed are unaffected.

## Related

- This is a prerequisite for accurate context-window accounting on
  Bedrock — the fix for #14710 (stale-connection client eviction)
  depends on correct context sizing to know when to compress.

Signed-off-by: Andre Kurait <andrekurait@gmail.com>
2026-04-23 20:33:09 +00:00
..
acp fix(acp): wire approval callback + make it thread-local (#13525) 2026-04-21 06:20:40 -07:00
agent fix(bedrock): resolve context length via static table before custom-endpoint probe 2026-04-23 20:33:09 +00:00
cli test(approval): regression guards for thread-local callback contract 2026-04-21 14:29:08 -07:00
cron test(cron): exercise _deliver_result and _send_media_via_adapter directly for timeout-cancel 2026-04-21 05:52:16 -07:00
e2e fix: follow-up for salvaged PRs #6293, #7387, #9091, #13131 2026-04-20 14:56:04 -07:00
environments/benchmarks fix(security): consolidated security hardening — SSRF, timing attack, tar traversal, credential leakage (#5944) 2026-04-07 17:28:37 -07:00
fakes
gateway fix(gateway): guard-match the finally-block _active_sessions delete 2026-04-23 05:15:52 -07:00
hermes_cli feat: add Xiaomi MiMo v2.5-pro and v2.5 model support (#14635) 2026-04-23 10:06:25 -07:00
honcho_plugin feat(honcho): wizard cadence default 2, surface reasoning level, backwards-compat fallback 2026-04-18 22:50:55 -07:00
integration fix(discord): strip RTP padding before DAVE/Opus decode (#11267) 2026-04-16 16:50:15 -07:00
plugins feat(image_gen): add openai-codex plugin (gpt-image-2 via Codex OAuth) (#14317) 2026-04-22 20:43:21 -07:00
run_agent refactor: remove _nr_to_assistant_message shim + fix flush_memories guard 2026-04-23 02:30:05 -07:00
skills fix(google-workspace): normalize authorized user token writes 2026-04-16 04:22:16 -07:00
tools feat(skills-guard): gate agent-created scanner on config.skills.guard_agent_created (default off) 2026-04-23 06:20:47 -07:00
tui_gateway Merge branch 'main' into fix/tui-provider-resolution 2026-04-22 11:47:49 -07:00
__init__.py
conftest.py test(conftest): reset module-level state + unset platform allowlists (#13400) 2026-04-21 01:33:10 -07:00
run_interrupt_test.py fix: thread safety for concurrent subagent delegation (#1672) 2026-03-17 02:53:33 -07:00
test_account_usage.py feat(account-usage): add per-provider account limits module 2026-04-21 01:56:35 -07:00
test_base_url_hostname.py security(runtime_provider): close OLLAMA_API_KEY substring-leak sweep miss (#13522) 2026-04-21 06:06:16 -07:00
test_batch_runner_checkpoint.py fix(batch_runner): mark discarded no-reasoning prompts as completed (#9950) 2026-04-20 04:56:06 -07:00
test_cli_file_drop.py fix(tui): improve macOS paste and shortcut parity 2026-04-21 08:00:00 -07:00
test_cli_skin_integration.py fix: align status bar skin tests with upstream main 2026-04-22 13:20:02 -07:00
test_ctx_halving_fix.py fix(tests): fix 78 CI test failures and remove dead test (#9036) 2026-04-13 10:50:24 -07:00
test_empty_model_fallback.py fix: fall back to provider's default model when model config is empty (#8303) 2026-04-12 03:53:30 -07:00
test_evidence_store.py
test_hermes_constants.py fix(gateway): harden Docker/container gateway pathway 2026-04-12 16:36:11 -07:00
test_hermes_logging.py fix(tests): fix 78 CI test failures and remove dead test (#9036) 2026-04-13 10:50:24 -07:00
test_hermes_state.py feat(dashboard): track real API call count per session 2026-04-22 05:51:58 -07:00
test_honcho_client_config.py feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623) 2026-04-02 15:33:51 -07:00
test_ipv4_preference.py feat: add network.force_ipv4 config to fix IPv6 timeout issues (#8196) 2026-04-11 23:12:11 -07:00
test_mcp_serve.py feat: add MCP server mode — hermes mcp serve (#3795) 2026-03-29 15:47:19 -07:00
test_mini_swe_runner.py fix(kimi): omit temperature entirely for Kimi/Moonshot models (#13157) 2026-04-20 12:23:05 -07:00
test_minimax_model_validation.py fix(models): validate MiniMax models against static catalog (#12611, #12460, #12399, #12547) 2026-04-19 22:44:47 -07:00
test_minisweagent_path.py chore: remove all remaining mini-swe-agent references 2026-03-24 08:19:23 -07:00
test_model_picker_scroll.py fix: CLI/UX batch — ChatConsole errors, curses scroll, skin-aware banner, git state banner (#5974) 2026-04-07 17:59:42 -07:00
test_model_tools.py feat(plugins): add transform_tool_result hook for generic tool-result rewriting (#12972) 2026-04-20 03:48:08 -07:00
test_model_tools_async_bridge.py fix(core): ensure non-blocking executor shutdown on async timeout 2026-04-22 14:42:32 -07:00
test_ollama_num_ctx.py fix: provider/model resolution — salvage 4 PRs + MiniMax aux URL fix (#5983) 2026-04-07 22:23:28 -07:00
test_packaging_metadata.py chore: prepare Hermes for Homebrew packaging (#4099) 2026-03-30 17:34:43 -07:00
test_plugin_skills.py fix(tests): attach caplog to specific logger in 3 order-dependent tests (#11453) 2026-04-17 00:20:40 -07:00
test_project_metadata.py build(deps): add qrcode to dingtalk + feishu extras (parity with messaging) (#11627) 2026-04-17 13:31:53 -07:00
test_retry_utils.py feat(agent): add jittered retry backoff 2026-04-08 00:41:36 -07:00
test_sql_injection.py fix(security): eliminate SQL string formatting in execute() calls 2026-03-19 15:16:35 +01:00
test_subprocess_home_isolation.py fix: per-profile subprocess HOME isolation (#4426) (#7357) 2026-04-10 13:37:45 -07:00
test_timezone.py test: speed up slow tests (backoff + subprocess + IMDS network) (#11797) 2026-04-17 14:21:22 -07:00
test_toolset_distributions.py
test_toolsets.py fix(ci): unblock test suite + cut ~2s of dead Z.AI probes from every AIAgent 2026-04-19 19:18:19 -07:00
test_trajectory_compressor.py fix(kimi): omit temperature entirely for Kimi/Moonshot models (#13157) 2026-04-20 12:23:05 -07:00
test_trajectory_compressor_async.py fix(kimi): omit temperature entirely for Kimi/Moonshot models (#13157) 2026-04-20 12:23:05 -07:00
test_transform_tool_result_hook.py test: stop testing mutable data — convert change-detectors to invariants (#13363) 2026-04-20 23:20:33 -07:00
test_tui_gateway_server.py Merge pull request #14135 from helix4u/fix/tui-state-db-optional 2026-04-22 20:11:07 -05:00
test_utils_truthy_values.py Gate tool-gateway behind an env var, so it's not in users' faces until we're ready. Even if users enable it, it'll be blocked server-side for now, until we unlock for non-admin users on tool-gateway. 2026-03-30 13:28:10 +09:00