agent · hermes-agent · Tangled

The agent that grows with you

hermes-agent agent

1 folder · 42 files

at sid/fix-platform-tool-loading

Teknium · fix(errors): classify OpenRouter privacy-guardrail 404s distinctly (#14943) · 6mo ago

fix(kimi,mcp): Moonshot schema sanitizer + MCP schema robustness (#14805)

Refactor Terminal and AIAgent cleanup

account_usage.py

feat(account-usage): add per-provider account limits module

anthropic_adapter.py

refactor: remove _nr_to_assistant_message shim + fix flush_memories guard

auxiliary_client.py

fix(agent): clarify exhausted OpenRouter auxiliary credentials

bedrock_adapter.py

feat: native AWS Bedrock provider via Converse API

codex_responses_adapter.py

refactor: extract codex_responses logic into dedicated adapter

context_compressor.py

fix: pass correct arguments in summary model fallback retry

context_engine.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

context_references.py

fix(agent): fall back when rg is blocked for @folder references

copilot_acp_client.py

fix(security): apply file safety to copilot acp fs

credential_pool.py

fix(auth): unify credential source removal — every source sticks (#13427)

credential_sources.py

fix(auth): unify credential source removal — every source sticks (#13427)

fix(display): render <missing old_text> in memory previews instead of empty quotes (#12852)

error_classifier.py

fix(errors): classify OpenRouter privacy-guardrail 404s distinctly (#14943)

fix(security): apply file safety to copilot acp fs

gemini_cloudcode_adapter.py

refactor: remove redundant local imports already available at module level

gemini_native_adapter.py

refactor: remove redundant local imports already available at module level

gemini_schema.py

fix(gemini): sanitize tool schemas for Google providers

google_code_assist.py

fix(gemini-cli): surface MODEL_CAPACITY_EXHAUSTED cleanly + drop retired gemma-4-26b (#11833)

google_oauth.py

feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270)

image_gen_provider.py

feat(plugins): pluggable image_gen backends + OpenAI provider (#13799)

image_gen_registry.py

feat(plugins): pluggable image_gen backends + OpenAI provider (#13799)

Merge branch 'main' into feat/dashboard-skill-analytics

manual_compression_feedback.py

fix(gateway): make manual compression feedback truthful

memory_manager.py

feat(honcho): context injection overhaul, 5-tool surface, cost safety, session isolation (#10619)

memory_provider.py

refactor(memory): drop on_session_reset — commit-only is enough

model_metadata.py

fix(context): resolve real Codex OAuth context windows (272k, not 1M) (#14935)

fix: normalize provider in list_provider_models to support aliases

moonshot_schema.py

fix(kimi,mcp): Moonshot schema sanitizer + MCP schema robustness (#14805)

nous_rate_guard.py

fix: Nous Portal rate limit guard — prevent retry amplification (#10568)

prompt_builder.py

feat(agent): add PLATFORM_HINTS for matrix, mattermost, and feishu (#14428)

prompt_caching.py

fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter

rate_limit_tracker.py

refactor: remove dead code — 1,784 lines across 77 files (#9180)

feat: replace kimi-k2.5 with kimi-k2.6 on OpenRouter and Nous Portal (#13148)

feat(agent): add jittered retry backoff

feat: shell hooks — wire shell scripts as Hermes hook callbacks

skill_commands.py

fix(skills): follow symlinked category dirs consistently

fix(skills): follow symlinks in iter_skill_index_files

subdirectory_hints.py

fix(agent): catch PermissionError in subdirectory hint discovery

title_generator.py

fix: increase max_tokens for GLM 5.1 reasoning headroom

Refactor Terminal and AIAgent cleanup

usage_pricing.py

fix(usage): read top-level Anthropic cache fields from OAI-compatible proxies