Adapted from PR #19188 by @LeonSGP43 — mocks cli_output helpers and
verifies interactive_setup persists credentials to .env without
crashing. Also adds megastary to AUTHOR_MAP.
The Teams adapter's interactive_setup() tried to import prompt,
prompt_yes_no, print_info, print_success, and print_warning from
hermes_cli.config, but those helpers live in hermes_cli.cli_output.
Only get_env_value/save_env_value live in hermes_cli.config.
This caused 'hermes setup' to crash with ImportError as soon as the
user picked Teams in the messaging-platforms wizard.
Split the import accordingly.
Per https://platform.claude.com/docs/en/build-with-claude/fast-mode:
"Fast mode is currently supported on Opus 4.6 only. Sending speed: fast
with an unsupported model returns an error."
Pre-fix, _is_anthropic_fast_model() returned True for any claude-* model,
so /fast on Opus 4.7 (or Sonnet/Haiku) would persist agent.service_tier=fast
in config.yaml and the adapter would inject extra_body["speed"] = "fast"
on every subsequent request. Opus 4.7 returns:
HTTP 400: 'claude-opus-4-7' does not support the `speed` parameter.
This wedged sessions across model upgrades (a user who ran /fast on Opus 4.6
and later switched the default model to 4.7 hit a hard 400 on every turn
until they manually edited config.yaml).
Changes:
- _is_anthropic_fast_model: gate on "opus-4-6" / "opus-4.6" only
- anthropic_adapter: add _supports_fast_mode predicate as defensive guard
so stale request_overrides on an unsupported model are dropped silently
instead of 400'ing
- Tests: flip the assertions that mirrored the bug (Sonnet/Haiku/Opus 4.7
asserting fast-mode support) to match the documented API contract
Commit 408dd8aa added a non-string guard for Pass 1 (dedup), but the same
pattern exists in Pass 2 (summarization/pruning) where content.startswith()
and len() are called on potentially non-string tool content.
When a provider returns tool results with non-string content (e.g. dict or
int from llama.cpp or similar), the pruning pass crashes with AttributeError.
Add the same isinstance(content, str) guard to Pass 2 for consistency.
Steers custom tool creation toward the plugin route by default.
The adding-tools.md guide is now explicitly for built-in core Hermes
tools only.
Key fixes:
- Plugin quickstart: ctx.register_tool() now uses correct keyword-arg
API (name=, toolset=, schema=, handler=) instead of broken 3-arg call
- Handler signature: (params, **kwargs) instead of (params)
- Handler return: json.dumps({...}) instead of plain string
- AGENTS.md: mentions plugin route before built-in tool instructions
- learning-path.md: plugins listed before core tool development
- contributing.md: separates plugin vs core tool paths
Based on PR #13138 by @helix4u.
On VPS/Docker and some Ubuntu 23.10+ hosts, Chromium refuses to start
without --no-sandbox:
- uid=0 (root): hard requirement (VPS/Docker deployments)
- AppArmor apparmor_restrict_unprivileged_userns=1 (Ubuntu 23.10+):
non-root too, under systemd or unprivileged containers
Detect both conditions and inject AGENT_BROWSER_CHROME_FLAGS with
--no-sandbox --disable-dev-shm-usage when the user hasn't already
set the flags themselves.
Salvage of #15771 — only the browser_tool.py fix is cherry-picked.
The PR's accompanying MCP preset addition (new feature surface)
was dropped so the bug fix can land independently.
Co-authored-by: ygd58 <buraysandro9@gmail.com>
Prevents pre-existing TWILIO_PHONE_NUMBER or SMS_WEBHOOK_URL values in
the outer test environment from leaking into the assertion context.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Clear inherited provider preference filters when delegation.provider is set so delegated children do not route back to the parent provider. Add a regression test for cross-provider delegation with parent OpenRouter filters.
Closes#10653
Closes#16082.
`hermes status` silently omitted four widely-used LLM providers
(Google/Gemini, DeepSeek, xAI/Grok, NVIDIA NIM) from the API Keys
and API-Key Providers sections. Add them, along with tuple-valued
env var support (first found wins) so Google can accept either
GOOGLE_API_KEY or GEMINI_API_KEY.
Also deduplicates the "NVIDIA" and "NVIDIA NIM" rows that were
both pointing at NVIDIA_API_KEY.
Salvage of #16159 (core behavior preserved + NVIDIA dedup fixup
on top of the tuple-support refactor).
Co-authored-by: briandevans <252620095+briandevans@users.noreply.github.com>
When a delegation child session (e.g. source='telegram') contains the
FTS5 hit but _resolve_to_parent() maps it to a different root session
(source='api_server'), the result entry was still reporting the child's
source because the loop discarded session_meta as `_` and fell back to
match_info.get('source'), which carries the child session's value.
Use the resolved parent's session_meta for source, model, and started_at
with match_info as a fallback, so the output accurately reflects the
session the user actually interacted with.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`updates.backup_keep: 0` (or any negative value) wiped the freshly-
created pre-update zip:
_prune_pre_update_backups(backup_dir, keep=0):
backups = sorted(..., reverse=True) # newest first, includes
# the zip we just wrote
for p in backups[0:]: # = all of them
p.unlink()
The wrapper in `main.py` then printed `Saved: <path>` for a file that
no longer existed (the size lookup is wrapped in `try/except OSError`
which silently degrades to "0 B"), leaving operators believing they had
a recovery point when they had none.
This is a real footgun because some config systems treat 0 as "keep
unlimited"; here it does the opposite — every backup is destroyed
right after creation.
Fix: clamp `keep` to a minimum of 1 inside `_prune_pre_update_backups`
since that helper is only invoked immediately after a fresh backup
is written. Operators who genuinely want no backups should set
`updates.pre_update_backup: false` (which gates creation entirely)
rather than relying on `backup_keep: 0`.
Also extends the `backup_keep` config docstring to spell out the floor
and point at `pre_update_backup: false` as the off-switch.
## Tests
Three regression tests added in `TestPreUpdateBackup`:
- `test_keep_zero_does_not_delete_freshly_created_backup` —
asserts the file persists after `keep=0`
- `test_keep_negative_does_not_delete_freshly_created_backup` —
same for negative values
- `test_keep_zero_still_prunes_older_backups` — proves the floor
only protects the new backup; older ones are still rotated out
Verified the new tests fail on origin/main (without the floor) and
pass with it; full `tests/hermes_cli/test_backup.py` suite green
(84 tests).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Gemini's OpenAI-compatibility endpoint strictly requires the `name` field
on `role: tool` messages — it returns HTTP 400 ("Request contains an
invalid argument") when the function name is missing. OpenAI/Anthropic/
ollama tolerate the absence, so the gap stays invisible until the
conversation accumulates a tool turn and the user routes it through Gemini
(direct API or via ollama-cloud proxy).
Fix: add a `_get_tool_call_name_static()` helper alongside the existing
`_get_tool_call_id_static()`, and populate `name` at every site that
constructs a `role: tool` message — the pre-call sanitizer stub, the
tool-call args repair marker, both interrupt-skip paths, both
result-append paths (parallel + sequential), the invalid-tool-name
recovery, the invalid-JSON-args recovery, and the exception fallback.
Each call site was already in scope of the function name (`function_name`,
`skipped_name`, `name`, or a dict tool_call), so the change is local —
no new lookups, no behavior change for providers that already worked.
Fixes#16478
Keep the configured vision provider when base_url is overridden so credential-pool lookup still resolves provider-specific API keys (e.g. ZAI_API_KEY), and add a regression test for this path.
Generic 400 and server-disconnect heuristics used absolute token/message-count fallbacks that are too aggressive for 1M context sessions. Gate those absolute fallbacks to smaller context windows while preserving relative pressure checks.
Fixes#16351
Reverts ff3d2773e2. Teknium reviewed the merged PR and decided this
behavior isn't wanted — tool-driven kanban_create should not mirror
the slash-command path's auto-subscribe. Orchestrators that want
their originating chat notified can call kanban_notify-subscribe
explicitly; we're not going to make it implicit.
Closes#19479.
When an orchestrator agent calls kanban_create from a gateway session
(e.g. a Telegram user delegating to an orchestrator profile), auto-
subscribe the originating (platform, chat, thread, user) to the new
task's terminal events. Mirrors the behavior of the /kanban create
slash command in gateway/run.py so tool-driven creation is at parity
with human-driven creation.
Without this, a user who interacts with an orchestrator exclusively
via the gateway never receives blocked / completed / gave_up
notifications for tasks the orchestrator created on their behalf —
silently breaking the gateway-first multi-agent flow the reporter
describes.
Reads the context-local HERMES_SESSION_* vars via get_session_env()
(not os.environ — those are contextvars for asyncio concurrency
safety). Falls through cleanly in CLI / cron contexts with no
session active (subscribed=False in the response). Best-effort: if
the gateway module isn't importable (test rigs stubbing gateway.*),
the task still creates, we just skip the subscription.
Response gains a 'subscribed' bool so the orchestrator knows whether
terminal events will land back in the originating chat or whether it
needs to poll / unblock manually.
Tests: 4 new in tests/tools/test_kanban_tools.py covering
CLI/no-subscribe, telegram/gateway-auto-subscribe, discord-DM/no-
thread subscribe, and partial-ctx/no-chat_id no-subscribe. 40/40
kanban tool tests pass.
Open-weight models (DeepSeek, Qwen, GLM) sometimes emit tool calls like
`{"urls": "https://a.com"}` when the tool schema declares
`type: array`. The call was JSON-valid but semantically wrong, and
`coerce_tool_args` would pass the bare string through — the tool then
failed with a confusing type error.
`coerce_tool_args` now wraps non-list, non-null values in a
single-element list when the schema declares `array`. Strings still go
through `_coerce_value` first so JSON-encoded arrays
(`'["a","b"]'`) parse correctly and nullable `"null"` still
becomes `None`. `None` itself is preserved — tools with sensible
defaults already handle it, and we don't want to silently mask a
deliberate null.
Salvaged from #19652 (NikolayGusev-astra) — the broader validate-then-
repair layer had several issues (duplicated existing coercion,
mis-classified `old_string` as a path field, prepended non-JSON
prefixes to tool results that break downstream JSON parsing, hardcoded
offset/limit defaults unsuitable for non-read_file tools). The one
genuinely new capability is wrapping bare scalars, which is implemented
here directly inside the existing coercion path.
Co-authored-by: Nikolay Gusev <ngusev@astralinux.ru>
ENV-assignment and JSON-field regex patterns in redact_sensitive_text()
cause false positives when reading source code files:
- MAX_TOKENS=*** triggers the ENV assignment pattern
- "apiKey": "test" in test fixtures triggers the JSON field pattern
Add code_file=False parameter. When code_file=True, skip only the
ENV-assignment and JSON-field regex passes; all other patterns (prefixes,
auth headers, private keys, DB connstrings, JWTs, URL secrets) are
still applied.
Update file_tools.py (read_file and search_files) to pass code_file=True
so agent code analysis is not polluted by false-positive redactions.
Closes#15934
Mirrors the Codex auto-import UX. On successful Nous login (either
`hermes auth add nous --type oauth` or `hermes login nous`), tokens are
mirrored to `$HERMES_SHARED_AUTH_DIR/nous_auth.json` (default
`~/.hermes/shared/nous_auth.json`, outside any named profile's
HERMES_HOME). On next login in a new profile, the flow offers to import
those credentials ("Import these credentials? [Y/n]") and rehydrates via
a forced refresh+mint instead of running the full device-code flow.
Runtime refresh in any profile syncs the rotated refresh_token back to
the shared store so sibling profiles don't hit stale-token fallback
after rotation.
The volatile 24h agent_key is NOT persisted to the shared store —
only the long-lived OAuth tokens are cross-profile useful.
- `HERMES_SHARED_AUTH_DIR` env var for tests + custom layouts
- Pytest seat belt mirrors the existing `_auth_file_path` guard so
forgetting to redirect the store in a test fails loudly
- File mode 0600 where platform supports it
- Runtime credential resolution is unchanged — shared store is only
consulted during the login flow, so profile isolation at runtime is
preserved
- Stale refresh_token + portal-down cases gracefully fall back to
device-code
Addresses a user report from Mike Nguyen: running
`hermes --profile <name> auth add nous --type oauth` for every new
profile is unnecessary friction now that Codex has a shared-import
flow via `~/.codex/auth.json`.
Broadens the existing fallback (previously only fired for
Photo_invalid_dimensions) to cover every send_photo exception class:
rate limits, corrupt file markers, format edge cases. The expected
dimension case still logs at INFO (document is the right path); all
other cases log at WARNING with exc_info so they're visible in logs.
If send_document itself fails, we still fall back to the base adapter's
text-only 'Image: /path' rendering as a last resort.
Salvage of #15837 — original PR author QifengKuang proposed the broader
try/except-style fallback. Adapted to keep the existing INFO-vs-WARNING
log split for dimension errors (the expected case).
Co-authored-by: QifengKuang <k2767567815@gmail.com>
Closes#19534 (security).
A worker spawned by the kanban dispatcher has HERMES_KANBAN_TASK set
to its own task id. The destructive tools (kanban_complete,
kanban_block, kanban_heartbeat) resolved task_id via
_default_task_id() which preferred an explicit arg over the env var,
with no ownership check — so a buggy or prompt-injected worker could
complete / block / heartbeat any OTHER task (sibling, cross-tenant,
anything) by supplying its id. Reporter's repro: worker for t_A
passed task_id=t_B to kanban_complete and got {"ok": true}.
Fix: add _enforce_worker_task_ownership(tid). If HERMES_KANBAN_TASK
is set and tid doesn't match, return a structured tool error with
guidance to use kanban_comment (for information handoff across tasks)
or kanban_create (for follow-up work). Orchestrator profiles (no env
var, but kanban toolset enabled per #18968) are exempt — their job
is routing and sometimes includes closing out child tasks.
Kept unrestricted (deliberately):
- kanban_show — workers legitimately read parent/sibling handoff context
- kanban_comment — cross-task comments are the handoff mechanism
- kanban_create — orchestrator fan-out, worker follow-up spawning
- kanban_link — parent/child linking
Tests: 5 new regression tests in tests/tools/test_kanban_tools.py
covering the grid (worker-attacks-foreign ×3 tools, worker-own-task
preserved, orchestrator-unrestricted). 36/36 pass.
The background memory/skill review fork had two user-visible issues:
1. max_iterations=8 was too tight for multi-step reviews. A review that
needs to skill_view one or two candidate skills, add a memory entry,
and patch a skill routinely blew the budget — surfacing an 'Iteration
budget exhausted (8/8)' warning to the user and leaving the review
half-finished.
2. Mid-review lifecycle messages leaked into the user's terminal past the
existing quiet_mode + redirect_stdout/stderr guards. _emit_status and
_emit_warning route through _vprint(force=True) -> _print_fn /
status_callback, which bypass sys.stdout entirely. The stdout redirect
only catches raw print() calls.
Changes:
- Bump the review fork's max_iterations from 8 to 16.
- Set review_agent.suppress_status_output = True on the fork. This
short-circuits _vprint unconditionally so _emit_status/_emit_warning
emissions (iteration-budget warnings, rate-limit retries, compression
messages) never reach the user. The only user-visible output remains
the compact final summary line ('💾 Self-improvement review: ...')
which is printed via self._safe_print on the *main* agent (outside
the fork's redirect/suppress scope).
Summarizer filter is already correct — _summarize_background_review_actions
only surfaces tool calls with data.get('success') is truthy, so failed
attempts and reasoning text never reach the summary line.
Instead of an unhelpful CalledProcessError traceback when running
`hermes gateway start/stop/restart` without first installing the service,
check for the unit file and exit with an actionable install hint.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(achievements): share card render on unlocked badges
Adds a Share button to each unlocked achievement card that opens a
modal and renders a 1200x630 PNG share card client-side via Canvas2D
(no backend, no network, no new deps). Two actions: Download PNG and
Copy image to clipboard.
Card layout mirrors the in-dashboard visual language: tier-colored
glow, icon from the existing LUCIDE sprite set, achievement name,
tier badge pill, description, progress stat line, and a Hermes Agent
watermark. Sized for X/Twitter, Discord, LinkedIn, Bluesky link
previews.
Vendored on top of the upstream @PCinkusz bundle; the 'in-progress
scan banner' precedent already established this divergence pattern.
Manifest bumped 0.3.1 -> 0.4.0.
* feat(achievements): share-on-X as primary action on share dialog
Adds a 'Share on X' button as the primary action in the share dialog.
Opens https://x.com/intent/post with a pre-filled tweet referencing
the achievement name, tier, @NousResearch, and the Hermes docs URL.
Copy image and Download PNG become secondary actions: users who want
the badge attached can Copy image, paste into the X composer, post.
Primary button styled as X's signature black-on-white fill so the
action is unambiguous.
When run_conversation encounters a non-retryable client error (401, 400,
etc.), it returns a dict with failed=True instead of raising. The gateway's
_run_and_close only branched on exceptions, so it always emitted run.completed
even for failed runs — clients could not distinguish success from failure.
Inspect the result dict before emitting: if failed=True, emit run.failed
with the error message; otherwise emit run.completed as before. The existing
except Exception path is unchanged for genuine programming errors.
Fixes#15561
Followup to #19653. The feature PR updated the Kanban user guide but
missed four other pages that document the same surface. Caught when
Teknium asked 'did you add docs to the guide and any other kanban
related docs around this?'.
- reference/cli-commands.md: rewrite the `hermes kanban` section to
document the `--board <slug>` global flag, the `boards`
subcommand group (list/create/switch/show/rename/rm), board
resolution order, and worked examples. Also fills in the
`create` / `complete` flag lists that had drifted from the
current CLI (`--summary`, `--metadata`, `--triage`,
`--idempotency-key`, `--max-runtime`, `--skill`).
- reference/environment-variables.md: add `HERMES_KANBAN_BOARD`
row, update `HERMES_KANBAN_DB` precedence note.
- reference/slash-commands.md: add `/kanban boards ...` and
`/kanban --board <slug> ...` to the two `/kanban` rows (CLI
table + gateway table).
- features/kanban-tutorial.md: the walkthrough uses the `default`
board, so just a note pointing readers at the overview's Boards
section if they want multiple queues, plus the corrected per-board
DB path.
Skill docs (devops-kanban-orchestrator, -worker) intentionally not
updated: those are agent-facing lifecycle playbooks and boards are
transparent to workers (HERMES_KANBAN_BOARD env var pins the DB
automatically), so there's nothing new for a worker to know.
Reporter of #19535 explicitly asked for a regression test — covers it
here so a future refactor of _set_status_direct can't silently re-enable
the direct ready/todo -> running bypass.
Asserts both: (a) HTTP 400 with 'running' in the detail message, and
(b) the task's status is unchanged after the rejected PATCH (pre-request
status preserved, no partial mutation).
The PATCH /tasks/:id endpoint allows setting status='running' via
_set_status_direct(), bypassing the dispatcher/claim path that creates
run rows, claim locks, expiry, and worker process metadata. This can
leave tasks stuck in 'running' with no active worker.
Fix: reject status='running' with HTTP 400, requiring all transitions
to 'running' to go through the canonical claim_task() path.
Closes#19535
The test 'test_inf_stays_string_for_integer_only' incorrectly asserted
that _coerce_number('inf') returns float('inf'), but the function
correctly returns the original string 'inf' because infinity is not
JSON-serializable.
Fixed the assertion to expect the string 'inf', and added two new tests
for negative infinity and NaN edge cases to improve coverage of the
non-JSON-serializable number guard in _coerce_number().
Follow-up to @changchun989's cherry-pick: reverts the validate-via-
normalize change so validate_profile_name remains a strict regex check
on the input AS-GIVEN. Callers that accept mixed-case user input
(dashboard UI, CLI args, import flows) call normalize_profile_name()
first, then validate the result. This keeps validate honest about
what the on-disk directory name must look like — e.g. ' jules '
(trailing whitespace) is now rejected instead of silently trimmed
and accepted.
- validate_profile_name: strict lowercase/regex check again, 'UPPER'
back in the invalid-names parametrize
- 8 call sites in profiles.py (create_profile, delete_profile,
set_active_profile, export_profile, import_profile, rename_profile,
resolve_profile_env, plus the clone_from branch): swap the
normalize-then-validate order
- scripts/release.py: add changchun989@proton.me -> changchun989 to
AUTHOR_MAP so CI doesn't block on the unmapped contributor email
All kanban + profile tests pass (268 across test_profiles.py +
test_kanban_db.py + test_kanban_core_functionality.py, plus 73 in
test_kanban_tools.py + test_kanban_dashboard_plugin.py).
Closes#18498.
- Add normalize_profile_name() for lowercase canonical IDs and Default alias
- Use canonical names in create/delete/rename/export/import/set_active paths
- Canonicalize Kanban assignee on create/assign, list filter, and worker spawn
- Tests for mixed-case assignees and profile resolution (fixes#18498)
`hermes import` was creating secret files with the process umask
(typically 0644) instead of 0600. zipfile.open() does not honor the
Unix mode bits stored in zip member external_attr; the restore loop
used open(target, "wb") which always falls back to umask.
Threat: silent privilege downgrade after a routine restore on
multi-user systems (shared dev boxes, CI runners, jump hosts) — any
local user could read API keys and OAuth tokens from ~/.hermes/.
Fix mirrors the convention already used at file creation
(hermes_cli/auth.py: stat.S_IRUSR | stat.S_IWUSR for auth.json).
The quick-snapshot restore path (restore_quick_snapshot) is
unaffected — it uses shutil.copy2 which preserves perms via
copystat().
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
