hermes-agent/tools
Teknium a0fedfbb1b
feat(checkpoints): v2 single-store rewrite with real pruning + disk guardrails (#20709)
Replaces the per-directory shadow-repo design with a single shared shadow
git store at ~/.hermes/checkpoints/store/. Object DB is now deduplicated
across every working directory the agent has ever touched; a dozen
worktrees of the same project cost near-zero in additional disk.

Why
---
Pre-v2 design had three compounding problems that let ~/.hermes/checkpoints/
grow to multi-GB on active machines:

1. Each working directory got its own full shadow git repo — no object
   dedup across projects or across worktrees of the same project.
2. _prune() was a documented no-op: max_snapshots only limited the
   /rollback listing. Loose objects accumulated forever.
3. Defaults: enabled=True, auto_prune=False — users paid the disk cost
   without ever asking for /rollback.

Field report on a single workstation: 847 MB across 47 shadow repos,
mostly redundant clones of the hermes-agent source tree.

Changes
-------
- tools/checkpoint_manager.py: full rewrite. Single bare store, per-project
  refs (refs/hermes/<hash>), per-project indexes (store/indexes/<hash>),
  per-project metadata (store/projects/<hash>.json with workdir +
  created_at + last_touch). On first v2 init, any pre-v2 per-directory
  shadow repos are auto-migrated into legacy-<timestamp>/ so the new
  store starts clean. _prune() now actually rewrites the per-project ref
  to the last max_snapshots commits and runs git gc --prune=now. New
  _enforce_size_cap() drops oldest commits round-robin across projects
  when the store exceeds max_total_size_mb. _drop_oversize_from_index()
  filters any single file larger than max_file_size_mb out of the snapshot.
- hermes_cli/checkpoints.py: new 'hermes checkpoints' CLI
  (status / list / prune / clear / clear-legacy) for managing the store
  outside a session.
- hermes_cli/config.py: flipped defaults — enabled=False, max_snapshots=20,
  auto_prune=True. Added max_total_size_mb=500, max_file_size_mb=10.
  Tightened DEFAULT_EXCLUDES (added target/, *.so/*.dylib/*.dll,
  *.mp4/*.mov, *.zip/*.tar.gz, .worktrees/, .mypy_cache/, etc.).
- run_agent.py / cli.py / gateway/run.py: thread the new kwargs through
  AIAgent and the startup auto_prune hooks.
- Tests rewritten to match v2 storage while keeping backwards-compat
  coverage for the pre-v2 prune path (per-directory shadow repos under
  base/ are still swept correctly for anyone mid-migration).
- Docs updated: user-guide/checkpoints-and-rollback.md explains the
  shared store, new defaults, migration, and the new CLI;
  reference/cli-commands.md documents 'hermes checkpoints'.

E2E validated
-------------
- Legacy migration: pre-v2 shadow repos auto-archived into legacy-<ts>/.
- Object dedup: two projects with an identical shared.py blob resolve to
  7 total objects in the store (v1 would have stored the blob twice).
- max_snapshots=3 actually enforced: after 6 commits, list shows 3.
- Orphan prune: deleting a project's workdir + 'hermes checkpoints prune
  --retention-days 0' removes its ref, index, and metadata; GC reclaims
  the objects.
- max_file_size_mb=1 excludes a 2 MB weights.bin while keeping the
  tracked source code files.
- hermes checkpoints {status,prune,clear,clear-legacy} all work from the
  CLI without an agent running.

Breaking / migration
--------------------
No in-place data migration — legacy per-directory shadow repos are moved
into legacy-<timestamp>/ on first run. Old /rollback history is still
accessible by inspecting the archive with git; run
'hermes checkpoints clear-legacy' to reclaim the space when ready. Users
relying on /rollback must now set checkpoints.enabled=true (or pass
--checkpoints) explicitly.
2026-05-06 05:44:35 -07:00
..
browser_providers feat: ungate Tool Gateway — subscription-based access with per-tool opt-in 2026-04-16 12:36:49 -07:00
environments docs: align terminal-backend count and naming across docs and code 2026-05-05 13:44:09 -07:00
neutts_samples refactor(tts): replace NeuTTS optional skill with built-in provider + setup flow 2026-03-17 02:33:12 -07:00
__init__.py Merge branch 'main' into rewbs/tool-use-charge-to-subscription 2026-03-31 08:48:54 +09:00
ansi_strip.py fix: strip ANSI at the source — clean terminal output before it reaches the model 2026-03-23 07:43:12 -07:00
approval.py feat(i18n): add display.language for static message translation (zh/ja/de/es) (#20231) 2026-05-05 08:03:07 -07:00
binary_extensions.py fix(tools): address PR review — remove _extract_raw_output, BudgetConfig everywhere, read_file hardening 2026-04-08 02:24:32 -07:00
browser_camofox.py refactor(config): add cfg_get() helper; migrate 20 nested-get call sites (#17304) 2026-04-28 23:17:39 -07:00
browser_camofox_state.py feat(browser): add persistent Camofox sessions and VNC URL discovery (salvage #4400) (#4419) 2026-04-01 04:18:50 -07:00
browser_cdp_tool.py chore: remove unused imports and dead locals (ruff F401, F841) (#17010) 2026-04-28 06:46:45 -07:00
browser_dialog_tool.py feat(browser): CDP supervisor — dialog detection + response + cross-origin iframe eval (#14540) 2026-04-23 22:23:37 -07:00
browser_supervisor.py fix(browser_supervisor): verify thread and loop health before returning cached supervisor 2026-04-30 20:33:33 -07:00
browser_tool.py fix(browser): tighten Lightpanda fallback edge cases 2026-05-06 03:41:21 -07:00
budget_config.py fix: preserve existing thresholds, remove pre-read byte guard 2026-04-08 02:24:32 -07:00
checkpoint_manager.py feat(checkpoints): v2 single-store rewrite with real pruning + disk guardrails (#20709) 2026-05-06 05:44:35 -07:00
clarify_tool.py refactor: add tool_error/tool_result helpers + read_raw_config, migrate 129 callsites 2026-04-07 13:36:38 -07:00
code_execution_tool.py fix(tools): serialize concurrent hermes_tools RPC calls from execute_code 2026-04-30 03:31:16 -07:00
credential_files.py refactor(config): add cfg_get() helper; migrate 20 nested-get call sites (#17304) 2026-04-28 23:17:39 -07:00
cronjob_tools.py feat(cron): add no_agent mode for script-only cron jobs (watchdog pattern) (#19709) 2026-05-04 12:31:01 -07:00
debug_helpers.py refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821) 2026-04-07 10:25:31 -07:00
delegate_tool.py fix(delegation): honor provider override for subagents 2026-05-04 05:22:35 -07:00
discord_tool.py fix(discord_tool): key capability cache by token instead of single global 2026-04-30 20:37:12 -07:00
env_passthrough.py refactor(config): add cfg_get() helper; migrate 20 nested-get call sites (#17304) 2026-04-28 23:17:39 -07:00
feishu_doc_tool.py fix(feishu-comment): use get_hermes_home(); drop dead asyncio wrapper; AUTHOR_MAP 2026-04-17 19:04:11 -07:00
feishu_drive_tool.py fix(feishu-comment): use get_hermes_home(); drop dead asyncio wrapper; AUTHOR_MAP 2026-04-17 19:04:11 -07:00
file_operations.py docs: align terminal-backend count and naming across docs and code 2026-05-05 13:44:09 -07:00
file_state.py feat(delegate): cross-agent file state coordination for concurrent subagents (#13718) 2026-04-21 16:41:26 -07:00
file_tools.py feat(file_tools): post-write delta lint on write_file + patch, add JSON/YAML/TOML/Python in-process linters (#20191) 2026-05-05 04:54:17 -07:00
fuzzy_match.py fix(patch): gate 'did you mean?' to no-match + extend to v4a/skill_manage 2026-04-21 02:03:46 -07:00
homeassistant_tool.py fix: clean up description escaping, add string-data tests 2026-04-13 04:45:07 -07:00
image_generation_tool.py fix(image-gen): force-refresh plugin providers in long-lived sessions 2026-04-23 03:01:18 -07:00
interrupt.py fix(interrupt): propagate to concurrent-tool workers + opt-in debug trace (#11907) 2026-04-17 20:39:25 -07:00
kanban_tools.py guard kanban worker lifecycle by run id 2026-05-05 15:09:28 -07:00
managed_tool_gateway.py fix(tools): add debug logging for token refresh and tighten domain check 2026-04-02 12:40:03 +11:00
mcp_oauth.py fix(mcp): decouple AnyUrl import from mcp dependency 2026-05-04 04:42:18 -07:00
mcp_oauth_manager.py fix(mcp-oauth): preserve server_url path for protected-resource validation (#16031) 2026-04-26 05:43:54 -07:00
mcp_tool.py fix(mcp): add periodic keepalive to _wait_for_lifecycle_event 2026-05-05 05:47:33 -07:00
memory_tool.py refactor: consolidate symlink-safe atomic replace into shared helper 2026-04-28 04:58:22 -07:00
mixture_of_agents_tool.py Fix (mixture_of_agents): replace deprecated Gemini model and forward max_tokens to OpenRouter (#6621) 2026-04-23 15:14:11 -07:00
neutts_synth.py fix(tts): document NeuTTS provider and align install guidance (#1903) 2026-03-18 02:55:30 -07:00
openrouter_client.py refactor: route ad-hoc LLM consumers through centralized provider router 2026-03-11 20:02:36 -07:00
osv_check.py feat: OSV malware check for MCP extension packages (#5305) 2026-04-05 12:46:07 -07:00
patch_parser.py fix(patch): gate 'did you mean?' to no-match + extend to v4a/skill_manage 2026-04-21 02:03:46 -07:00
path_security.py refactor: extract shared helpers to deduplicate repeated code patterns (#7917) 2026-04-11 13:59:52 -07:00
process_registry.py fix(terminal): guard background process spawn against deleted cwd (#19933) 2026-05-04 15:35:34 -07:00
registry.py perf(tools): memoize get_tool_definitions + TTL-cache check_fn results (#17098) 2026-04-28 18:20:17 -07:00
rl_training_tool.py refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821) 2026-04-07 10:25:31 -07:00
schema_sanitizer.py fix(tool-schemas): reactive strip of pattern/format on llama.cpp grammar 400s 2026-05-05 04:25:18 -07:00
send_message_tool.py fix(email): add required Date header to send_message_tool._send_email 2026-05-04 02:48:20 -07:00
session_search_tool.py fix(session-search): report source from resolved parent, not FTS5 child session (#15909) 2026-05-04 05:07:40 -07:00
skill_manager_tool.py fix(skills): pin protects against deletion only, not edits (#20220) 2026-05-05 05:43:10 -07:00
skill_provenance.py fix(curator): only mark agent-created for background-review sediment (#19621) 2026-05-04 02:42:16 -07:00
skill_usage.py fix(curator): protect hub skills by frontmatter name 2026-05-05 04:55:22 -07:00
skills_guard.py feat(skills-guard): gate agent-created scanner on config.skills.guard_agent_created (default off) 2026-04-23 06:20:47 -07:00
skills_hub.py skills-hub: hash binary skill bundle files correctly 2026-05-04 01:28:12 -07:00
skills_sync.py refactor: consolidate symlink-safe atomic replace into shared helper 2026-04-28 04:58:22 -07:00
skills_tool.py fix(skills): support category-qualified local skill names 2026-05-05 10:15:31 -07:00
slash_confirm.py feat(gateway,cli): confirm /reload-mcp to warn about prompt cache invalidation 2026-04-29 21:56:47 -07:00
terminal_tool.py fix(terminal): skip sudo prompt when local NOPASSWD sudo works 2026-04-30 20:38:09 -07:00
tirith_security.py fix: guard against None tirith path in security scanner 2026-04-23 03:08:53 -07:00
todo_tool.py fix(tools): enforce ID uniqueness in TODO store during replace operations 2026-04-11 16:22:50 -07:00
tool_backend_helpers.py fix(cli): coerce use_gateway config flags in tool routing 2026-04-26 19:02:55 -07:00
tool_output_limits.py feat(skills): add design-md skill for Google's DESIGN.md spec (#14876) 2026-04-23 21:51:19 -07:00
tool_result_storage.py fix(tools): neutralize shell injection in _write_to_sandbox via path quoting (#7940) 2026-04-11 14:26:11 -07:00
transcription_tools.py fix(ci): stabilize main test suite regressions (#17660) 2026-04-29 23:18:55 -07:00
tts_tool.py fix(tts): update MiniMax API endpoint to v1/text_to_speech 2026-05-04 12:36:09 -07:00
url_safety.py fix(security): treat quoted false as false in browser SSRF guards 2026-04-26 18:27:13 -07:00
vision_tools.py fix(vision): guard user_prompt type in video_analyze_tool before debug_call_data construction 2026-05-03 15:28:04 -07:00
voice_mode.py fix: point optional-dep install hints at the venv's python (#11938) 2026-04-17 21:16:33 -07:00
web_tools.py docs(web_tools): correct web_extract summarizer timeout comment 2026-05-05 13:24:19 -07:00
website_policy.py refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821) 2026-04-07 10:25:31 -07:00
xai_http.py feat(xai): upgrade to Responses API, add TTS provider 2026-04-16 02:24:08 -07:00
yuanbao_tools.py chore: remove unused imports and dead locals (ruff F401, F841) (#17010) 2026-04-28 06:46:45 -07:00