hermes-agent/agent
teknium1 fa4e87b253
fix(egress): v3 round — GodsBoy/stephenschoettler/arshkumarsingh findings
GodsBoy 2nd-round P1 (all 4 addressed):
- _detect_docker_bridge_ip: replace `ip.count('.') == 3` heuristic with
  ipaddress.IPv4Address validation + reject unspecified/loopback/multicast/
  reserved/link-local/global addresses.  Hostile `ip` shim on PATH used to
  be able to inject 0.0.0.0 here and re-open INADDR_ANY binding.
- cmd_setup credential_source preservation: re-running `hermes egress
  setup` without --from-bitwarden no longer silently downgrades a previous
  bitwarden config back to env.  Require --no-bitwarden to switch
  explicitly; otherwise preserve the existing mode and surface the
  decision.
- fail_on_uncovered_providers docstring/default mismatch: docstring used
  to claim default=True; behavior was default=False.  Resolved by
  truth-in-advertising — docstring now correctly states default=False —
  AND splitting providers into a strict LLM-specific tier
  (_LLM_SPECIFIC_NON_BEARER_PROVIDERS, used by start blocking) and a
  generic uncovered tier (used by wizard warnings).  Generic cloud creds
  (AWS_*, GOOGLE_APPLICATION_CREDENTIALS) no longer trip refuse-start
  for operators using terraform/gcloud alongside Hermes.  New
  discover_blocked_providers() returns the strict subset.
- start_proxy poll-loop must verify listening before pidfile:
  previously fell through deadline-expired as success and wrote a
  pidfile for a non-listening daemon.  Refactored into a do-while
  shape, require `listening=True` for success, kill the child + unlink
  the pidfile on failure paths.

GodsBoy 2nd-round P2 (the worth-keeping subset):
- O_NOFOLLOW + 0o600 + st_uid check on iron-proxy.log open (symmetric
  with the pidfile and audit-log paths the same PR hardens).
- pidfile O_EXCL: refactored pidfile-write into _write_pidfile_safely
  which uses O_EXCL to detect concurrent starts.  EEXIST with a live
  pid means "another start in progress" — refuse with actionable
  message; EEXIST with a dead pid means "stale crash" — unlink and
  retry once.  Discriminates rather than racing.
- _VERSION_CACHE: invalidate on install_iron_proxy success;
  don't cache empty stdout (would poison `hermes egress status` for
  the lifetime of the process if first probe hit a corrupt binary).
- ensure_audit_log now RAISES on OSError instead of swallowing it as
  a warning.  Previous behavior let the daemon create the file under
  the default umask, exactly the world-readable scenario the helper
  was built to prevent.  cmd_setup catches the new RuntimeError and
  surfaces "✗" with the actionable message.
- SIGINT/SIGTERM handler scoped around the start_proxy poll loop:
  Ctrl-C while waiting for `hermes egress start` no longer leaks an
  orphan daemon with the port bound.  Handler kills the child +
  unlinks the pidfile before re-raising.
- pidfile written IMMEDIATELY after Popen, BEFORE the listening
  verification.  Parent dying during the poll loop now leaves a
  pidfile pointing at the orphan so the next `hermes egress stop` can
  clean up.  Failure paths in the poll loop explicitly unlink.
- _DEFAULT_UPSTREAM_DENY_CIDRS: add ::ffff:0:0/96 (IPv4-mapped IPv6 —
  closes the v6-resolved IMDS bypass), 100.64.0.0/10 (CGNAT / cloud
  overlays / K8s pod networks), 198.18.0.0/15 (RFC2544 benchmark).
- _NON_BEARER_PROVIDERS split into LLM-specific (Anthropic / Azure /
  Gemini — block when strict) vs generic-cloud (AWS_*, GCP appdefault
  — warn-only).
- docker.py except narrowing: load_config can raise yaml.YAMLError on
  a malformed config.yaml, not just ImportError.  Two callsites
  (collision check + precedence resolution) now catch yaml.YAMLError
  via a sentinel `import yaml` and fail-safe to enforced mode.

GodsBoy 2nd-round P3:
- _reset_for_tests: was a no-op claiming symmetry with bitwarden;
  now actually clears _VERSION_CACHE and _proxy_nonce so in-process
  callers (notebooks, pytest -p no:xdist) don't see state leakage.
- tests/test_iron_proxy_cli.py: replaced hardcoded Path("/tmp/...")
  with hermes_home/-derived fixtures.  Matches the same cleanup we
  did for test_iron_proxy.py in the previous round.
- --rotate-tokens confirmation gate: when there are existing tokens,
  prompt for "rotate" confirmation (skipped when stdin isn't a tty
  so CI/scripted use still works) AND back up the mappings to a
  timestamped sibling before overwriting.  Surface a no-op note when
  rotate is requested with no existing tokens.

stephenschoettler (runtime-boundary review):
- #1 BWS silent degrade at proxy start: when credential_source=bitwarden
  but the BWS access token or project_id is missing OR the fetch
  returns no values for mapped providers, raise instead of silently
  falling back to host env.  cmd_start also pre-checks at the wizard
  layer for actionable error messages.  Opt-in escape hatch via new
  `proxy.allow_env_fallback: true` config for migration scenarios.
- #2 docker_env collision detection extended: `docker_env:
  {OPENROUTER_API_KEY: sk-real}` in config.yaml with enforce_on_docker:
  true now raises just like an HTTPS_PROXY collision would.  The
  collision check pulls mapped provider names from load_mappings() at
  call time.
- #3 PID nonce persisted to disk: cross-CLI-invocation stale-pidfile
  defense now works.  start_proxy writes the nonce next to the pidfile
  (sibling 0o600), stop_proxy reads it back via _read_persisted_nonce()
  and uses it as a _pid_alive signal in the new process.  Falls back
  to argv0 basename matching when the file is missing (legacy install).

arshkumarsingh:
- #1 NODE_OPTIONS append-merge: egress dict no longer sets NODE_OPTIONS
  directly (would clobber the operator's --max-old-space-size etc.).
  Carry the egress flag in a sentinel key
  _HERMES_EGRESS_NODE_OPTIONS_APPEND; DockerEnvironment merges into the
  existing NODE_OPTIONS in env_args computation with de-duplication.
- #2 docs: structured per-request audit log is at audit.log, not
  iron-proxy.log (the latter is daemon stdout/stderr).  Diagram and
  step-7 text corrected; both file roles are now documented separately.

Tests
- Added 12 new tests in test_iron_proxy.py covering bridge-IP rejection
  (parametrized over 8 dangerous inputs), default deny-list adjacency
  (IPv4-mapped-v6 + CGNAT), blocked-providers strict-subset property,
  _pid_proc_starttime parser with paren-containing comm,
  stop_proxy SIGKILL suppression on starttime drift, _reset_for_tests
  clear behavior, iron_proxy_version don't-cache-empty, NODE_OPTIONS
  sentinel verification, ensure_audit_log raise-on-OSError, and
  persisted-nonce roundtrip.
- Added 1 new test in test_iron_proxy_cli.py covering cmd_start
  BWS-token-missing fail-loud.
- All 100 tests in test_iron_proxy + test_iron_proxy_cli pass; all 78
  tests in test_docker_environment + test_config still pass.

Acknowledged but not addressed:
- GodsBoy P3 dead-code `extra_env` kwarg: kept (removing is a breaking
  change for any out-of-tree caller; the kwarg is documented and works).
- Residual risks GodsBoy called out: iron-proxy in-memory secret
  zeroisation (Go-binary territory, out of scope); _PROXY_SUBPROCESS_ENV
  _ALLOWLIST cosmetic gaps (RUST_LOG, GOMAXPROCS); follow-up.
2026-05-24 04:22:53 -07:00
..
lsp chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
proxy_sources fix(egress): v3 round — GodsBoy/stephenschoettler/arshkumarsingh findings 2026-05-24 04:22:53 -07:00
secret_sources feat(secrets): Bitwarden Secrets Manager integration with lazy bws install (#30035) 2026-05-21 14:10:34 -07:00
transports fix(xai): restore encrypted reasoning replay across turns 2026-05-20 23:12:45 -07:00
__init__.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
account_usage.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
agent_init.py fix(cli): synchronize HERMES_SESSION_ID across environment and contextvar during session switches 2026-05-23 17:46:55 -07:00
agent_runtime_helpers.py fix(compressor): propagate api_mode and fix root logger calls 2026-05-23 17:38:19 -07:00
anthropic_adapter.py refactor: extract 7 helpers from convert_messages_to_anthropic 2026-05-22 04:23:02 -07:00
async_utils.py fix(async): close unscheduled coroutines in all threadsafe bridges (#26584) 2026-05-15 14:00:01 -07:00
auxiliary_client.py feat(plugins): add register_auxiliary_task() to PluginContext API 2026-05-23 17:49:47 -07:00
azure_identity_adapter.py feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
background_review.py chore: trim verbose comments/docstrings, add AUTHOR_MAP entry 2026-05-21 12:49:21 +05:30
bedrock_adapter.py chore(deps): lazy-install boto3/botocore for bedrock adapter 2026-05-17 02:31:18 -07:00
browser_provider.py fix(browser): self-review pass — dead-import, log levels, future-proofing 2026-05-17 04:04:15 -07:00
browser_registry.py fix(browser): self-review pass — dead-import, log levels, future-proofing 2026-05-17 04:04:15 -07:00
chat_completion_helpers.py fix(compressor): propagate api_mode and fix root logger calls 2026-05-23 17:38:19 -07:00
codex_responses_adapter.py fix(xai): restore encrypted reasoning replay across turns 2026-05-20 23:12:45 -07:00
codex_runtime.py fix(xai): surface provider 'error' SSE frame in Codex fallback stream (#27184) 2026-05-16 23:41:09 -07:00
context_compressor.py fix(compressor): ABC compliance — total_tokens, api_mode, logger consistency 2026-05-23 17:38:19 -07:00
context_engine.py fix(compressor): ABC compliance — total_tokens, api_mode, logger consistency 2026-05-23 17:38:19 -07:00
context_references.py fix(agent): fall back when rg is blocked for @folder references 2026-04-20 01:56:41 -07:00
conversation_compression.py fix(cli): synchronize HERMES_SESSION_ID across environment and contextvar during session switches 2026-05-23 17:46:55 -07:00
conversation_loop.py fix(compressor): propagate api_mode and fix root logger calls 2026-05-23 17:38:19 -07:00
copilot_acp_client.py fix: guard yaml.safe_load, flock unlock, TOCTOU races, and atomic writes 2026-05-19 00:12:41 -07:00
credential_pool.py fix(codex-oauth): quarantine terminal refresh errors so dead tokens are not replayed across sessions 2026-05-18 10:31:40 -07:00
credential_sources.py feat(xai-oauth): add xAI Grok OAuth (SuperGrok Subscription) provider 2026-05-15 12:11:32 -07:00
curator.py feat(curator): hint at hermes curator pin in the rename block (#23212) 2026-05-10 06:44:53 -07:00
curator_backup.py fix(skills): prune dependency/venv dirs from all skill scanners (#30042) 2026-05-21 14:18:02 -07:00
display.py chore: remove Atropos RL environments and tinker-atropos integration (#26106) 2026-05-15 10:36:38 +05:30
error_classifier.py fix(agent): recover from providers rejecting list-type tool content (#27344) (#30259) 2026-05-21 23:40:16 -07:00
file_safety.py fix(file-safety): widen read-deny to .env, mcp-tokens/, webhook secrets, root 2026-05-22 20:15:09 -07:00
gemini_cloudcode_adapter.py fix(agent/gemini-cloudcode): seed delta defaults for reasoning-only stream chunks 2026-05-14 08:03:56 -07:00
gemini_native_adapter.py fix(auxiliary): evict async wrappers on poisoned client (follow-up to #23482) 2026-05-11 11:13:20 -07:00
gemini_schema.py chore: remove unused imports and dead locals (ruff F401, F841) (#17010) 2026-04-28 06:46:45 -07:00
google_code_assist.py chore: remove unused imports and dead locals (ruff F401, F841) (#17010) 2026-04-28 06:46:45 -07:00
google_oauth.py fix(security): guard os.chmod(parent) against / and top-level dirs 2026-05-20 22:56:55 -07:00
i18n.py feat(i18n): localize all gateway commands + web dashboard, add 8 new locales (16 total) (#22914) 2026-05-10 07:14:14 -07:00
image_gen_provider.py feat(plugins): pluggable image_gen backends + OpenAI provider (#13799) 2026-04-21 21:30:10 -07:00
image_gen_registry.py fix(plugins): filter resolution by is_available() in web + image_gen registries 2026-05-13 22:31:28 -07:00
image_routing.py fix(agent): consult supports_vision override in auto-mode routing 2026-05-20 23:27:10 -07:00
insights.py Merge branch 'main' into feat/dashboard-skill-analytics 2026-04-20 05:25:49 -07:00
iteration_budget.py refactor(run_agent): extract OpenAI proxy, safe stdio, IterationBudget 2026-05-16 17:59:32 -07:00
lmstudio_reasoning.py feat(agent): add lmstudio integration 2026-04-28 12:27:36 -07:00
manual_compression_feedback.py fix(compression): include system prompt + tool schemas in token estimates (#18265) 2026-04-30 23:03:54 -07:00
markdown_tables.py fix(cli): vertical fallback for markdown tables wider than terminal (#23948) 2026-05-11 16:49:13 -07:00
memory_manager.py 🐛 fix(memory): require newline after context tag 2026-05-18 10:53:08 -07:00
memory_provider.py docs(agent): remove stale BuiltinMemoryProvider references from memory module docstrings 2026-05-05 13:33:49 -07:00
message_sanitization.py refactor(run_agent): extract message sanitization to agent/message_sanitization.py 2026-05-16 17:41:09 -07:00
model_metadata.py fix(compressor): propagate api_mode and fix root logger calls 2026-05-23 17:38:19 -07:00
models_dev.py fix(xai): resolve Grok Build context for OAuth 2026-05-22 13:05:36 -07:00
moonshot_schema.py fix(moonshot): strip $ref siblings and collapse tuple items in tool schemas (#27104) 2026-05-16 13:02:19 -07:00
nous_rate_guard.py codebase: add encoding='utf-8' to all bare open() calls (PLW1514) 2026-05-08 14:27:40 -07:00
onboarding.py docs(onboarding): lead OpenClaw residue banner with migrate, warn that cleanup breaks OpenClaw (#17507) 2026-04-29 08:08:36 -07:00
plugin_llm.py feat(plugins): run any LLM call from inside a plugin via ctx.llm (#23194) 2026-05-10 07:09:28 -07:00
portal_tags.py feat(nous): unified client=hermes-client-v<version> tag on every Portal request (#24779) 2026-05-12 20:49:20 -07:00
process_bootstrap.py refactor(run_agent): extract OpenAI proxy, safe stdio, IterationBudget 2026-05-16 17:59:32 -07:00
prompt_builder.py refactor(ntfy): convert built-in adapter to platform plugin 2026-05-23 16:13:01 -07:00
prompt_caching.py fix(cache): kill long-lived prefix layout — system prompt is now byte-static within a session (#24778) 2026-05-12 20:46:04 -07:00
rate_limit_tracker.py refactor: remove dead code — 1,784 lines across 77 files (#9180) 2026-04-13 16:32:04 -07:00
redact.py perf(agent-loop): cut 47% of per-conversation function calls via 3 targeted hot-path optimizations (#28866) 2026-05-19 14:25:10 -07:00
retry_utils.py feat(agent): add jittered retry backoff 2026-04-08 00:41:36 -07:00
shell_hooks.py fix: guard yaml.safe_load, flock unlock, TOCTOU races, and atomic writes 2026-05-19 00:12:41 -07:00
skill_bundles.py feat(skills): add skill bundles — alias /<name> loads multiple skills (#28373) 2026-05-18 21:38:05 -07:00
skill_commands.py fix(skills): load symlinked skill slash commands 2026-05-18 00:34:29 -07:00
skill_preprocessing.py fix: treat inline-shell timeout guard as timeout 2026-05-18 19:36:04 -07:00
skill_utils.py fix(skills): load Linux-tagged skills on Termux (android sys.platform) 2026-05-21 19:08:38 -07:00
stream_diag.py refactor(run_agent): extract stream diagnostics to agent/stream_diag.py 2026-05-16 18:28:17 -07:00
subdirectory_hints.py fix(agent): catch PermissionError in subdirectory hint discovery 2026-04-09 03:10:30 -07:00
system_prompt.py perf(prompt): cache kanban worker guidance at session init 2026-05-18 20:56:44 -07:00
think_scrubber.py fix(agent): stateful streaming scrubber for reasoning-block leaks (#17924) (#20184) 2026-05-05 04:33:38 -07:00
title_generator.py fix: improve telegram topic mode setup 2026-05-04 12:07:17 -07:00
tool_dispatch_helpers.py fix(agent): set tool_name on tool-result messages at construction time 2026-05-19 20:49:11 +01:00
tool_executor.py fix(compressor): propagate api_mode and fix root logger calls 2026-05-23 17:38:19 -07:00
tool_guardrails.py fix: add recovery hints to loop guard warnings 2026-05-19 00:12:12 -07:00
tool_result_classification.py fix: classify landed file mutations with diagnostics 2026-05-13 06:46:23 -07:00
trajectory.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
usage_pricing.py fix(pricing): add deepseek-v4-pro to official docs pricing table 2026-05-12 16:32:57 -07:00
video_gen_provider.py feat(video_gen): unified video_generate tool with pluggable provider backends (#25126) 2026-05-13 16:39:41 -07:00
video_gen_registry.py feat(video_gen): unified video_generate tool with pluggable provider backends (#25126) 2026-05-13 16:39:41 -07:00
web_search_provider.py fix(web): align _LEGACY_PREFERENCE with legacy 7-provider order + doc cleanup 2026-05-13 22:31:28 -07:00
web_search_registry.py fix(web): align _LEGACY_PREFERENCE with legacy 7-provider order + doc cleanup 2026-05-13 22:31:28 -07:00