RomanNum3ral
/
hermes-agent
mirror of https://github.com/NousResearch/hermes-agent.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
hermes-agent/agent
History
Soju06 82e2c9ce40 perf(agent): reuse the per-request OpenAI wire client across sequential LLM calls 
Every LLM call built a fresh openai.OpenAI wire client (new httpx pool,
TCP+TLS handshake, measured 19.2ms p50 / 35.5ms p95 per call at ~5 calls
per tool-loop turn) and closed it when the request finished. Cache ONE
reusable wire client on the agent, keyed by the effective client kwargs:

- _create_request_openai_client hands back the cached client when the
  effective kwargs are identical; any change (credential rotation,
  provider failover, vision default_headers) evicts and rebuilds.
- Only a request that produced a response reports a reuse close reason
  (request_complete / stream_request_complete); error unwinds report
  *_error_cleanup and really close, so a retry after a request error
  always builds a fresh pool.
- Cross-thread aborts poison the slot: a pool whose sockets were
  shutdown(SHUT_RDWR) from a stranger thread is never reused (#29507) —
  the owner-thread close discards it and the next create rebuilds. The
  holder read and the abort are atomic (under the holder lock) at all
  three abort sites, so a late abort can never poison the NEXT request's
  checked-out client.
- Worker-side interrupt breaks close the half-read SSE stream on the
  owning thread before building the partial response; a failed close
  poisons the slot (otherwise each interrupt leaked one checked-out
  connection until the pool hit PoolTimeout). run_codex_stream gets the
  same poison-on-close-failure handling.
- Single checked-out slot (in_use): a concurrent call gets an untracked
  client with the old per-request lifecycle.
- release_clients() / close() really close the cached client when idle;
  if a worker has it checked out they abort the sockets and detach the
  slot, deferring the FD release to the worker's own close.
- MoA facade and Mock passthroughs never enter the cache; max_retries=0
  is preserved on all request clients.
 		2026-07-28 19:06:59 +05:30
..
lsp fix(windows): sweep remaining unguarded text-mode subprocess sites codebase-wide 2026-07-24 11:45:57 -07:00
pet
…
proxy_sources fix(windows): sweep remaining unguarded text-mode subprocess sites codebase-wide 2026-07-24 11:45:57 -07:00
secret_sources fix(windows): sweep remaining unguarded text-mode subprocess sites codebase-wide 2026-07-24 11:45:57 -07:00
transports fix(codex): scope 24h retention to Bedrock Mantle 2026-07-24 15:54:08 -07:00
__init__.py
…
account_usage.py fix(auth): detect upstream Codex quota resets and lift stale pool cooldowns (#69494) 2026-07-22 10:58:22 -07:00
agent_init.py fix(xai): send Hermes-Agent User-Agent on chat/completions 2026-07-27 17:47:28 -07:00
agent_runtime_helpers.py fix(agent): shut down sockets on httpx mount pools during interrupt abort 2026-07-28 18:07:44 +05:30
anthropic_adapter.py nous portal anthropic wire 2026-07-27 11:53:48 -04:00
async_utils.py
…
aux_accounting.py
…
auxiliary_client.py Revert "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 22:28:08 -04:00
azure_identity_adapter.py
…
backend_identity.py refactor(fallback): single owner for backend identity and failure-scoped skips 2026-07-26 23:41:54 -07:00
background_review.py fix(curator): make the autonomous write policy consistent (#67140) 2026-07-25 19:27:17 -07:00
battery.py
…
bedrock_adapter.py feat(bedrock): add Converse API prompt caching (cachePoint) 2026-07-23 11:45:07 -07:00
billing_links.py feat(billing): shared cross-surface out-of-credits signal 2026-07-22 18:08:59 -05:00
billing_usage.py
…
billing_view.py feat(billing): carry the payment-method union through to clients (#71542) 2026-07-27 01:49:43 +05:30
bounded_response.py
…
browser_provider.py
…
browser_registry.py
…
chat_completion_helpers.py perf(agent): reuse the per-request OpenAI wire client across sequential LLM calls 2026-07-28 19:06:59 +05:30
codex_responses_adapter.py fix(codex): send prompt_cache_retention 24h for the GPT-5.5 family 2026-07-24 15:54:08 -07:00
codex_runtime.py perf(agent): reuse the per-request OpenAI wire client across sequential LLM calls 2026-07-28 19:06:59 +05:30
coding_context.py fix(agent): cache static system prompt prefixes 2026-07-24 16:01:38 -07:00
context_breakdown.py feat(cli,gateway): unify /context into a visual context-usage breakdown 2026-07-26 18:06:21 -07:00
context_compressor.py revert: PR #72817 — session activity watchdog, stall notify, compress timeout 2026-07-28 00:15:00 +05:00
context_engine.py fix(context-engine): snapshot select_context read-only inputs; scope on_turn_complete coverage doc 2026-07-23 19:44:35 -07:00
context_references.py fix(context): keep @ref tokens inline instead of stripping them from the prompt 2026-07-27 22:55:18 -05:00
conversation_compression.py refactor(agent): share static-prefix reconstruction, memoize failed rebuilds 2026-07-28 01:10:05 +05:30
conversation_loop.py perf(state): apply per-call token accounting on a background single-writer queue 2026-07-28 18:47:54 +05:30
copilot_acp_client.py fix(core,cli,gateway,plugins): add encoding='utf-8' to read_text() calls 2026-07-24 17:10:39 -07:00
credential_persistence.py
…
credential_pool.py fix: break unbounded 401 retry loop in credential pool OAuth path 2026-07-24 15:50:36 -07:00
credential_sources.py fix(windows): sweep remaining bare read_text/write_text sites + linter rule 2026-07-24 17:10:39 -07:00
credits_tracker.py feat(credits): report $used of $cap instead of % in the usage notice 2026-07-23 01:28:58 -05:00
curator.py fix: curator labels bundled skills as agent-created (#64393) 2026-07-25 18:10:24 -07:00
curator_backup.py
…
delegation_context.py fix(kanban): harden delegated-child mutation boundary 2026-07-23 07:33:36 -07:00
display.py
…
error_classifier.py fix(errors): log when the empty-stub guard and malformed-body classification fire 2026-07-27 20:27:56 -07:00
errors.py
…
file_safety.py fix(secrets): harden encrypted Bitwarden cache 2026-07-22 04:40:07 -07:00
gemini_native_adapter.py fix(gemini): explain legacy Standard-key 401 rejections with migration guidance 2026-07-26 20:58:57 -07:00
gemini_schema.py fix(gemini): preserve typed enum constraints as strings 2026-07-26 20:59:16 -07:00
i18n.py feat(i18n): add Arabic (ar) catalog for agent/CLI messages 2026-07-24 12:10:03 -05:00
image_gen_provider.py
…
image_gen_registry.py
…
image_routing.py feat(image_routing): accept vision alias for custom provider models 2026-07-23 08:32:09 -07:00
insights.py perf(state): apply per-call token accounting on a background single-writer queue 2026-07-28 18:47:54 +05:30
iteration_budget.py feat: raise default tool-calling iteration limit from 90 to 500 2026-07-26 12:54:45 -07:00
jiter_preload.py
…
kanban_stop.py
…
learn_prompt.py
…
learning_graph.py
…
learning_graph_render.py
…
learning_mutations.py
…
lmstudio_reasoning.py
…
manual_compression_feedback.py fix(compress): classify unconfirmed lock-acquire failures and cover all manual-compress surfaces 2026-07-23 08:19:14 -07:00
markdown_tables.py
…
memory_manager.py fix(memory): honor disabled toolsets for provider tools 2026-07-24 13:00:53 +05:30
memory_provider.py
…
message_content.py
…
message_sanitization.py
…
moa_loop.py refactor(moa): co-locate guidance peel with attach, add round-trip contract 2026-07-28 01:10:05 +05:30
moa_trace.py
…
model_metadata.py feat(models): add anthropic/claude-opus-5 to OpenRouter and Nous Portal catalogs 2026-07-24 13:00:15 -07:00
models_dev.py
…
moonshot_schema.py
…
nous_rate_guard.py fix: decode config and state files as UTF-8 on non-UTF-8 locales 2026-07-24 17:10:39 -07:00
onboarding.py feat(surfaces): route busy-input corrections through active-turn redirect 2026-07-22 12:10:58 -05:00
oneshot.py
…
plugin_llm.py
…
portal_tags.py
…
process_bootstrap.py
…
prompt_builder.py fix(P1+P2): marker names skill_view(name='X') + DEDUP rule for repeated [SKILL_PRUNED] markers 2026-07-23 16:58:06 -07:00
prompt_caching.py fix(agent): restrict strip flatten to decoration-produced shapes 2026-07-28 01:10:05 +05:30
rate_limit_tracker.py
…
reactions.py
…
reasoning_timeouts.py fix(timeouts): add claude-fable to reasoning stale-timeout floor table 2026-07-27 23:09:47 +05:00
redact.py fix(redact): stop masking prose words that embed a secret keyword (Secretary, tokenizer, author=) 2026-07-26 20:59:11 -07:00
replay_cleanup.py
…
retry_utils.py
…
runtime_cwd.py
…
secret_scope.py fix(secrets): scope BWS-injected provider keys 2026-07-22 04:39:17 -07:00
shell_hooks.py feat(delegate): expose redacted child tool history 2026-07-26 20:36:47 -07:00
skill_bundles.py
…
skill_commands.py fix(gateway): project a /skill turn onto its invocation for every client 2026-07-28 03:44:17 -05:00
skill_preprocessing.py fix: add explicit UTF-8 encoding to all subprocess text=True calls (#53428) 2026-07-24 11:45:57 -07:00
skill_utils.py fix(skills): parse stored GitHub credentials without scanner false positives 2026-07-26 20:59:26 -07:00
ssl_guard.py fix(ssl): detect and repair a missing certifi cacert.pem via existing venv-repair infra 2026-07-24 15:53:38 -07:00
ssl_verify.py
…
stream_diag.py
…
stream_single_writer.py
…
subagent_lifecycle.py fix(delegation): integrate lifecycle refactor with tool-history + daemon pool 2026-07-26 23:27:30 -07:00
subdirectory_hints.py
…
subscription_view.py feat(cli): plan catalog on Free + plan= deep link + top-up/auto-refill copy split (#68689) 2026-07-22 08:11:09 +05:30
system_prompt.py refactor(agent): share static-prefix reconstruction, memoize failed rebuilds 2026-07-28 01:10:05 +05:30
think_scrubber.py
…
thinking_timeout_guidance.py
…
thread_scoped_output.py
…
title_generator.py fix(sessions): stop titling a session after the skill it invoked 2026-07-26 02:58:16 -05:00
tool_dispatch_helpers.py
…
tool_executor.py Revert "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 22:28:08 -04:00
tool_guardrails.py refactor(guardrails): make runaway-loop caps per-turn, not session-total 2026-07-26 21:27:45 -07:00
tool_result_classification.py
…
trace_upload.py fix(windows): sweep remaining unguarded text-mode subprocess sites codebase-wide 2026-07-24 11:45:57 -07:00
trajectory.py
…
transcription_provider.py
…
transcription_registry.py
…
tts_provider.py
…
tts_registry.py
…
turn_context.py fix(agent): type a synthesized user turn when its row is written 2026-07-28 03:54:16 -05:00
turn_finalizer.py Revert "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 22:28:08 -04:00
turn_retry_state.py feat(agent): add active-turn redirect core primitive 2026-07-22 12:02:40 -05:00
turn_summary.py fix(cli): report unknown line deltas for content-free diffs instead of +0 -0 2026-07-26 17:47:51 -07:00
usage_pricing.py
…
verification_evidence.py fix(gateway,tools,agent): close leaked SQLite connections in delivery, delegation, and verification ledgers 2026-07-24 15:55:08 -07:00
verification_stop.py
…
verify_hooks.py
…
vertex_adapter.py
…
video_gen_provider.py
…
video_gen_registry.py
…
web_search_provider.py
…
web_search_registry.py
…