This website requires JavaScript.
7bccd904c7
Merge PR #629 : feat: add Polymarket prediction market skill (read-only)
2026-03-07 17:28:03 -08:00
313d522b61
feat: add Polymarket prediction market skill (read-only)
2026-03-07 17:27:29 -08:00
9ee4fe41fe
Fix image_generate 'Event loop is closed' in gateway
2026-03-07 16:56:49 -08:00
39ee3512cb
Merge PR #614 : fix: resolve systemd restart loop with --replace flag
2026-03-07 16:33:27 -08:00
42673556af
Merge PR #575 : fix(setup): prevent OpenRouter model list fallback for Nous provider
2026-03-07 16:22:13 -08:00
faab73ad58
Merge PR #573 : fix(doctor): detect OpenAI custom endpoint env settings
2026-03-07 16:16:08 -08:00
7e36468511
fix: /clear command broken inside TUI (patch_stdout interference)
2026-03-07 16:09:23 -08:00
86eed141af
fix: rebuild compressed payload before retry
2026-03-07 15:13:45 -05:00
c6df39955c
fix: limit concurrent Modal sandbox creations to avoid deadlocks
2026-03-07 21:34:06 +00:00
9ba5d399e5
fix: restore missing MIT license file
2026-03-07 13:43:08 -08:00
19459b7623
Improve skills tool error handling
2026-03-08 00:30:49 +03:00
306d92a9d7
refactor(context_compressor): improve summary generation logic and error handling
2026-03-07 11:54:51 -08:00
5baae0df88
feat(scheduler): enhance job configuration with reasoning effort, prefill messages, and provider routing
2026-03-07 11:37:16 -08:00
24f6a193e7
fix: remove stale 'model' assertion from delegate_task schema test
2026-03-07 11:29:55 -08:00
8c0f8baf32
feat(delegate_tool): add additional parameters for child agent configuration
2026-03-07 11:29:17 -08:00
d80c30cc92
feat(gateway): proactive async memory flush on session expiry
2026-03-07 11:27:50 -08:00
e64d646bad
Critical: fix bug in new subagent tool call budget to not be session-level but tool call loop level
2026-03-07 10:32:51 -08:00
b84f9e410c
feat: default reasoning effort from xhigh to medium
2026-03-07 10:14:19 -08:00
ee5daba061
fix: resolve systemd restart loop with --replace flag (#576 )
2026-03-07 18:08:12 +00:00
23e84de830
refactor: remove model parameter from AIAgent initialization
2026-03-07 09:48:19 -08:00
48e0dc8791
feat: implement Z.AI endpoint detection for API key validation
2026-03-07 09:43:37 -08:00
b0b19fdeb1
fix(session): atomic write for sessions.json to prevent data loss on crash
2026-03-07 20:54:45 +03:30
fb0f579b16
refactor: remove model parameter from delegate_task function
2026-03-07 09:20:27 -08:00
5a711f32b1
fix: enhance payload and context compression handling
2026-03-07 09:19:07 -08:00
8c26a057a3
fix: reset all retry counters at start of run_conversation()
2026-03-07 20:12:08 +03:00
ae4644f495
Fix Ruff lint warnings (unused imports and unnecessary f-strings)
2026-03-07 17:08:09 +00:00
4d34427cc7
fix: update model version in agent configurations
2026-03-07 09:06:37 -08:00
70cffa4d3b
fix: return "deny" on approval callback timeout instead of None
2026-03-07 19:30:00 +03:00
ee7d8c56c7
fix: prevent data loss in clipboard PNG conversion when ImageMagick fails
2026-03-07 19:27:23 +03:00
41877183bc
Merge PR #604 : fix(tests): isolate max_turns tests from CI env and update default to 90
2026-03-07 08:57:36 -08:00
451a007fb1
fix(tests): isolate max_turns tests from CI env and update default to 90
2026-03-07 19:38:41 +03:00
0a82396718
feat: shared iteration budget across parent + subagents
2026-03-07 08:16:37 -08:00
5da55ea1e3
fix: sanitize orphaned tool-call/result pairs in message compression
2026-03-07 08:08:00 -08:00
40bc7216e1
fix(security): use in-memory set for permanent allowlist save
2026-03-07 05:38:20 +03:30
5cdcb9e26f
fix: strip MarkdownV2 italic markers in Telegram plaintext fallback
2026-03-07 18:55:25 +03:00
ce7e7fef30
docs(skill): expand duckduckgo-search with DDGS Python API coverage
2026-03-07 21:06:21 +05:30
064c009deb
feat: show update-available notice in CLI banner
2026-03-07 07:35:36 -08:00
86caa8539c
Improve TTS error handling and logging
2026-03-07 16:53:30 +03:00
caab1cf453
fix: update setup/config UI for local browser mode
2026-03-07 01:23:27 -08:00
55c70f3508
fix: strip MarkdownV2 escapes from Telegram plaintext fallback
2026-03-07 01:23:18 -08:00
d29249b8fa
feat: local browser backend — zero-cost headless Chromium via agent-browser
2026-03-07 01:14:57 -08:00
f668e9fc75
feat: platform-conditional skill loading + Apple/macOS skills
2026-03-07 00:47:54 -08:00
74fe1e2254
chore: remove TODO.md — all items tracked as issues
2026-03-07 00:07:14 -08:00
348936752a
fix: simplify timezone migration to use os.getenv directly
2026-03-07 00:05:05 -08:00
69a36a3361
Merge PR #309 : fix(timezone): timezone-aware now() for prompt, cron, and execute_code
2026-03-07 00:04:41 -08:00
8712dd6d1c
Merge pull request #308 from batuhankocyigit/patch-2
2026-03-06 23:43:09 -08:00
55a21fe37b
docs: add Environments, Benchmarks & Data Generation guide
2026-03-06 23:31:45 -08:00
f55f625277
chore: reorder terminal backends in setup wizard
2026-03-06 22:21:57 -08:00
9dac85b069
fix: uv pip install fails outside venv in setup wizard
2026-03-06 21:55:33 -08:00
99bd69baa8
Merge feat/modular-setup-wizard: modular setup wizard with section subcommands and tool-first UX
2026-03-06 21:12:30 -08:00
a62a137a4f
fix: handle dict-format model config in setup wizard display
2026-03-06 21:11:40 -08:00
82b18e8ac2
feat: unify hermes tools and hermes setup tools into single flow
2026-03-06 18:11:35 -08:00
0111c9848d
fix: remove ANSI codes and em dashes from menu labels
2026-03-06 17:55:44 -08:00
ab9cadfeee
feat: modular setup wizard with section subcommands and tool-first UX
2026-03-06 17:46:31 -08:00
8bf28e1441
fix(setup): prevent OpenRouter model list fallback for Nous provider
2026-03-07 07:16:22 +03:00
ce28f847ce
fix: update OpenRouter model names for yc-bench config
2026-03-06 19:58:56 -08:00
5609117882
fix(doctor): recognize OPENAI_API_KEY custom endpoint config
2026-03-06 19:47:09 -08:00
b4fbb6fe10
feat: add YC-Bench long-horizon agent benchmark environment
2026-03-06 19:25:56 -08:00
82d7e9429e
chore: add GLM/Kimi/MiniMax models to insights pricing (zero cost)
2026-03-06 19:12:14 -08:00
e2821effb5
feat: add direct API-key providers as auxiliary client fallbacks
2026-03-06 19:08:54 -08:00
9742f11fda
chore: add context lengths for Kimi and MiniMax models
2026-03-06 19:01:38 -08:00
53b4b7651a
Add official OpenClaw migration skill for Hermes Agent
2026-03-06 18:57:12 -08:00
388dd4789c
feat: add z.ai/GLM, Kimi/Moonshot, MiniMax as first-class providers
2026-03-06 18:55:12 -08:00
fdebca4573
Merge pull request #571 from NousResearch/rewbs/nous-key-remint-attempt-on-401
2026-03-06 18:52:01 -08:00
479dfc096a
Merge PR #473 : Update model id in OpenRouter from minimax-m2.1 to minimax-m2.5
2026-03-06 18:43:18 -08:00
3c6c11b7c9
Merge PR #420 : fix: respect OPENAI_BASE_URL when resolving API key priority
2026-03-06 18:43:13 -08:00
bc091eb7ef
fix: implement Nous credential refresh on 401 error for retry logic
2026-03-07 13:34:23 +11:00
a857321463
fix(code-execution): close server socket in finally block to prevent fd leak
2026-03-07 05:41:11 +03:30
f75b1d21b4
fix: execute_code and delegate_task now respect disabled toolsets
2026-03-06 17:36:06 -08:00
33cfe1515d
fix: sanitize FTS5 queries and close mirror DB connections
2026-03-07 04:24:45 +03:00
94053d75a6
fix: custom endpoint no longer leaks OPENROUTER_API_KEY (#560 )
2026-03-06 17:16:14 -08:00
2a68099675
fix(tests): isolate tests from user ~/.hermes/ config and SOUL.md
2026-03-06 17:10:35 -08:00
3b43f7267a
fix: count actual tool calls instead of tool-related messages
2026-03-07 04:07:52 +03:00
6cd3bc6640
Merge PR #563 : fix: prevent data loss in skills sync on copy/update failure
2026-03-06 17:01:30 -08:00
211b55815e
fix: prevent data loss in skills sync on copy/update failure
2026-03-07 03:58:32 +03:00
8ae4a6f824
fix: improve handling of empty responses after tool calls
2026-03-06 16:54:31 -08:00
b98301677a
docs: add /insights to all help menus and documentation
2026-03-06 16:03:20 -08:00
f2fdde5ba4
fix: show user-modified skills count in hermes update output
2026-03-06 16:14:43 -08:00
4f56e31dc7
fix: track origin hashes in skills manifest to preserve user modifications
2026-03-06 16:13:47 -08:00
6d3804770c
Merge pull request #552 from NousResearch/feat/insights
2026-03-06 16:00:28 -08:00
ab0f4126cf
fix: restore all removed bundled skills + fix skills sync system
2026-03-06 15:57:12 -08:00
1755a9e38a
Design agent migration skill for Hermes Agent from OpenClaw | Run successful dry tests with reports
2026-03-06 15:12:45 -08:00
585f8528b2
fix: deep review — prefix matching, tool_calls extraction, query perf, serialization
2026-03-06 14:50:57 -08:00
75f523f5c0
fix: unknown/custom models get zero cost instead of fake estimates
2026-03-06 14:18:19 -08:00
68fbae5692
docs: add Custom & Self-Hosted LLM Providers guide
2026-03-06 14:15:57 -08:00
80f1dd8d37
docs: add Custom & Self-Hosted LLM Providers guide
2026-03-06 14:15:57 -08:00
b52b37ae64
feat: add /insights command with usage analytics and cost estimation
2026-03-06 14:04:59 -08:00
566aeaeefa
Make skill file writes atomic
2026-03-07 00:49:10 +03:00
7a0544ab57
fix: three small inconsistencies across cron, gateway, and daytona
2026-03-06 16:52:17 +03:00
d63b363cde
refactor: extract atomic_json_write helper, add 24 checkpoint tests
2026-03-06 05:50:12 -08:00
c05c60665e
Merge PR #298 : Make process_registry checkpoint writes atomic
2026-03-06 05:32:35 -08:00
b4873a5de7
fix(setup): Escape skips instead of exiting, add control hints to all prompts
2026-03-06 05:27:11 -08:00
913f8ce0a5
Merge PR #297 : Make batch_runner checkpoint incremental and atomic
2026-03-06 05:16:31 -08:00
453e0677d6
fix: use regex for search output parsing to handle Windows drive-letter paths
2026-03-06 15:54:33 +03:00
4a63737227
Merge PR #433 : fix(whatsapp): replace Linux-only fuser with cross-platform port cleanup
2026-03-06 04:52:25 -08:00
3e93db16bd
Merge PR #436 : fix: use _max_tokens_param in max-iterations retry path
2026-03-06 04:46:24 -08:00
f863a42351
Merge PR #441 : fix(gateway): return response from /retry handler instead of discarding it
2026-03-06 04:42:54 -08:00
dc55f493be
fix: add missing re.DOTALL to DeepSeek V3.1 parser (same bug as V3)
2026-03-06 04:41:47 -08:00
936fda3f9e
Merge PR #444 : fix: add missing re.DOTALL flag to DeepSeek V3 tool call parser
2026-03-06 04:39:53 -08:00
ecb8148a9f
Merge PR #448 : fix(cli): use correct dict key for codex auth file path in status output
2026-03-06 04:34:46 -08:00
teknium1