Moonsong 4e66bf1f80 fix(auxiliary): gate Anthropic base_url override on Anthropic-compatible host (#52608) ... When operator config has provider=anthropic with model.base_url pointing at a non-Anthropic host (e.g. https://openrouter.ai/api/v1 with provider=anthropic), the auxiliary Anthropic path was unconditionally applying that override. Main-session traffic routed correctly because the main path attaches the right credential for the actual destination, but every side-channel call (memory extractors, reflection, vision, title generation, janus extractor/promise) sent ANTHROPIC_API_KEY to the foreign host and 401'd. Gate the override on hostname == api.anthropic.com. Operators routing main through a non-Anthropic provider must use that provider's own auxiliary client; the Anthropic aux path now stays pointed at api.anthropic.com. Regression tests cover openrouter, openai, anthropic-with-path, empty, and anthropic-default-base_url cases.		2026-06-26 11:21:05 +05:30
..
lsp
pet	feat(pets): quality-first OpenRouter model chain + stronger atlas gates + global pet-gen notifications	2026-06-24 23:11:21 -05:00
secret_sources
transports	fix(cache): content-address prompt_cache_key so recurring cron jobs reuse the warm prefix (#52295)	2026-06-24 21:46:30 -07:00
__init__.py
account_usage.py
agent_init.py	feat(moa): expose MoA presets as selectable virtual models (#46081)	2026-06-25 13:52:06 -07:00
agent_runtime_helpers.py	fix(hermes_state): persist billing provider/base_url after mid-session /model switch	2026-06-25 14:44:00 -07:00
anthropic_adapter.py	fix(anthropic): use platform.claude.com for OAuth token exchange	2026-06-23 23:59:40 -07:00
async_utils.py
auxiliary_client.py	fix(auxiliary): gate Anthropic base_url override on Anthropic-compatible host (#52608)	2026-06-26 11:21:05 +05:30
azure_identity_adapter.py
background_review.py	feat(background-review): aux-model selector for the self-improvement review (#49252)	2026-06-22 14:54:53 -07:00
bedrock_adapter.py
billing_view.py
browser_provider.py
browser_registry.py
chat_completion_helpers.py	feat(agent): apply per-reasoning-model stale-timeout floor in stream + non-stream detectors	2026-06-25 22:12:06 -07:00
codex_responses_adapter.py
codex_runtime.py	fix(codex): seed app-server sessions with configured cwd	2026-06-21 16:39:02 -07:00
coding_context.py	fix(agent): require code for coding posture	2026-06-25 16:40:27 -05:00
context_compressor.py	fix(compression): abort (preserve context) on transient network summary failure (#29559, #25585)	2026-06-24 18:31:51 +05:30
context_engine.py
context_references.py
conversation_compression.py	fix(auxiliary): honor fallback chain when compression provider auth is unavailable	2026-06-25 13:08:18 -07:00
conversation_loop.py	fix(interrupt): keep partial streamed reply when stopped mid-response	2026-06-25 23:54:20 -05:00
copilot_acp_client.py
credential_persistence.py
credential_pool.py	fix(auth): write rotated Codex/xAI pool grant through to global root (#48415) (#52760)	2026-06-25 19:14:06 -07:00
credential_sources.py
credits_tracker.py
curator.py	fix(curator): make external-skill write guard actually fire during curation	2026-06-25 22:03:02 -07:00
curator_backup.py
display.py	fix(browser): force secret-pattern redaction on browser_type display	2026-06-25 22:02:22 -07:00
error_classifier.py	fix(agent): detect thinking-timeout for reasoning models and surface actionable guidance instead of misleading file-write advice	2026-06-25 19:00:48 -07:00
errors.py
file_safety.py
gemini_native_adapter.py
gemini_schema.py
i18n.py
image_gen_provider.py
image_gen_registry.py
image_routing.py
insights.py
iteration_budget.py
jiter_preload.py
learn_prompt.py	fix(learn): name distilled skills as author Hermes, not the host OS user (#52388)	2026-06-25 12:48:08 -07:00
lmstudio_reasoning.py
manual_compression_feedback.py
markdown_tables.py
memory_manager.py	fix(agent): validate context/memory tool schemas before wrapping	2026-06-25 02:17:29 +05:30
memory_provider.py	fix(backup): capture memory-provider state stored outside HERMES_HOME (#50325)	2026-06-21 12:03:46 -07:00
message_content.py
message_sanitization.py	fix(agent): close tool-call sequence on all interrupt aborts, not just finalize_turn	2026-06-25 12:24:34 -05:00
moa_loop.py	feat(moa): expose MoA presets as selectable virtual models (#46081)	2026-06-25 13:52:06 -07:00
model_metadata.py
models_dev.py
moonshot_schema.py
nous_rate_guard.py
onboarding.py
oneshot.py	feat(agent): one-shot LLM helper + llm.oneshot gateway RPC (#51261)	2026-06-23 08:01:50 +00:00
plugin_llm.py
portal_tags.py
process_bootstrap.py
prompt_builder.py	feat(tools): add project workspace tools	2026-06-25 16:40:27 -05:00
prompt_caching.py
rate_limit_tracker.py
reasoning_timeouts.py	fix(agent): detect thinking-timeout for reasoning models and surface actionable guidance instead of misleading file-write advice	2026-06-25 19:00:48 -07:00
redact.py	fix(redact): mask all Authorization schemes and x-api-key style headers	2026-06-21 14:08:06 -07:00
retry_utils.py	fix: handle named custom providers and Z.AI overload retries	2026-06-25 00:17:17 -07:00
runtime_cwd.py
secret_scope.py
shell_hooks.py
skill_bundles.py
skill_commands.py
skill_preprocessing.py
skill_utils.py	fix(curator): protect external skills from background curation	2026-06-25 22:03:02 -07:00
ssl_guard.py
stream_diag.py
subdirectory_hints.py
system_prompt.py	feat(computer_use): cross-platform cua-driver (macOS/Windows/Linux)	2026-06-22 06:42:30 -07:00
think_scrubber.py
thinking_timeout_guidance.py	fix(agent): detect thinking-timeout for reasoning models and surface actionable guidance instead of misleading file-write advice	2026-06-25 19:00:48 -07:00
title_generator.py
tool_dispatch_helpers.py	feat(agent): require verification before finishing edits	2026-06-24 23:02:48 -05:00
tool_executor.py	fix: redact browser typed text surfaces	2026-06-25 22:02:22 -07:00
tool_guardrails.py
tool_result_classification.py
trajectory.py
transcription_provider.py
transcription_registry.py
tts_provider.py
tts_registry.py
turn_context.py	fix: persist non-NULL system prompt on fresh turn setup (#45499) (#52616)	2026-06-25 12:54:19 -07:00
turn_finalizer.py	fix(agent): close tool-call sequence on all interrupt aborts, not just finalize_turn	2026-06-25 12:24:34 -05:00
turn_retry_state.py
usage_pricing.py	fix(bedrock): price Claude prompt-cache tokens in /usage (#50307)	2026-06-21 11:48:43 -07:00
verification_evidence.py	feat(agent): recognize focused ad-hoc verification scripts	2026-06-24 23:03:45 -05:00
verification_stop.py	feat(agent): recognize focused ad-hoc verification scripts	2026-06-24 23:03:45 -05:00
video_gen_provider.py
video_gen_registry.py
web_search_provider.py
web_search_registry.py