## What does this PR do?
The trajectory compressor could corrupt training trajectories by cutting a
conversation in the middle of a tool-call/tool-response pair. In the from/value
trajectory format a `tool` turn (carrying `<tool_response>` markers) is always
emitted immediately after the `gpt` turn whose `<tool_call>` it answers, so the
two turns must stay together. The compressible region's end boundary, however,
was chosen purely by token accumulation: the loop stopped at the first turn where
the accumulated tokens met the savings target, with no regard for turn roles. For
any over-budget trajectory whose savings boundary happened to land between a `gpt`
turn and its `tool` turn, the `gpt` (with its `<tool_call>`) was summarised away
into the replacement `human` message while the now-orphaned `tool` turn (with its
`<tool_response>`) was kept verbatim in the tail — producing an unmatched marker
and silently corrupting the training signal. The head boundary had the mirror
problem when the first tool turn was not protected.
This change snaps both compression boundaries to a clean turn boundary before the
region is extracted and replaced, so the summary always covers whole gpt+tool
blocks and a `tool` turn is never separated from the `gpt` turn that precedes it.
The boundary is moved forward when possible (folding an orphaned tool turn into
the region that already holds its gpt) and falls back to moving backward when no
clean boundary exists ahead, such as when the protected tail itself begins on a
tool turn.
## Related Issue
N/A
## Type of Change
- [x] 🐛 Bug fix (non-breaking change that fixes an issue)
## Changes Made
- `trajectory_compressor.py`: added `_is_boundary_clean()` and `_snap_boundary()`
helpers on `TrajectoryCompressor`, and applied them to both the head and tail
compression boundaries in `compress_trajectory()` and
`compress_trajectory_async()`. When snapping collapses the region to nothing
safe to compress, the trajectory is returned unchanged and flagged as still
over the limit rather than being corrupted.
- `tests/test_trajectory_compressor.py`: added `TestCompressionToolPairIntegrity`
covering the sync and async paths plus direct unit tests for the boundary
snapping (forward skip and backward fallback).
## How to Test
1. Run the focused tests: `pytest tests/test_trajectory_compressor.py -q`.
2. The new sync/async cases build a trajectory of gpt/tool pairs with an oversized
middle gpt turn and choose a token target that forces the accumulation
boundary to stop between a `<tool_call>` and its `<tool_response>`. They assert
that `<tool_call>` and `<tool_response>` markers stay balanced after
compression and that every kept `tool` turn is immediately preceded by a `gpt`
turn (never the inserted summary or another tool turn).
## Checklist
### Code
- [x] I've read the [Contributing Guide](https://github.com/NousResearch/hermes-agent/blob/main/CONTRIBUTING.md)
- [x] My commit messages follow [Conventional Commits](https://www.conventionalcommits.org/) (`fix(scope):`, `feat(scope):`, etc.)
- [x] I searched for [existing PRs](https://github.com/NousResearch/hermes-agent/pulls) to make sure this isn't a duplicate
- [x] My PR contains **only** changes related to this fix/feature (no unrelated commits)
- [x] I've run `pytest tests/ -q` and all tests pass
- [x] I've added tests for my changes (required for bug fixes, strongly encouraged for features)
- [x] I've tested on my platform: macOS 15 (Darwin 25.5)
### Documentation & Housekeeping
- [x] I've updated relevant documentation (README, `docs/`, docstrings) — or N/A
- [x] I've updated `cli-config.yaml.example` if I added/changed config keys — or N/A
- [x] I've updated `CONTRIBUTING.md` or `AGENTS.md` if I changed architecture or workflows — or N/A
- [x] I've considered cross-platform impact (Windows, macOS) per the [compatibility guide](https://github.com/NousResearch/hermes-agent/blob/main/CONTRIBUTING.md#cross-platform-compatibility) — or N/A
- [x] I've updated tool descriptions/schemas if I changed tool behavior — or N/A
1. trajectory_compressor.py: yaml.safe_load() returns None on empty
files, crashing with TypeError on `if 'tokenizer' in data`. Fix by
adding `or {}` fallback. (HIGH — blocks startup with empty config)
2. 6 files with fcntl.flock(LOCK_UN) in finally blocks without
try/except: cron/scheduler.py, hermes_cli/auth.py,
agent/shell_hooks.py, tools/skill_usage.py,
tools/environments/file_sync.py, tools/memory_tool.py. If unlock
raises OSError, fd.close() is skipped and the lock is held forever.
The msvcrt branches already had try/except; the fcntl branches did
not. Fix by wrapping in try/except (OSError, IOError): pass.
3. agent/copilot_acp_client.py line 639: TOCTOU race — path.exists()
followed by path.read_text() with no try/except. If file is deleted
between the check and the read, FileNotFoundError propagates. Fix
by using try/except FileNotFoundError.
4. gateway/sticker_cache.py: non-atomic write via Path.write_text()
can leave truncated JSON on crash, causing JSONDecodeError on next
load. Fix by writing to tempfile + fsync + os.replace (atomic).
Closes the last Python-on-Windows UTF-8 exposure by making every
text-mode open() call explicit about its encoding.
Before: on Windows, bare open(path, 'r') defaults to the system
locale encoding (cp1252 on US-locale installs). That means reading
any config/yaml/markdown/json file with non-ASCII content either
crashes with UnicodeDecodeError or silently mis-decodes bytes.
After: all 89 affected call sites in production code now pass
encoding='utf-8' explicitly. Works identically on every platform
and every locale, no surprise behavior.
Mechanical sweep via:
ruff check --preview --extend-select PLW1514 --unsafe-fixes --fix --exclude 'tests,venv,.venv,node_modules,website,optional-skills, skills,tinker-atropos,plugins' .
All 89 fixes have the same shape: open(x) or open(x, mode) became
open(x, encoding='utf-8') or open(x, mode, encoding='utf-8'). Nothing
else changed. Every modified file still parses and the Windows/sandbox
test suite is still green (85 passed, 14 skipped, 0 failed across
tests/tools/test_code_execution_windows_env.py +
tests/tools/test_code_execution_modes.py + tests/tools/test_env_passthrough.py +
tests/test_hermes_bootstrap.py).
Scope notes:
- tests/ excluded: test fixtures can use locale encoding intentionally
(exercising edge cases). If we want to tighten tests later that's
a separate PR.
- plugins/ excluded: plugin-specific conventions may differ; plugin
authors own their code.
- optional-skills/ and skills/ excluded: skill scripts are user-authored
and we don't want to mass-edit them.
- website/ and tinker-atropos/ excluded: vendored / generated content.
46 files touched, 89 +/- lines (symmetric replacement). No behavior
change on POSIX or on Windows when the file is ASCII; bug fix on
Windows when the file contains non-ASCII.
Mechanical cleanup across 43 files — removes 46 unused imports
(F401) and 14 unused local variables (F841) detected by
`ruff check --select F401,F841`. Net: -49 lines.
Also fixes a latent NameError in rl_cli.py where `get_hermes_home()`
was called at module line 32 before its import at line 65 — the
module never imported successfully on main. The ruff audit surfaced
this because it correctly saw the symbol as imported-but-unused
(the call happened before the import ran); the fix moves the import
to the top of the file alongside other stdlib imports.
One `# noqa: F401` kept in hermes_cli/status.py for `subprocess`:
tests monkeypatch `hermes_cli.status.subprocess` as a regression
guard that systemctl isn't called on Termux, so the name must
exist at module scope even though the module body doesn't reference
it. Docstring explains the reason.
Also fixes an invalid `# noqa:` directive in
gateway/platforms/discord.py:308 that lacked a rule code.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Kimi's gateway selects the correct temperature server-side based on the
active mode (thinking -> 1.0, non-thinking -> 0.6). Sending any
temperature value — even the previously "correct" one — conflicts with
gateway-managed defaults.
Replaces the old approach of forcing specific temperature values (0.6
for non-thinking, 1.0 for thinking) with an OMIT_TEMPERATURE sentinel
that tells all call sites to strip the temperature key from API kwargs
entirely.
Changes:
- agent/auxiliary_client.py: OMIT_TEMPERATURE sentinel, _is_kimi_model()
prefix check (covers all kimi-* models), _fixed_temperature_for_model()
returns sentinel for kimi models. _build_call_kwargs() strips temp.
- run_agent.py: _build_api_kwargs, flush_memories, and summary generation
paths all handle the sentinel by popping/omitting temperature.
- trajectory_compressor.py: _effective_temperature_for_model returns None
for kimi (sentinel mapped), direct client calls use kwargs dict to
conditionally include temperature.
- mini_swe_runner.py: same sentinel handling via wrapper function.
- 6 test files updated: all 'forces temperature X' assertions replaced
with 'temperature not in kwargs' assertions.
Net: -76 lines (171 added, 247 removed).
Inspired by PR #13137 (@kshitijk4poor).
Follow up salvaged PR #12668 by threading base_url through the
remaining direct-call sites so kimi-k2.5 uses temperature=1.0 on
api.moonshot.ai and keeps 0.6 on api.kimi.com/coding. Add focused
regression tests for run_agent, trajectory_compressor, and
mini_swe_runner.
Adds Arcee AI as a standard direct provider (ARCEEAI_API_KEY) with
Trinity models: trinity-large-thinking, trinity-large-preview, trinity-mini.
Standard OpenAI-compatible provider checklist: auth.py, config.py,
models.py, main.py, providers.py, doctor.py, model_normalize.py,
model_metadata.py, setup.py, trajectory_compressor.py.
Based on PR #9274 by arthurbr11, simplified to a standard direct
provider without dual-endpoint OpenRouter routing.
Aligns MiniMax provider with official API documentation. Fixes 6 bugs:
transport mismatch (openai_chat -> anthropic_messages), credential leak
in switch_model(), prompt caching sent to non-Anthropic endpoints,
dot-to-hyphen model name corruption, trajectory compressor URL routing,
and stale doctor health check.
Also corrects context window (204,800), thinking support (manual mode),
max output (131,072), and model catalog (M2 family only on /anthropic).
Source: https://platform.minimax.io/docs/api-reference/text-anthropic-api
Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
Automated dead code audit using vulture + coverage.py + ast-grep intersection,
confirmed by Opus deep verification pass. Every symbol verified to have zero
production callers (test imports excluded from reachability analysis).
Removes ~1,534 lines of dead production code across 46 files and ~1,382 lines
of stale test code. 3 entire files deleted (agent/builtin_memory_provider.py,
hermes_cli/checklist.py, tests/hermes_cli/test_setup_model_selection.py).
Co-authored-by: alt-glitch <balyan.sid@gmail.com>
Comprehensive cleanup across 80 files based on automated (ruff, pyflakes, vulture)
and manual analysis of the entire codebase.
Changes by category:
Unused imports removed (~95 across 55 files):
- Removed genuinely unused imports from all major subsystems
- agent/, hermes_cli/, tools/, gateway/, plugins/, cron/
- Includes imports in try/except blocks that were truly unused
(vs availability checks which were left alone)
Unused variables removed (~25):
- Removed dead variables: connected, inner, channels, last_exc,
source, new_server_names, verify, pconfig, default_terminal,
result, pending_handled, temperature, loop
- Dropped unused argparse subparser assignments in hermes_cli/main.py
(12 instances of add_parser() where result was never used)
Dead code removed:
- run_agent.py: Removed dead ternary (None if False else None) and
surrounding unreachable branch in identity fallback
- run_agent.py: Removed write-only attribute _last_reported_tool
- hermes_cli/providers.py: Removed dead @property decorator on
module-level function (decorator has no effect outside a class)
- gateway/run.py: Removed unused MCP config load before reconnect
- gateway/platforms/slack.py: Removed dead SessionSource construction
Undefined name bugs fixed (would cause NameError at runtime):
- batch_runner.py: Added missing logger = logging.getLogger(__name__)
- tools/environments/daytona.py: Added missing Dict and Path imports
Unnecessary global statements removed (14):
- tools/terminal_tool.py: 5 functions declared global for dicts
they only mutated via .pop()/[key]=value (no rebinding)
- tools/browser_tool.py: cleanup thread loop only reads flag
- tools/rl_training_tool.py: 4 functions only do dict mutations
- tools/mcp_oauth.py: only reads the global
- hermes_time.py: only reads cached values
Inefficient patterns fixed:
- startswith/endswith tuple form: 15 instances of
x.startswith('a') or x.startswith('b') consolidated to
x.startswith(('a', 'b'))
- len(x)==0 / len(x)>0: 13 instances replaced with pythonic
truthiness checks (not x / bool(x))
- in dict.keys(): 5 instances simplified to in dict
- Redefined unused name: removed duplicate _strip_mdv2 import in
send_message_tool.py
Other fixes:
- hermes_cli/doctor.py: Replaced undefined logger.debug() with pass
- hermes_cli/config.py: Consolidated chained .endswith() calls
Test results: 3934 passed, 17 failed (all pre-existing on main),
19 skipped. Zero regressions.
The AsyncOpenAI client was created once at __init__ and stored as an
instance attribute. process_directory() calls asyncio.run() which creates
and closes a fresh event loop. On a second call, the client's httpx
transport is still bound to the closed loop, raising RuntimeError:
"Event loop is closed" — the same pattern fixed by PR #3398 for the
main agent loop.
Create the client lazily in _get_async_client() so each asyncio.run()
gets a client bound to the current loop.
Co-authored-by: binhnt92 <binhnt.ht.92@gmail.com>
dict.get(key, default) returns None — not the default — when the key IS
present but explicitly set to null/~ in YAML. Calling .lower() on that
raises AttributeError.
Use (config.get(key) or fallback) so both missing keys and explicit nulls
coalesce to the intended default.
Files fixed:
- tools/tts_tool.py — _get_provider()
- tools/web_tools.py — _get_backend()
- tools/mcp_tool.py — MCPServerTask auth config
- trajectory_compressor.py — _detect_provider() and config loading
Co-authored-by: dieutx <dangtc94@gmail.com>
Normalize summary-model content before stripping so empty or non-string
responses do not trigger retry/fallback paths. Adds sync and async
regression tests for None content.
Add centralized call_llm() and async_call_llm() functions that own the
full LLM request lifecycle:
1. Resolve provider + model from task config or explicit args
2. Get or create a cached client for that provider
3. Format request args (max_tokens handling, provider extra_body)
4. Make the API call with max_tokens/max_completion_tokens retry
5. Return the response
Config: expanded auxiliary section with provider:model slots for all
tasks (compression, vision, web_extract, session_search, skills_hub,
mcp, flush_memories). Config version bumped to 7.
Migrated all auxiliary consumers:
- context_compressor.py: uses call_llm(task='compression')
- vision_tools.py: uses async_call_llm(task='vision')
- web_tools.py: uses async_call_llm(task='web_extract')
- session_search_tool.py: uses async_call_llm(task='session_search')
- browser_tool.py: uses call_llm(task='vision'/'web_extract')
- mcp_tool.py: uses call_llm(task='mcp')
- skills_guard.py: uses call_llm(provider='openrouter')
- run_agent.py flush_memories: uses call_llm(task='flush_memories')
Tests updated for context_compressor and MCP tool. Some test mocks
still need updating (15 remaining failures from mock pattern changes,
2 pre-existing).
Route all remaining ad-hoc auxiliary LLM call sites through
resolve_provider_client() so auth, headers, and API format (Chat
Completions vs Responses API) are handled consistently in one place.
Files changed:
- tools/openrouter_client.py: Replace manual AsyncOpenAI construction
with resolve_provider_client('openrouter', async_mode=True). The
shared client module now delegates entirely to the router.
- tools/skills_guard.py: Replace inline OpenAI client construction
(hardcoded OpenRouter base_url, manual api_key lookup, manual
headers) with resolve_provider_client('openrouter'). Remove unused
OPENROUTER_BASE_URL import.
- trajectory_compressor.py: Add _detect_provider() to map config
base_url to a provider name, then route through
resolve_provider_client. Falls back to raw construction for
unrecognized custom endpoints.
- mini_swe_runner.py: Route default case (no explicit api_key/base_url)
through resolve_provider_client('openrouter') with auto-detection
fallback. Preserves direct construction when explicit creds are
passed via CLI args.
- agent/auxiliary_client.py: Fix stale module docstring — vision auto
mode now correctly documents that Codex and custom endpoints are
tried (not skipped).
These two files were creating bare OpenAI clients pointing at OpenRouter
without the HTTP-Referer / X-OpenRouter-Title / X-OpenRouter-Categories
headers that the rest of the codebase sends for app attribution.
- skills_guard.py: LLM audit client (always OpenRouter)
- trajectory_compressor.py: sync + async summarization clients
(guarded with 'openrouter' in base_url check since the endpoint
is user-configurable)
- Updated `trajectory_compression.yaml` to include a new `per_trajectory_timeout` setting, allowing for a timeout of 300 seconds per trajectory. This enhancement helps prevent hanging on problematic entries during processing, improving overall reliability and efficiency in trajectory handling.
- Updated the main function to accept both single JSONL files and directories for compression.
- Added support for sampling a percentage of trajectories before compression.
- Improved usage documentation with detailed examples for various compression scenarios.
- Enhanced error handling for input validation and dry run mode.
- Streamlined output handling to manage temporary files during processing.
- Introduced mini_swe_runner.py for executing tasks using mini-swe-agent environments (local, Docker, Modal) and outputting trajectories in Hermes format.
- Implemented trajectory_compressor.py to post-process agent trajectories, compressing them within a target token budget while preserving essential content.
- Added trajectory_compression.yaml configuration file for customizable compression settings.
- Created sample_and_compress.py script to download, sample, and compress trajectories from HuggingFace datasets.
- Enhanced logging and error handling across new modules for improved usability and debugging.
