Rl capabilities && File Operator Tools by teknium1 · Pull Request #15 · NousResearch/hermes-agent

teknium1 · 2026-02-05T11:50:35Z

Initial RL training toolset and complete file operations toolset (to make it operate much more like a coding agent)

- Updated `.env.example` to include Tinker and WandB API keys for reinforcement learning training. - Enhanced `model_tools.py` to clarify configuration options and streamline the RL training process. - Expanded `README.md` with detailed instructions for setting up RL training using Tinker and WandB. - Modified `hermes_cli` files to integrate RL training tools and ensure proper configuration checks. - Improved `rl_training_tool.py` to reflect changes in training parameters and configuration management.

- Added the tinker-atropos submodule for enhanced RL training capabilities. - Updated model_tools.py to reorder RL function definitions and improve descriptions. - Modified rl_cli.py to include checks for the tinker-atropos setup and provide user guidance. - Adjusted toolsets.py and __init__.py to reflect changes in RL function availability. - Enhanced rl_training_tool.py to manage training processes directly without a separate API server.

- Modified `model_tools.py` to update default model IDs and add new RL function `rl_test_inference`. - Enhanced `README.md` with installation instructions for submodules and updated API key usage. - Improved `rl_cli.py` to load configuration from `~/.hermes/config.yaml` and set terminal working directory for RL tools. - Updated `run_agent.py` to handle empty string arguments as empty objects for better JSON validation. - Refined installation scripts to ensure submodules are cloned and installed correctly, enhancing setup experience.

… streaming - Added unique run ID generation for WandB tracking during test inference. - Enabled WandB usage for test tracking and updated command-line arguments accordingly. - Implemented real-time output streaming for process execution, improving log visibility and debugging. - Enhanced error handling to display last few lines of stderr for better troubleshooting.

- Introduced file manipulation capabilities in `model_tools.py`, including functions for reading, writing, patching, and searching files. - Added a new `file` toolset in `toolsets.py` and updated distributions to include file tools. - Enhanced `setup-hermes.sh` and `install.sh` scripts to check for and optionally install `ripgrep` for faster file searching. - Implemented a new `file_operations.py` module to encapsulate file operations using shell commands. - Updated `doctor.py` and `install.ps1` to check for `ripgrep` and provide installation guidance if not found. - Added fuzzy matching and patch parsing capabilities to improve file manipulation accuracy and flexibility.

taeyun16 · 2026-03-30T16:13:14Z

🔍 자동 분석 결과

이슈 요약

리더보드 시스템 — 주간/월간/지역별 순위로 경쟁 유도 + 보상 제공

기술 구현 고려사항

백엔드 (Phoenix/Ash)

리더보드 스냅샷: weekly_leaderboards (period_start, period_end, category)
순위 계산: (Oban, 매주 월요일 00:00 KST)
- WeeklyVoteKing: 주간 투표 수 top 100
- MonthlyCollector: 월간 신규 고양이 수집 top 100
- StreakChampion: 연속 투표 최장 기간 top 100
- RegionalRank: PostGIS ST_DWithin로 지역 필터링
순위 변동 추적: leaderboard_changes (user_id, change_amount, direction)
보상 지급: period结束时 자동 + 배지 발송

iOS (SwiftUI)

리더보드 탭: (segmented: 주간/월간/지역)
순위 Cell: (rank, avatar, name, score, change delta)
내 순위 고정: sticky bottom bar — "내 순위: 15위 / 234명"
변경 알림: 순위 진입/변동 시 토스트 + 햅틱

우선순위 제안

Phase 1: 주간 투표왕 (가장 단순 — existing vote_count 활용)
Phase 2: 지역별 순위 (PostGIS regional 쿼리 의존)
Phase 3: 월간 수집왕 (고양이 도감 완료 후)
Phase 4: 연속 기록왕 (Streak 시스템 통합)

관련existing 코드

— 아직 없으면 Streak worker 패턴 참고
Regional ranking: PostGIS queries

🤖 HanNyang Auto Resolver

* fix: cross-platform terminal/browser support and build fixes - Use platform-aware default shell (zsh on macOS, bash on Linux/Windows) instead of hardcoding /bin/zsh everywhere - Mark Playwright packages as external in Vite to fix chromium-bidi bundle errors during dev - Copy pty-helper.py to dist/server/assets/ on build so production server can find it - Fix browser launch guard to check `context` instead of `browser` (which is always null with launchPersistentContext) - Exclude unused diagnostics.ts stub from route tree - Update README with Playwright install step and Extra section Co-Authored-By: Claude Opus 4.6 <[email protected]> * docs: add Ubuntu/Debian prerequisites for Tauri desktop build Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>

Previously hermes-api.ts helper functions (hermesGet, hermesPost, hermesPatch, hermesDeleteReq, streamChat) sent no Authorization header, causing 401 'Invalid API key' errors when the gateway has API_SERVER_KEY configured. Also exports BEARER_TOKEN from gateway-capabilities.ts so hermes-api.ts can import and reuse it for auth headers. Co-authored-by: mgnyc11 <[email protected]>

zhangtobybot-a11y · 2026-04-11T11:11:20Z

已合并到 PR #45

zhangtobybot-a11y · 2026-04-11T11:11:24Z

已合并到 PR #45

…ameter + schema property' (NousResearch#15) from fix/terminal-notify-on-complete into main

Rl capabilities && File Operator Tools

Fixes 12 remaining MEDIUM issues from the deep audit (19 total, 7 fixed in Round 12): design_agent: - NousResearch#15: add asyncio.wait_for(300s) around LLM API call to prevent infinite hangs - NousResearch#17: replace 2x hardcoded 'claude-opus-4-8' with shared DEFAULT_MODEL constant qa_agent / validate_agent: - NousResearch#20,NousResearch#22,NousResearch#23: already fixed in Round 12 (verified — dynamic timeout/threshold values used) memory.py: - NousResearch#24: frontmatter parser uses regex r'^---$' instead of str.split('---',2), preventing false splits on content containing '---' (SQL, markdown tables) - NousResearch#25: parse and preserve 'description' field from frontmatter in metadata, fixing write→load roundtrip data loss profiles.py: - NousResearch#26: ProfileConfig now frozen=True (immutable dataclass per coding standards) deploy_agent: - NousResearch#31: replace 2x sync subprocess.run with asyncio.create_subprocess_exec - fix 5x .decode() → .decode('utf-8', errors='replace') for Windows CJK safety - remove unused import subprocess db.py: - NousResearch#27: add class docstring explaining RLock + _unlocked pattern - NousResearch#28: FK constraints already in DDL (verified PRAGMA foreign_keys=ON active) - NousResearch#29: add _ensure_connection() with PRAGMA integrity_check(1) + auto-reconnect on 4 critical methods (create_task, get_task, claim_task, submit_result) - extract _create_connection() static method for reuse by reconnect Tests: 79 passed, 0 failed

…s.md

Three remaining findings from the code review. #12 — hermes_cli/superagent.py: _strip_fences only handled a SINGLE leading-and-trailing ``` envelope. Common model failure mode is 'Here is the plan you asked for:\\n```yaml\\nfanout: 2\\n ...\\n```\\nLet me know.' — the leading prose means stripped.startswith('```') is False so the function returned the whole text unchanged, then yaml.safe_load choked → exit 2. Fix: regex-based extraction with _FENCE_BLOCK_RE that pulls the YAML body out of fenced blocks even when there's prose on either side. Falls back to the simple-strip path for fence- only output (preserves existing behaviour). #13 — hermes_cli/web_server.py: /ready was BOTH side-effecting AND racy. (a) Called path.parent.mkdir(parents=True, exist_ok= True) on every probe — k8s polls every few seconds, so a read-only mount surfaced PermissionError every hit and a writeable mount got directories repeatedly recreated. (b) The .readiness_probe storage check used a shared filename; two concurrent k8s probes (liveness + readiness simultaneous) could race, one's unlink raising FileNotFoundError → false 'not_ready' on a healthy node. Fix: (a) audit_log probe just reports parent.exists(); never mutates. (b) storage probe uses a per-PID + per-call unique filename and tolerates FileNotFoundError on cleanup. #15 — hermes_cli/superagent.py + hermes_cli/orchestrate.py: parent AIAgent was constructed bare with model=... provider=... quiet_mode=True only — no api_key, no base_url, no api_mode, no credential_pool. delegate_task then pulled effective_ api_key=None from the parent, so child subagents failed to authenticate whenever credentials lived in config.yaml rather than env vars (the production case for serious users). Fix: mirror hermes_cli/oneshot.py's resolve_runtime_provider pattern in both _build_parent_agent and superagent.py's parent construction. Threads api_key / base_url / provider / api_mode / credential_pool from the resolved runtime, exactly like oneshot does. 274 tests pass — no regressions. All 15 code-review findings are now fixed across three commits (f25ae81 showstoppers, 06e71bc critical correctness, this commit lower-severity polish). https://claude.ai/code/session_01PNyEMgrzVHtXnPGwUfotWw

…indings (one test each) #7 release_gate_parked suggested_command now carries the FULL gate sequence (event payload.commands joined with &&, fallback to joined _RELEASE_GATE_COMMANDS) instead of next(iter(...)) -> the bare leading cd. #8 freigabe/live_test_depth threaded into create_task's INSERT (new params) and the separate post-INSERT UPDATE removed from ingest_planspec -> root provenance is atomic with row creation, no NULL window / strand-on-raise. NousResearch#10 drop the redundant planspec_id child-dict key (always == planspec_subtask_id) and the dead `or` fallback in plugin_api; use planspec_subtask_id exclusively. NousResearch#11 add idempotent idx_events_kind on task_events(kind, task_id) (+ _REBUILD_SPECS) so the decision_queue kind='release_gate_parked' scan isn't full-table. NousResearch#13 /planspecs/detail: resolve+read EXACTLY once (parse_binding_planspec only, no validate-then-re-resolve TOCTOU window) and genericise resolve_planspec_path findings so the server's absolute vault path is never disclosed. NousResearch#14 lock the lossy AC body round-trip with a characterization test + explicit altitude-boundary docstring (structured fields live only in the .md; the full structured store is a Phase-4 follow-up). NousResearch#15 D1 characterization: make the docstring/contract truthful (no bug found -> no xfail; assertions are verified-correct regression tripwires). Gates: ruff clean; touched test files 643 passed; full scripts/run_tests.sh re-run for the record. Adversarial tree_root_woke real-chain repro still PASS. Co-Authored-By: Claude Opus 4.8 <[email protected]>

NousResearch#2 registry.get() alias + __contains__ — dict-like API consistency - tools/registry.py: added get() as alias for get_entry() - added __contains__ so "tool_name" in registry works NousResearch#3 _BUILTIN_SUBCOMMANDS guard test — catches missing entries - hermes_cli/main.py: added warning comment with test reference - tests/hermes_cli/test_main_integrity.py: 4 tests verifying the frozenset contains all core subcommands including reach NousResearch#4 hermes doctor --functional — actually test if tools work - hermes_cli/subcommands/doctor.py: added --functional flag - hermes_cli/doctor.py: runs reach capability functional probes as a new doctor section, showing real API call results NousResearch#6 proxy config in config.yaml — for restricted networks - hermes_cli/config.py: added proxy.url and proxy.apply_to_all to DEFAULT_CONFIG, added "proxy" to _KNOWN_ROOT_KEYS NousResearch#10 web toolset error messages — point to free alternatives - tools/web_tools.py: WEB_SEARCH_SCHEMA and WEB_EXTRACT_SCHEMA descriptions now mention free alternatives (Jina Reader, Exa, DDG) and "hermes reach setup" command for auto-configuration NousResearch#11 hermes mcp doctor — batch-test all MCP servers - hermes_cli/subcommands/mcp.py: added "doctor" subcommand - hermes_cli/main.py: _mcp_doctor() handler that tests all configured servers and reports status NousResearch#13 test isolation — investigated, not reproducible (pre-existing) - test passes consistently across 135 tests in 3 modules NousResearch#15 __tools__ list support — robust tool auto-discovery - tools/registry.py: _module_registers_tools() now also detects module-level __tools__ = [...] list declarations - tests/tools/test_registry.py: 3 new tests for __tools__ detection

hutchutchutch · 2026-06-24T21:46:12Z

Refactor progress on the PR #15 file-operations surface: extracted standalone file operation helpers into tools/file_operations_support.py while preserving the public tools.file_operations import surface. Commit: 44d016602 (refactor(file-ops): extract support helpers). Validation: py_compile for touched modules; focused file_operations suite 188 passed; standard gateway batches 265 passed and 115 passed; git diff --check clean. Note: broader file_tools/macOS temp-path tests still hit the existing /private/var sensitive-path guard and were not caused by this extraction.

hutchutchutch · 2026-06-24T21:49:21Z

Refactor progress on PR #15 file operations, second slice: extracted lint registries and in-process lint helpers into tools/file_operations_lint.py while preserving imports from tools.file_operations. Commit: a41161fc5 (refactor(file-ops): extract lint helpers). Validation: py_compile for touched modules; focused file-operation/LSP lint suite 220 passed; standard gateway batches 265 passed and 115 passed; git diff --check clean.

hutchutchutch · 2026-06-24T21:57:47Z

Refactor progress on PR #15 file operations, third slice: extracted search result types and shell search implementation into tools/file_operations_search.py while preserving ShellFileOperations.search and private wrapper method names used by tests. Commit: c342e24f1 (refactor(file-ops): extract search implementation). Validation: py_compile for touched modules; focused search/file-operation suite 200 passed; broader file-operation/LSP lint suite 229 passed; standard gateway batches 265 passed and 115 passed; git diff --check clean. Current line counts: tools/file_operations.py 1502, tools/file_operations_search.py 380, support 164, lint 110.

hutchutchutch · 2026-06-24T22:02:17Z

Refactor progress on PR #15 file operations, fourth slice: moved lint/LSP orchestration behind tools/file_operations_lint.py while preserving ShellFileOperations private wrapper methods used by tests. Commit: c90c097ce (refactor(file-ops): extract lint orchestration). Validation: py_compile for touched modules; focused file-operation/LSP suite 240 passed; standard gateway batches 265 passed and 115 passed; git diff --check clean. Current line counts: tools/file_operations.py 1189, search 380, lint 339, support 164.

hutchutchutch · 2026-06-24T22:08:15Z

Refactor progress on PR #15 file operations, fifth slice: extracted read/delete/move behavior into tools/file_operations_read.py and moved shared result dataclasses into tools/file_operations_results.py while preserving tools.file_operations exports and ShellFileOperations wrapper methods. Commit: a20c28974 (refactor(file-ops): extract read and file actions). Validation: py_compile for touched modules; focused file-operation/parser/live suite 241 passed; standard gateway batches 265 passed and 115 passed; git diff --check clean. Current line counts: tools/file_operations.py 879, read 221, results 82, search 380, lint 339, support 164.

hutchutchutch · 2026-06-24T22:14:00Z

Refactor progress on PR #15 file operations, sixth slice: extracted write/patch mutation behavior into tools/file_operations_write.py and moved the abstract FileOperations interface into tools/file_operations_interface.py. Commit: 80da36609 (refactor(file-ops): extract write and patch actions). Validation: py_compile for touched modules; focused mutation/read/parser/LSP suite 284 passed; standard gateway batches 265 passed and 115 passed; git diff --check clean. The original hotspot is now under target: tools/file_operations.py 476 lines; interface 75; write 222; read 221; results 82; search 380; lint 339; support 164.

hutchutchutch · 2026-06-24T22:23:10Z

Progress update for PRD #15:

Implemented the next file-tool refactor slice in e6683b654 (refactor(file-tools): extract tracker state).

What changed:

Added tools/file_tools_state.py for read dedup state, read timestamp/staleness helpers, read tracker cap enforcement, and patch failure tracking.
Kept tools.file_tools as the compatibility adapter: existing private names like _read_tracker, _read_tracker_lock, _patch_failure_tracker, _cap_read_tracker_data, _check_file_staleness, reset_file_dedup, and notify_other_tool_call remain importable from tools.file_tools.
Preserved legacy monkeypatch behavior for _READ_HISTORY_CAP, _DEDUP_CAP, and _READ_TIMESTAMPS_CAP by syncing patched adapter constants into the state module before cap enforcement.

Line counts after this slice:

tools/file_tools.py: 1435 lines, down from 1671 before this slice.
tools/file_tools_state.py: 249 lines.

Validation:

python -m py_compile tools/file_tools.py tools/file_tools_state.py
focused tracker/read/staleness suite with TMPDIR rooted under /Users/home/.hermes/tmp-pytest-hermes-agent-issue15 -> 89 passed
tests/tools/test_gateway_cwd_contract.py with the same non-sensitive temp root -> 4 passed
Standard gateway batch A -> 265 passed
Standard gateway batch B -> 115 passed
git diff --check / staged diff check clean

Notes:

A combined path/cwd batch hit existing test-state leakage where one test left live cwd cache state for a reused task id; tests/tools/test_gateway_cwd_contract.py passes in isolation.
tests/tools/test_file_tools.py still has the existing macOS /tmp vs /private/tmp expectation mismatch on three mocked write/patch assertions; this predates and is unrelated to the tracker-state extraction.

hutchutchutch · 2026-06-24T22:29:02Z

Progress update for PRD #15:

Implemented another file-tool refactor slice in 6c6ead02f (refactor(file-tools): extract path safety helpers).

What changed:

Added tools/file_tools_paths.py for cwd resolution, TERMINAL_CWD sentinel handling, live cwd lookup, path-resolution warnings, blocked-device checks, sensitive path checks, Hermes config path resolution, and cross-profile/container mirror guards.
Kept tools.file_tools as the compatibility adapter for existing private imports and monkeypatches, including _resolve_path_for_task, _path_resolution_warning, _is_blocked_device, _is_blocked_device_path, _check_sensitive_path, _check_cross_profile_path, and _hermes_config_resolved/_hermes_config_resolved_loaded.
Preserved live file-ops cache lookup through a small adapter so path helpers do not own the file-ops cache.

Line counts after this slice:

tools/file_tools.py: 1139 lines, down from 1435 after the previous slice and 1671 before today.
tools/file_tools_paths.py: 313 lines.
tools/file_tools_state.py: 249 lines.

Validation:

python -m py_compile tools/file_tools.py tools/file_tools_paths.py tools/file_tools_state.py
focused tracker/read/staleness suite with TMPDIR rooted under /Users/home/.hermes/tmp-pytest-hermes-agent-issue15 -> 89 passed
focused Hermes config sensitive-path compatibility class -> 5 passed
tests/tools/test_gateway_cwd_contract.py with the non-sensitive temp root -> 4 passed
Standard gateway batch A -> 265 passed
Standard gateway batch B -> 115 passed
git diff --check / staged diff check clean

Notes:

The combined path/cwd batch still hits the existing order-dependent live cwd cache leakage for a reused task id; the affected cwd contract file passes in isolation.
This slice keeps the upstream-facing tool function names and private test patch points intact to reduce nightly merge risk.

hutchutchutch · 2026-06-24T22:32:42Z

Progress update for PRD #15:

Implemented the third file-tools slice in 37c3bdd13 (refactor(file-tools): extract env cache helpers).

What changed:

Added tools/file_tools_env.py for terminal-environment-backed ShellFileOperations creation and cache population.
Kept tools.file_tools as the compatibility adapter for _get_file_ops, _file_ops_lock, _file_ops_cache, and clear_file_ops_cache so existing tests and monkeypatches continue to target the same module.
The new helper receives the existing cache, lock, ShellFileOperations factory, and logger as arguments; it does not own the public cache state.

Line counts after this slice:

tools/file_tools.py: 1031 lines, down from 1139 after the path slice and 1671 before today.
tools/file_tools_env.py: 129 lines.
tools/file_tools_paths.py: 313 lines.
tools/file_tools_state.py: 249 lines.

Validation:

python -m py_compile tools/file_tools.py tools/file_tools_env.py tools/file_tools_paths.py tools/file_tools_state.py
focused env/cache/read/staleness suite with TMPDIR rooted under /Users/home/.hermes/tmp-pytest-hermes-agent-issue15 -> 80 passed
focused cwd/container suite -> 32 passed
Standard gateway batch A -> 265 passed
Standard gateway batch B -> 115 passed
git diff --check / staged diff check clean

This continues the low-merge-risk pattern: move implementation behind small modules while preserving the old tools.file_tools import and patch surface.

hutchutchutch · 2026-06-24T22:40:06Z

Progress update for PRD #15:

Implemented the next file-tools slice in 9a3e19b4d (refactor(file-tools): extract read handler).

What changed:

Added tools/file_tools_read.py for the read_file_tool implementation: pagination normalization, device guard, extractable document handling, binary/read safety guards, dedup/stub-loop handling, max-character guard, redaction, large-file hinting, and file-state read registration.
Kept tools.file_tools.read_file_tool as the registered compatibility wrapper.
The wrapper injects existing adapter functions/state (_get_file_ops, _get_max_read_chars, _resolve_path_for_task, _cap_read_tracker_data, _read_tracker, _read_tracker_lock), so existing tests and monkeypatches keep targeting tools.file_tools.

Line counts after this slice:

tools/file_tools.py: 788 lines, down from 1031 before this slice and 1671 before today.
tools/file_tools_read.py: 246 lines.
Existing extracted helpers remain under target: env 129, paths 313, state 249.

Validation:

python -m py_compile tools/file_tools.py tools/file_tools_read.py tools/file_tools_env.py tools/file_tools_paths.py tools/file_tools_state.py
focused read guards / read loop / read_extract / file_state registry suite -> 98 passed
tests/tools/test_file_staleness.py -> 11 passed
tests/agent/test_file_safety_credentials.py -> 20 passed
tests/tools/test_file_tools.py::TestReadFileHandler -> 4 passed
Standard gateway batch A -> 265 passed
Standard gateway batch B -> 115 passed
git diff --check / staged diff check clean

Note:

One intentionally broad combined read/staleness batch still hit the known order-dependent live cwd cache leakage; the affected staleness test passes in isolation and the focused stale suite passes fully.

hutchutchutch · 2026-06-24T22:43:12Z

Progress update for PRD #15:

Implemented the next file-tools slice in 6138eaa1a (refactor(file-tools): extract search handler).

What changed:

Added tools/file_tools_search.py for the search_files implementation: pagination normalization, repeated-search loop guard, ShellFileOperations search dispatch, match redaction, warning/hint formatting, and structured error handling.
Kept tools.file_tools.search_tool as the compatibility wrapper.
The wrapper injects existing adapter functions/state (_get_file_ops, normalize_search_pagination, _read_tracker, _read_tracker_lock), so existing tests and monkeypatches keep targeting tools.file_tools.

Line counts after this slice:

tools/file_tools.py: 741 lines, down from 788 after the read slice and 1671 before today.
tools/file_tools_search.py: 95 lines.

Validation:

python -m py_compile tools/file_tools.py tools/file_tools_search.py
tests/tools/test_file_tools.py::TestSearchHandler + tests/tools/test_read_loop_detection.py::TestSearchLoopDetection -> 13 passed
Standard gateway batch A -> 265 passed
Standard gateway batch B -> 115 passed
git diff --check / staged diff check clean

Next remaining PR #15 seam is the write/patch mutation handler block; extracting that should bring tools/file_tools.py close to or under the 500-line target.

hutchutchutch · 2026-06-24T22:51:28Z

Progress update for PRD #15:

Implemented the mutation/schema slice in 50e42d119 (refactor(file-tools): extract mutation handlers).

What changed:

Added tools/file_tools_mutation.py for write_file_tool and patch_tool implementation: sensitive/cross-profile guards, stale warnings, file_state locks, read timestamp refresh, files_modified/resolved_path reporting, V4A traversal guard, and patch failure escalation hints.
Added tools/file_tools_schemas.py for static file tool schemas.
Kept tools.file_tools.write_file_tool, tools.file_tools.patch_tool, _handle_write_file, and _handle_patch as compatibility/registry wrappers.
Restored compatibility re-exports for _detect_line_ending and _normalize_line_endings from tools.file_operations after the earlier support-helper extraction.

Line counts after this slice:

tools/file_tools.py: 455 lines (under the ~500 target; down from 1671 before today).
tools/file_operations.py: 478 lines (still under target).
New helper modules remain small: mutation 235, schemas 103, search 95, read 246, env 129, paths 313, state 249.

Validation:

python -m py_compile tools/file_operations.py tools/file_tools.py tools/file_tools_mutation.py tools/file_tools_schemas.py and related helper modules
tests/tools/test_line_ending_preservation.py -> 12 passed
tests/tools/test_file_staleness.py -> 11 passed
tests/tools/test_patch_failure_tracking.py -> 5 passed
mutation handler unit subset excluding known macOS /tmp normalization assertions -> 22 passed
mutation state/cross-profile/cwd combined batch -> 72 passed, with the known order-dependent live-cwd cache case failing when combined but passing in isolation
Standard gateway batch A -> 265 passed
Standard gateway batch B -> 115 passed
git diff --check / staged diff check clean

Known existing caveats kept separate:

tests/tools/test_file_tools.py still has three macOS /tmp vs /private/tmp mocked-call expectation failures; production behavior was not changed for this refactor.
A broad combined cwd/staleness batch can still hit the existing live cwd cache order leak; the focused staleness suite passes.

…ded for version bumps) (NousResearch#15) * [agento] fix: green-gate Gate 3 — auto-PASS dependabot PRs (no CR needed for version bumps) dependabot[bot] PRs are automated dependency bumps. Requiring a CodeRabbit review blocks them indefinitely when CR hits rate limits. Add PR_GATE3_AUTHOR check: if author == dependabot[bot], Gate 3 auto-PASSes. Human-authored PRs continue to require CR APPROVED. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * [agento] fix: set LATEST_CR=APPROVED for dependabot Gate 3 auto-PASS (Gate 5 fast-path) BugBot caught that LATEST_CR was unset when dependabot PRs auto-PASS Gate 3, making Gate 5's CR-approved non-blocking fast-path unreachable for those PRs. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * [agento] fix: skeptic-cron Gate 3 — dependabot PRs auto-PASS (no CR needed) Mirrors green-gate Gate 3 dependabot exemption so dependabot version bumps can be auto-merged by skeptic-cron without requiring a formal CR review. Adds author field to PR JSON payload so dependabot detection works in the loop. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> --------- Co-authored-by: Claude Sonnet 4.6 <[email protected]>

Rl capabilities && File Operator Tools

…seat) Rebase reconciliation for issue NousResearch#15 (v2026.6.19 merge). Commit 1's multi-user-isolation change "ResponseStore JSON blob now carries user_id" auto-merged its `"user_id": user_id` line into upstream v2026.6.19's NEW `_write_sse_responses._persist_response_snapshot` (git matched the `_response_store.put(...)` block), but `user_id` was not in that method's scope -> NameError at runtime on the streaming /v1/responses path (api_server.py:3261). py_compile/import don't catch undefined names in nested closures; surfaced by the api_server regression suite. Fix: add `user_id` param to `_write_sse_responses` and forward it from `_handle_responses` (which holds `user_id = scope["user_id"]`). Belongs logically in commit 166397c (multi-user isolation v1); kept separate so the rebase replay stays auditable. Authoritative kg suites: 231 passed. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

Rl capabilities && File Operator Tools

…de changes) Ran a read-only dry-run against a real exported skill library (76 SKILL.md, 25 candidates, nested category dirs + CJK) in an isolated HERMES_HOME. Pipeline ran cleanly and safely (no mutation); LLM decisions were sensible (2 consolidations proposed, rest kept standalone). Two real gaps fixtures could never expose: - dry-run under-reports consolidation proposals (counts/arrays stay 0 while prose proposes merges) — asymmetric vs split/deprecate (KNOWN_ISSUES NousResearch#15) - keyword-retention guard is near-inert on nested/CJK skills: _load_skill_keywords resolves only flat paths -> name-only fallback (KNOWN_ISSUES NousResearch#16) Guards were not exercised (model used the YAML channel; 25 skill_view, 0 skill_manage). No code changed. Co-Authored-By: Claude <[email protected]>

…n report (NousResearch#15 / P0) In dry-run nothing is removed, so the removal-based classification left consolidated/pruned empty even when the model proposed merges — while splits/deprecations already surfaced their YAML proposals. A dry-run preview therefore under-reported what a real run would do (REPORT.md printed 'consolidated: 0' above a prose body proposing merges). Surface the YAML-block consolidation/pruning proposals into run.json counts/arrays + REPORT.md, tagged source='model (proposed, dry-run)' and behind a DRY-RUN banner. The fold runs AFTER the cron-rewrite block so a dry-run never mutates cron/jobs.json; real-run classification is unchanged (guarded by a test). Co-Authored-By: Claude <[email protected]>

…h-pass real-data re-verification Co-Authored-By: Claude <[email protected]>

…o code changes) Ran a read-only dry-run against a larger, deliberately uncleaned backup (130 usage records vs 123 files, path-prefixed keys, all-active-despite-archive, external symlink). Result: no errors/exceptions handling the dirty data; LLM emitted a well-formed empty structured block (keep all 27); guard not exercised (YAML channel). NousResearch#15 fix makes the reported 0 trustworthy (matches empty block) vs the 8th-pass ambiguous 0. One untested dimension noted: the active-vs-archived usage mismatch's effect on the deterministic prune is not covered by dry-run (prune is skipped). No code changed. Co-Authored-By: Claude <[email protected]>

Anthropic bills any >200K-input request on a subscription (OAuth) account to the EXTRA-USAGE budget, not plan limits — even without the context-1m beta header (1M context is GA on Claude 4.6+). A 339K-token desktop session got permanent 'You are out of extra usage' 400s while a small probe on the same token returned 200. Fix: _apply_subscription_context_cap() clamps the resolved context to 200K when the token is an OAuth/setup token (sk-ant-oat*, eyJ*, cc-*). Metered API keys (sk-ant-api*) are NOT capped. Escape hatch: anthropic.long_context. Tests: test_critical26_subscription_context_capped_at_plan_lane, test_critical26_long_context_escape_hatch (both pass) See CRITICAL NousResearch#15 in CRITICAL-ISSUES.md for full RCA.

Rl capabilities && File Operator Tools

teknium1 added 6 commits February 3, 2026 23:41

initial RL training tools and loop

f018999

teknium1 merged commit 8dd3831 into main Feb 5, 2026

SHL0MS mentioned this pull request Mar 30, 2026

[UX] Tool approval UX: "always" label is misleading, timeout is not configurable #4067

Closed

h4x3rotab pushed a commit to Clawdi-AI/hermes-agent that referenced this pull request Apr 10, 2026

Merge PR NousResearch#15: Final header cleanup — subtractive pass

58fc261

malaiwah pushed a commit to malaiwah/hermes-agent that referenced this pull request Apr 11, 2026

Merge pull request 'fix(terminal): add missing notify_on_complete par…

7e557c0

…ameter + schema property' (NousResearch#15) from fix/terminal-notify-on-complete into main

kshitijk4poor mentioned this pull request Apr 15, 2026

feat: add hermes-blender skill for 3D modeling and rendering #10191

Closed

njiangk mentioned this pull request Apr 21, 2026

fix(whatsapp): mitigate libsignal protobufjs CVE in bridge deps #13259

Closed

3 tasks

angelburgosrosado pushed a commit to angelburgosrosado/hermes-agent that referenced this pull request Apr 27, 2026

Merge pull request NousResearch#15 from NousResearch/rl-capabilities

8552bd9

Rl capabilities && File Operator Tools

blaketyndall-eng mentioned this pull request May 14, 2026

W2-T08: lru_cache get_tool_output_limits to skip per-call config parse blaketyndall-eng/hermes-agent#10

Merged

acoastalfog mentioned this pull request May 23, 2026

Bridge legacy KB dashboard plugin to standalone app #31190

Closed

Renge-Star mentioned this pull request May 24, 2026

[--tui] gateway exits mid-turn with stdin EOF (TUI closed the command pipe) — NOT byterover-related #27282

Closed

BowmanStephen mentioned this pull request May 25, 2026

[feature-adoption] Adopt remaining unused Hermes features (9 unstarted) BowmanStephen/hermes-agent#9

Open

madlouse mentioned this pull request Jun 2, 2026

Feature: Gateway-level hard routing gate for outbound message classification #37271

Open

xzmzm added a commit to xzmzm/hermes-agent that referenced this pull request Jun 3, 2026

fix: reorder patches NousResearch#15/NousResearch#16 in hermes-patche…

87a9100

…s.md

cristianmgm7 mentioned this pull request Jun 10, 2026

feat(platforms): add Carbon Voice as a platform plugin #43226

Open

alt-glitch mentioned this pull request Jun 19, 2026

fix(opentui): render V4A (hunk-less) diffs instead of falling back to raw params alt-glitch/hermes-agent#7

Merged

waefrebeorn pushed a commit to waefrebeorn/slermes that referenced this pull request Jul 2, 2026

Merge pull request NousResearch#15 from NousResearch/rl-capabilities

b33d361

Rl capabilities && File Operator Tools

seiichi3141 mentioned this pull request Jul 4, 2026

feat(kai): broadcast CLI — OBS 起動/配信開始停止/クリーン終了の一括制御（M4） HyuCode/kai-agent#3

Merged

falkoro mentioned this pull request Jul 9, 2026

[Bug]: TypeError: Completions.create() got an unexpected keyword argument 'system' in chat_completions.py via _build_kwargs_from_profile #60821

Closed

1 task

kulikman pushed a commit to kulikman/hermes-agent that referenced this pull request Jul 16, 2026

Merge pull request NousResearch#15 from NousResearch/rl-capabilities

26d6674

Rl capabilities && File Operator Tools

feiguang50-hub pushed a commit to feiguang50-hub/hermes-agent that referenced this pull request Jul 19, 2026

docs: mark NousResearch#15/NousResearch#16 P0s resolved + record nint…

64b644a

…h-pass real-data re-verification Co-Authored-By: Claude <[email protected]>

ElystrumCore mentioned this pull request Jul 19, 2026

feat(plugins): fail-closed required enforcers + scheduled-run/model-spend governance ElystrumCore/hermes-agent#1

Merged

waym0reom3ga added a commit to waym0reom3ga/autolycus-agent that referenced this pull request Jul 21, 2026

Merge pull request NousResearch#15 from NousResearch/rl-capabilities

a12d7d4

Rl capabilities && File Operator Tools

Uh oh!

Conversation

teknium1 commented Feb 5, 2026

Uh oh!

taeyun16 commented Mar 30, 2026

🔍 자동 분석 결과

이슈 요약

기술 구현 고려사항

백엔드 (Phoenix/Ash)

iOS (SwiftUI)

우선순위 제안

관련existing 코드

Uh oh!

zhangtobybot-a11y commented Apr 11, 2026

Uh oh!

zhangtobybot-a11y commented Apr 11, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

hutchutchutch commented Jun 24, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants