mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-26 17:38:36 +00:00
3e74f75e41
* feat(agent): coding-context posture with per-model edit-format tuning Hermes detects when it's running in a coding context — an interactive surface (CLI, TUI, ACP, desktop) sitting in a code workspace (git repo or recognised project root) — and shifts into a coding posture. Outside that (chat platforms, non-workspaces) nothing changes. The posture is modelled as a frozen RuntimeMode selected from a small ContextProfile registry (coding/general). A profile is data: the toolset to collapse to, the operating brief to inject, and seams for model routing and memory. Every domain reads the same resolved object instead of re-probing git/config on its own: - System prompt — RuntimeMode.system_blocks(): an operating brief (gather context before editing, edit through tools not chat, verify with terminal, cap retry loops) plus a live git/workspace snapshot, built once and baked into the stable prompt tier so per-conversation caching is preserved. - Per-model edit-format tuning — the brief nudges each model family toward the patch mode it handles best: OpenAI/Codex toward mode='patch' (V4A multi-file diffs), Anthropic toward mode='replace' (string replacement). The model id rides on RuntimeMode; unknown families keep neutral wording. - Skill index — non-coding skill categories are pruned from the prompt's skill index (discovery-only; skills_list/skill_view still reach the full catalog, with a disclosure note). - Toolset — only under the opt-in 'focus' mode does the posture collapse to the coding toolset + enabled MCP servers; the default posture is prompt-only and never overrides configured toolsets. Activation via agent.coding_context: auto (default), focus, on, off. Subagents inherit the posture for free via toolset inheritance + the shared prompt builder. Detection is not memoized so a long-lived gateway/TUI process can't pin a stale posture across working directories. * feat(agent): cover new-file authoring in the coding edit-format nudge The per-model edit-format guidance only addressed editing existing code (patch mode='patch' vs 'replace'), but authoring a brand-new file — write_file, not patch — is a large fraction of real coding work and the nudge was silent on it. Surfaced when building a single-file artifact where the dominant operation was write_file and the steering offered no guidance. Both family lines now lead with "author new files with write_file; for edits to existing code prefer ...". Tests assert write_file appears in each family's brief; unknown families still get neutral wording. * docs(agent): correct memoization docstring + clarify TUI config-load asymmetry * feat(agent): sharpen the coding posture — verify-loop facts, wider edit steering, $HOME guard Tuning pass on the coding posture from dogfooding it as a harness: - Workspace snapshot now hands the model its verify loop up front: detected manifests + package manager (lockfile sniff), the exact verify commands (package.json scripts, Makefile targets, scripts/run_tests.sh, pytest config), and which context files (AGENTS.md / CLAUDE.md / .cursorrules) exist at the root. Marker-only (non-git) projects get the snapshot too instead of nothing. The "verify before claiming done" brief line was the highest-value piece in evals — this turns it from advice into an executable loop instead of making the model rediscover the test command every session. Still stat-cheap, size-guarded reads, built once at prompt time. - Edit-format steering covers the families Hermes actually serves: Gemini and open-weight coding models (DeepSeek, Qwen, Kimi, GLM, Grok, Hermes, Llama, Mistral, Devstral, MiniMax) steer to mode='replace' — their RL scaffolds use str_replace-style editors. Previously only GPT/Codex and Claude families got steering; the models Hermes users disproportionately run all fell to neutral. - Operating brief gains four behaviors elite harnesses encode: batch independent reads/searches in one turn; fix root causes and the bug class (sibling call paths), not the reported site; no drive-by refactors/renames/reformatting; never read, print, or commit secrets. Plus a patch-failure escalation ladder: after the same region fails twice, rewrite the enclosing function/file with write_file instead of a third patch attempt. - $HOME dotfiles guard: a git repo rooted exactly at the home directory (or a marker sitting in it, e.g. a global ~/AGENTS.md) is user config, not a code workspace — without the guard, every session anywhere under a dotfiles-managed home silently flipped to the coding posture. Real projects under such a home still detect via their own markers/repos; 'on' mode bypasses the guard. |
||
|---|---|---|
| .. | ||
| lsp | ||
| transports | ||
| __init__.py | ||
| test_anthropic_adapter.py | ||
| test_anthropic_keychain.py | ||
| test_anthropic_kwargs_sanitize.py | ||
| test_anthropic_mcp_prefix_strip.py | ||
| test_anthropic_oauth_pkce.py | ||
| test_anthropic_output_field_leak.py | ||
| test_anthropic_thinking_block_order.py | ||
| test_arcee_trinity_overrides.py | ||
| test_async_utils.py | ||
| test_auxiliary_client.py | ||
| test_auxiliary_client_anthropic_custom.py | ||
| test_auxiliary_client_azure_foundry.py | ||
| test_auxiliary_client_xai_oauth_recovery.py | ||
| test_auxiliary_config_bridge.py | ||
| test_auxiliary_main_first.py | ||
| test_auxiliary_named_custom_providers.py | ||
| test_auxiliary_transport_autodetect.py | ||
| test_auxiliary_user_default_headers.py | ||
| test_azure_identity_adapter.py | ||
| test_bedrock_1m_context.py | ||
| test_bedrock_adapter.py | ||
| test_bedrock_integration.py | ||
| test_cascading_interrupt_6600.py | ||
| test_codex_cloudflare_headers.py | ||
| test_codex_responses_adapter.py | ||
| test_codex_ttfb_watchdog.py | ||
| test_coding_context.py | ||
| test_compress_focus.py | ||
| test_compression_concurrent_fork.py | ||
| test_compression_logging_session_context.py | ||
| test_compressor_historical_media.py | ||
| test_compressor_image_tokens.py | ||
| test_context_compressor.py | ||
| test_context_compressor_cross_session_guard.py | ||
| test_context_compressor_summary_continuity.py | ||
| test_context_compressor_temporal_anchoring.py | ||
| test_context_engine.py | ||
| test_context_engine_host_contract.py | ||
| test_context_references.py | ||
| test_copilot_acp_client.py | ||
| test_copilot_acp_deprecation.py | ||
| test_credential_pool.py | ||
| test_credential_pool_routing.py | ||
| test_credits_cold_start.py | ||
| test_credits_fixture_snapshot.py | ||
| test_credits_policy.py | ||
| test_credits_tracker.py | ||
| test_crossloop_client_cache.py | ||
| test_curator.py | ||
| test_curator_activity.py | ||
| test_curator_backup.py | ||
| test_curator_classification.py | ||
| test_curator_reports.py | ||
| test_custom_provider_extra_body.py | ||
| test_custom_providers_vision.py | ||
| test_deepseek_anthropic_thinking.py | ||
| test_direct_provider_url_detection.py | ||
| test_display.py | ||
| test_display_emoji.py | ||
| test_display_todo_progress.py | ||
| test_display_tool_failure.py | ||
| test_error_classifier.py | ||
| test_external_skills.py | ||
| test_external_skills_dirs_cache.py | ||
| test_file_safety.py | ||
| test_file_safety_container_mirror.py | ||
| test_file_safety_credentials.py | ||
| test_file_safety_cross_profile.py | ||
| test_file_safety_sandbox_mirror.py | ||
| test_gemini_cloudcode.py | ||
| test_gemini_fast_fallback.py | ||
| test_gemini_free_tier_gate.py | ||
| test_gemini_native_adapter.py | ||
| test_gemini_schema.py | ||
| test_i18n.py | ||
| test_image_gen_registry.py | ||
| test_image_routing.py | ||
| test_insights.py | ||
| test_jiter_preload.py | ||
| test_kimi_coding_anthropic_thinking.py | ||
| test_last_total_tokens.py | ||
| test_local_stream_timeout.py | ||
| test_markdown_tables.py | ||
| test_memory_async_sync.py | ||
| test_memory_provider.py | ||
| test_memory_session_switch.py | ||
| test_memory_user_id.py | ||
| test_minimax_auxiliary_url.py | ||
| test_minimax_provider.py | ||
| test_model_metadata.py | ||
| test_model_metadata_local_ctx.py | ||
| test_model_metadata_ssl.py | ||
| test_models_dev.py | ||
| test_moonshot_schema.py | ||
| test_non_stream_stale_timeout.py | ||
| test_nous_credits_gauge.py | ||
| test_nous_credits_snapshot.py | ||
| test_nous_oauth_401_guidance.py | ||
| test_nous_rate_guard.py | ||
| test_onboarding.py | ||
| test_openrouter_response_cache.py | ||
| test_plugin_llm.py | ||
| test_portal_tags.py | ||
| test_prompt_builder.py | ||
| test_prompt_caching.py | ||
| test_proxy_and_url_validation.py | ||
| test_rate_limit_tracker.py | ||
| test_redact.py | ||
| test_resume_stale_active_task.py | ||
| test_runtime_cwd.py | ||
| test_save_url_image.py | ||
| test_set_runtime_main_custom_provider.py | ||
| test_shell_hooks.py | ||
| test_shell_hooks_consent.py | ||
| test_skill_bundles.py | ||
| test_skill_commands.py | ||
| test_skill_commands_reload.py | ||
| test_skill_utils.py | ||
| test_stream_read_timeout_floor.py | ||
| test_streaming_context_scrubber.py | ||
| test_subagent_progress.py | ||
| test_subagent_stop_hook.py | ||
| test_subdirectory_hints.py | ||
| test_summary_prefix_semantics.py | ||
| test_system_prompt.py | ||
| test_system_prompt_restore.py | ||
| test_think_scrubber.py | ||
| test_title_generator.py | ||
| test_tool_dispatch_helpers.py | ||
| test_tool_guardrails.py | ||
| test_tool_result_classification.py | ||
| test_transcription_registry.py | ||
| test_tts_registry.py | ||
| test_turn_context.py | ||
| test_turn_retry_state.py | ||
| test_unsupported_parameter_retry.py | ||
| test_unsupported_temperature_retry.py | ||
| test_usage_pricing.py | ||
| test_video_gen_registry.py | ||
| test_vision_resolved_args.py | ||
| test_vision_routing_31179.py | ||