mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-11 08:42:11 +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 | ||
| secret_sources | ||
| transports | ||
| __init__.py | ||
| account_usage.py | ||
| agent_init.py | ||
| agent_runtime_helpers.py | ||
| anthropic_adapter.py | ||
| async_utils.py | ||
| auxiliary_client.py | ||
| azure_identity_adapter.py | ||
| background_review.py | ||
| bedrock_adapter.py | ||
| browser_provider.py | ||
| browser_registry.py | ||
| chat_completion_helpers.py | ||
| codex_responses_adapter.py | ||
| codex_runtime.py | ||
| coding_context.py | ||
| context_compressor.py | ||
| context_engine.py | ||
| context_references.py | ||
| conversation_compression.py | ||
| conversation_loop.py | ||
| copilot_acp_client.py | ||
| credential_persistence.py | ||
| credential_pool.py | ||
| credential_sources.py | ||
| credits_tracker.py | ||
| curator.py | ||
| curator_backup.py | ||
| display.py | ||
| error_classifier.py | ||
| file_safety.py | ||
| gemini_cloudcode_adapter.py | ||
| gemini_native_adapter.py | ||
| gemini_schema.py | ||
| google_code_assist.py | ||
| google_oauth.py | ||
| i18n.py | ||
| image_gen_provider.py | ||
| image_gen_registry.py | ||
| image_routing.py | ||
| insights.py | ||
| iteration_budget.py | ||
| jiter_preload.py | ||
| lmstudio_reasoning.py | ||
| manual_compression_feedback.py | ||
| markdown_tables.py | ||
| memory_manager.py | ||
| memory_provider.py | ||
| message_sanitization.py | ||
| model_metadata.py | ||
| models_dev.py | ||
| moonshot_schema.py | ||
| nous_rate_guard.py | ||
| onboarding.py | ||
| plugin_llm.py | ||
| portal_tags.py | ||
| process_bootstrap.py | ||
| prompt_builder.py | ||
| prompt_caching.py | ||
| rate_limit_tracker.py | ||
| redact.py | ||
| retry_utils.py | ||
| runtime_cwd.py | ||
| shell_hooks.py | ||
| skill_bundles.py | ||
| skill_commands.py | ||
| skill_preprocessing.py | ||
| skill_utils.py | ||
| stream_diag.py | ||
| subdirectory_hints.py | ||
| system_prompt.py | ||
| think_scrubber.py | ||
| title_generator.py | ||
| tool_dispatch_helpers.py | ||
| tool_executor.py | ||
| tool_guardrails.py | ||
| tool_result_classification.py | ||
| trajectory.py | ||
| transcription_provider.py | ||
| transcription_registry.py | ||
| tts_provider.py | ||
| tts_registry.py | ||
| turn_context.py | ||
| turn_finalizer.py | ||
| turn_retry_state.py | ||
| usage_pricing.py | ||
| video_gen_provider.py | ||
| video_gen_registry.py | ||
| web_search_provider.py | ||
| web_search_registry.py | ||