hermes-bsd/agent
Teknium e3236e99a4 fix(anthropic): API-key path skips OAuth autodiscovery + prunes stale entries
When the user picks 'Anthropic API key' at `hermes setup` (vs 'Claude
Pro/Max subscription'), `save_anthropic_api_key()` writes ANTHROPIC_API_KEY
to ~/.hermes/.env and zeros ANTHROPIC_TOKEN.  That env-var pattern is the
user's explicit choice of auth method — API key, not OAuth.

But the anthropic credential pool's autodiscovery (_seed_from_singletons)
unconditionally read ~/.claude/.credentials.json from the Claude Code CLI
and any saved hermes_pkce creds, and added them to the SAME anthropic
pool as the user's API key.  Two problems:

  1. Even with the API key at higher priority, a 401/429 on the API key
     would rotate the session onto an autodiscovered OAuth credential,
     silently flipping the agent into the Claude Code masquerade
     mid-conversation: 'You are Claude Code' system block, every tool
     renamed to mcp_*, claude-cli User-Agent header.

  2. Switching OAuth → API key at `hermes setup` cleared the env vars
     but left previously-seeded OAuth entries dormant in auth.json,
     where rotation could revive them.

The user picking the API-key path is explicitly opting OUT of the
masquerade.  Mixing OAuth credentials into their pool defeats that
choice.

Fix: in `_seed_from_singletons` for provider='anthropic', detect the
API-key path (ANTHROPIC_API_KEY set in env, no OAuth env var set) and:
  - Skip calling read_claude_code_credentials() and
    read_hermes_oauth_credentials() entirely
  - Prune any stale hermes_pkce / claude_code entries that may already
    be in the on-disk pool

OAuth-path users (ANTHROPIC_TOKEN set) are unaffected — autodiscovery
continues to fire as before.

Tests: 3 new regression tests (api-key skips autodiscovery, api-key
prunes stale entries, oauth path still autodiscovers).  Full file 70/70.
2026-05-25 17:41:40 -07:00
..
lsp chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
secret_sources perf(cli): cut hermes startup 63% — flip head-to-head vs codex (#31968) 2026-05-25 03:06:39 -07:00
transports fix(codex): size and propagate timeouts for Responses-API requests; lower stale defaults 2026-05-25 01:47:55 -07:00
__init__.py
account_usage.py
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(credential-pool): correct pool rotation when weekly usage limit is reached 2026-05-25 06:32:30 -07:00
anthropic_adapter.py fix(security): close TOCTOU window when saving Claude Code OAuth credentials (#21152) 2026-05-24 17:45:12 -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 fix(credential-pool): correct pool rotation when weekly usage limit is reached 2026-05-25 06:32:30 -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 fix(background-review): allow pinned skills to be improved 2026-05-23 22:57:42 -07:00
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(codex): add time-to-first-byte watchdog for stalled Codex streams 2026-05-25 05:34:42 -07:00
codex_responses_adapter.py fix(codex): size and propagate timeouts for Responses-API requests; lower stale defaults 2026-05-25 01:47:55 -07:00
codex_runtime.py fix(codex): add time-to-first-byte watchdog for stalled Codex streams 2026-05-25 05:34:42 -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
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(agent): log outer-loop exceptions at ERROR with traceback (#32264) 2026-05-25 15:16:54 -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_persistence.py fix: avoid persisting borrowed credential secrets (#31416) 2026-05-25 00:32:08 -07:00
credential_pool.py fix(anthropic): API-key path skips OAuth autodiscovery + prunes stale entries 2026-05-25 17:41:40 -07:00
credential_sources.py fix(model): include Premium+ in xAI OAuth label 2026-05-24 18:12:16 -07:00
curator.py
curator_backup.py fix(skills): prune dependency/venv dirs from all skill scanners (#30042) 2026-05-21 14:18:02 -07:00
display.py feat(cli): show todo progress as done/total fraction 2026-05-23 21:03:51 -07:00
error_classifier.py fix(error-classifier): treat 5xx request-validation errors as non-retryable 2026-05-24 15:15:37 -07:00
file_safety.py fix(security): block read_file on project-local .env files 2026-05-25 03:40:47 -07:00
gemini_cloudcode_adapter.py
gemini_native_adapter.py
gemini_schema.py
google_code_assist.py
google_oauth.py fix(security): guard os.chmod(parent) against / and top-level dirs 2026-05-20 22:56:55 -07:00
i18n.py
image_gen_provider.py fix(image_gen): cache xAI ephemeral URL responses to disk (#26942) (#31759) 2026-05-24 18:10:47 -07:00
image_gen_registry.py
image_routing.py fix(agent): consult supports_vision override in auto-mode routing 2026-05-20 23:27:10 -07:00
insights.py
iteration_budget.py refactor(run_agent): extract OpenAI proxy, safe stdio, IterationBudget 2026-05-16 17:59:32 -07:00
lmstudio_reasoning.py
manual_compression_feedback.py
markdown_tables.py
memory_manager.py 🐛 fix(memory): require newline after context tag 2026-05-18 10:53:08 -07:00
memory_provider.py
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 chore(models): drop retired grok-4-1-fast from metadata, tests, docs 2026-05-25 14:51:43 -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
onboarding.py
plugin_llm.py
portal_tags.py
process_bootstrap.py refactor(run_agent): extract OpenAI proxy, safe stdio, IterationBudget 2026-05-16 17:59:32 -07:00
prompt_builder.py feat(security): promptware defense — shared threat patterns + memory load-time scan + tool-result delimiters (#32269) 2026-05-25 14:52:24 -07:00
prompt_caching.py
rate_limit_tracker.py
redact.py fix(debug): redact BlueBubbles webhook secrets 2026-05-24 15:43:48 -07:00
retry_utils.py
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
system_prompt.py fix(profiles): cross-profile soft guard on file-write tools + system-prompt hint (#31290) 2026-05-24 00:38:17 -07:00
think_scrubber.py
title_generator.py
tool_dispatch_helpers.py feat(security): promptware defense — shared threat patterns + memory load-time scan + tool-result delimiters (#32269) 2026-05-25 14:52:24 -07:00
tool_executor.py fix(cli): surface tool failures with specific error messages 2026-05-23 21:03:51 -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
trajectory.py
transcription_provider.py feat(stt): add register_transcription_provider() plugin hook 2026-05-25 01:41:19 -07:00
transcription_registry.py feat(stt): add register_transcription_provider() plugin hook 2026-05-25 01:41:19 -07:00
tts_provider.py feat(tts): add register_tts_provider() plugin hook (closes #30398) 2026-05-24 18:04:54 -07:00
tts_registry.py feat(tts): add register_tts_provider() plugin hook (closes #30398) 2026-05-24 18:04:54 -07:00
usage_pricing.py
video_gen_provider.py
video_gen_registry.py
web_search_provider.py
web_search_registry.py