ouyangbo/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 10 Packages Projects Releases Wiki Activity
28,271 Commits 1 Branch 0 Tags
cf60ebbdfd264c3fc067b9e3230df8752c50d2ec
Commit Graph

18 Commits

Author SHA1 Message Date
Stephen Chin 5247a6f07f fix(compaction): clarify runtime capability state 
Use a distinct runtime_capabilities field on agents, preserve compatibility with earlier snapshots, and resolve the canonical direct OpenAI endpoint when a cross-provider switch omits base_url. Keep ambiguous proxy routes fail-closed.
 2026-08-30 05:16:10 -07:00
Stephen Chin 903c36b6d4 fix(compaction): resolve capability from effective switch URL 2026-08-30 05:16:10 -07:00
Stephen Chin 08c7879ca1 fix(compaction): preserve native capability across runtime switches 
Stage destination native-compaction capabilities until the complete runtime and context setup succeeds, and restore them with primary and fallback runtimes. Keep native compaction default-deny across live switches and session reconstruction.\n\nVerification: uv run --with pytest --with pyyaml python -m pytest tests/run_agent/test_switch_model_context.py tests/run_agent/test_native_compaction.py tests/run_agent/test_native_compaction_switch_capabilities.py tests/run_agent/test_switch_model_rollback.py tests/run_agent/test_fallback_reasoning_override.py tests/run_agent/test_primary_runtime_restore.py tests/run_agent/test_provider_fallback.py -q -o 'addopts='; uv run --with ruff ruff check <touched files>; git diff --check
 2026-08-30 05:16:10 -07:00
Teknium 3913ac2ba0 test: pair load_config_readonly stubs at pruned-file sites (post-merge with main's readonly sweep) 
Main's 243c9182b1/a16fd675df/7142dc4580 added load_config_readonly
sibling stubs across 38 files; our pruned versions of 11 of those files
kept only the load_config stubs. Re-applied the pairing at every
surviving site (26 patch()/setattr sites) — same return_value/
side_effect as the adjacent load_config stub. 494 tests green across
the 11 files.
 2026-07-29 15:37:24 -07:00
teknium1 243c9182b1 test: patch load_config_readonly alongside load_config across affected suites 
The readonly swaps mean agent/ modules now read config through
load_config_readonly(); tests that stubbed only load_config stopped
intercepting those reads. Added sibling readonly stubs (same
return_value/side_effect/lambda) at every affected site across 11 test
files, found via a tree-wide sweep of load_config stubs cross-referenced
against the swapped modules. 3,915 tests green across the 38-file
sibling sweep.
 2026-07-29 15:28:15 -07:00
Teknium 6b81590c55 test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions 
Systematic prune per AGENTS.md test policy, one pass over every major
test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli,
cron, tui_gateway, honcho/openviking, root-level):

- DELETE: source-reading tests (read_text/getsource on prod files),
  change-detector tests (exact catalog counts, model-name snapshots,
  config version literals), mock-echo tests (assert a mock returns what
  it was told), assertion-free/trivial tests, near-duplicate
  parametrizations (boundaries + one representative kept), async/sync
  twin duplicates, cosmetic within-file variations.
- KEEP (mandatory): security/redaction/approval guards, message-role
  alternation invariants, prompt-caching/deterministic-call-id
  invariants, issue-number regression tests (deduped), E2E tests.
- 6 test files deleted outright (script-style/no-assert or fully
  redundant); conftest.py, fakes/, fixtures/ untouched.
- tests/acp/conftest.py added: autouse fixture stubs the live
  models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server
  tests performed on every session create — test_server.py 147s → 3.4s,
  and the tests are now genuinely hermetic.
- Sleep-based slowness shrunk where safe (codex_ttfb_watchdog,
  compression_concurrent_fork, etc.); no wall-clock assertion tightened.

Verification: full hermetic suite via scripts/run_tests.sh —
2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall
(baseline: 583s wall, 13,564s subprocess CPU).
 2026-07-29 13:10:23 -07:00
LunarNexus 8c12fa7cf0 fix(lmstudio): respect applied runtime context 2026-07-29 02:19:13 +05:30
cucurigoo 63dd651b3d fix(providers): scope route-owned runtime settings 2026-07-22 11:19:37 +05:30
cucurigoo f3f0135154 fix(providers): fail closed on missing active route 2026-07-22 11:19:37 +05:30
cucurigoo ddd667503e test(providers): cover URL whitespace route identity 2026-07-22 11:19:37 +05:30
cucurigoo 639cee5216 test(providers): complete hermetic route coverage 2026-07-22 11:19:37 +05:30
cucurigoo 2507af2194 test(providers): cover query path slash identity 2026-07-22 11:19:37 +05:30
cucurigoo fcae6fb9b8 test(providers): cover route URL identity boundaries 2026-07-22 11:19:37 +05:30
cucurigoo cb785e6b49 fix(providers): align custom route scoping 2026-07-22 11:19:37 +05:30
cucurigoo 97499d702e fix(compression): harden startup route scoping 2026-07-22 11:19:37 +05:30
cucurigoo 377244f7c8 fix(compression): prevent stale-budget retry loops 2026-07-22 11:19:37 +05:30
Stephen Schoettler 3c106c89a1 test(ci): stabilize shared optional dependency baselines 2026-05-13 17:32:22 -07:00
Ronald Reis fd3e855d58 fix: pass config_context_length to switch_model context compressor 
When switching models at runtime, the config_context_length override
was not being passed to the new context compressor instance. This
meant the user-specified context length from config.yaml was lost
after a model switch.

- Store _config_context_length on AIAgent instance during __init__
- Pass _config_context_length when creating new ContextCompressor in switch_model
- Add test to verify config_context_length is preserved across model switches

Fixes: quando estamos alterando o modelo não está alterando o tamanho do contexto
 2026-04-10 05:52:45 -07:00