Follow-ups for the consolidated salvage:
- Memoize the config.yaml-derived timeout on the file's mtime_ns so the
rebuild-on-timeout-change check from PR #57437 costs one stat() per
get_honcho_client() call instead of a full YAML load on the hot path.
- hermes honcho status now displays the host-block-resolved
dialecticCadence (remnant from PR #63776, whose runtime fix landed
in #62290).
- AUTHOR_MAP entries for the salvaged contributor emails.
- Make the config imports lazy inside _auto_title_enabled(), matching the
existing _title_language() pattern (title_generator is imported from agent
code paths where a module-level hermes_cli import risks circularity).
- Check the enabled flag after the cheap first-exchange guard in
maybe_auto_title so config isn't read on every turn of a long session.
- Repoint the two new tests at the real import site.
- Document the key in cli-config.yaml.example and merge the enabled flag
into the existing title_generation block in configuration.md.
- AUTHOR_MAP entry for the contributor.
* fix: detect env-var-configured providers absent from PROVIDER_REGISTRY
is_provider_explicitly_configured() only checked PROVIDER_REGISTRY (a
manually-maintained dict) for env-var names. Providers that exist solely
in the models.dev catalog — e.g. openrouter — were never recognised as
explicitly configured, so they were filtered out of the desktop model
picker even when their API key was set in .env.
Add a fallback to get_provider() (which reads the models.dev catalog)
when PROVIDER_REGISTRY returns None. Both ProviderConfig and ProviderDef
expose .auth_type and .api_key_env_vars with the same shape.
* test: keep OpenRouter provider gate assertion behavioral
* chore(release): map salvaged OpenRouter contributor
---------
Co-authored-by: zzpigpinggai <zzpigpinggai@users.noreply.github.com>
Add the flag-gated compute-host supervisor, delta/control protocol, PPID orphan guard, inline fail-open path, synthetic GIL-heavy turn seam, and AC-4 certify harness.
Verified on current origin/main: 343 focused tests pass; Ruff and diff checks pass; 360s AC-4 run with six heavy lanes passes at 6.11ms serving p99 with zero stalls and valid load.
Co-authored-by: Kyzcreig <9063726+Kyzcreig@users.noreply.github.com>
The salvaged choices list predates the max/ultra effort levels (#62650);
add them so the Discord dropdown matches the canonical ladder. Discord
caps choices at 25 — we're at 11, plenty of headroom.
_clean_reasoning_effort kept its own whitelist that stopped at 'max',
silently dropping 'ultra' from MoA slot configs. Route it through
hermes_constants.parse_reasoning_effort — the same one-source-of-truth
fix the salvaged commit applies to the gateway — so future effort
levels can't drift here either. Docs updated to list ultra.
Follow-up to salvaged PR #64012.
Follow-ups on top of the cherry-picked cluster commits:
- slack: scope-authoritative app-token read — get_secret() with a
narrow UnscopedSecretError fallback to os.getenv. Keeps @kohoj's
correct semantics (scoped profile can never silently inherit the
default profile's Socket Mode app) while fixing the regression where
the default-profile startup loop and background reconnect rebuild,
which call connect() unscoped under multiplex, would raise and
fail-loop. Supersedes the 'or os.getenv' variant from #64461 which
reintroduced the cross-profile fallback leak.
- test: unscoped-multiplex fallback regression test for connect().
- run.py: convert the last legacy self.adapters.get(source.platform)
site (_rename_discord_auto_thread) to _adapter_for_source(source)
so profile-routed Discord sources rename threads on the right
adapter (from #57417's sweep).
- AUTHOR_MAP entry for @aguung.
Follow-up on the salvaged #64611 commit: the original guard blocked the
install tree unconditionally, which would have broken the legitimate
'developing Hermes from a source clone' CLI flow (launching hermes inside
the repo and getting its AGENTS.md as project context).
Refined policy:
- resolve_context_cwd(): validates configured paths (missing dir -> None +
warning) but honors an EXPLICIT install-tree cwd verbatim — deliberate
user choice.
- build_context_files_prompt(): blocks only the cwd=None -> os.getcwd()
FALLBACK into the install tree, with a new allow_install_tree_fallback
param. system_prompt.py passes it for platform cli/tui (launch dir is
the user's real shell cwd there); desktop/gateway surfaces keep the
guard (their fallback dir is self-spawned, never user-picked).
- Warning log names the resolved dir and the terminal.cwd remedy.
E2E-verified all five scenarios: desktop fallback blocked, in-tree CLI dev
keeps AGENTS.md, explicit install-tree cwd honored, invalid TERMINAL_CWD
falls to None then blocked, normal workspace loads.
Follow-ups to @SAMBAS123's #64986 salvage:
- Replace the hardcoded token-platform set in _platform_has_bot_credential
with PLATFORM_TOKEN_ENV_NAMES, a shared canonical map in gateway/config.py
also used by the empty-token validation warning — one source of truth, so
future token platforms can't silently bypass the gate or drift between
the two sites.
- After secondary-profile startup, warn loudly for any platform skipped on
the primary that no secondary profile ended up serving: an enabled
platform with no credential anywhere is a config error, not a silent
no-op.
- AUTHOR_MAP entry for the salvaged commit's author email.
git diff on a lockfile is unreadable: npm reorders entries, rewrites
integrity hashes, and moves packages between nesting levels, so a
one-line package.json bump produces a thousand-line textual diff.
scripts/ci/lockfile_diff.py instead parses the `packages` map out of
both versions of every tracked package-lock.json (via `git show`),
reduces each to {install path: version}, and set-diffs the maps —
reorder/hash churn vanishes, leaving only actual version movement
(added / removed / updated, with nested dedup copies tracked
separately).
The lockfile-diff workflow posts the result as a Markdown table in a
PR comment gated behind a hidden marker: subsequent pushes PATCH the
existing comment instead of stacking new ones, and a push that reverts
all lockfile changes updates the comment to say so. Advisory only —
never fails on findings; fork PRs (read-only token) degrade to a
warning.
Wired through the ci.yml orchestrator with a new npm_lock lane in
classify_changes.py (fails open on .github/ changes per the existing
contract).
* fix(nix): fold makeWrapper line continuations into optionalStrings
When rev == null (any dirty-tree build), the empty optionalString
expansion left the previous line's trailing backslash dangling onto a
blank line, ending the makeWrapper command early and running
`--suffix PYTHONPATH ...` as its own shell command (`--suffix: command
not found`, exit 127). Clean trees passed CI; dirty trees with
extraPythonPackages failed — exactly the path the NixOS module
exercises.
The continuation now lives inside each optionalString (" \\\n --set
..."), so the makeWrapper chain stays intact whether or not the
optional flags expand.
Verified by building with rev = null + extraPythonPackages =
[ pyfiglet ]: wrapper builds, PYTHONPATH suffix lands inside the
makeWrapper call, wrapped `hermes --version` runs, and the collision
check still executes (certifi correctly rejected).
* perf(nix): filter derivation sources to shrink rebuild scope
Every derivation previously saw the whole repo, so any file change
rebuilt everything. Each derivation now gets a filtered src with only
the files it consumes:
- lib.nix: derive npm workspace topology from the root package.json
`workspaces` globs (single source of truth — a new workspace member
is picked up with zero nix edits). pythonSrc (cleanSourceWith)
excludes the JS workspace trees, docs/website, docker/.github,
tests, nix/, flake.nix/flake.lock, root docs, and skills/ +
optional-skills/. importNpmLock reads from a fileset-filtered
npmRoot (root manifests + member package.jsons only).
- mkNpmPassthru takes `dirs` — the workspace dirs the package
contains — and builds a per-package fileset src from them. web and
desktop include apps/shared (file: dep). One shared
`nix run .#update-npm-lockfile` replaces the per-package
update_*_lockfile bins that only existed inside build sandboxes.
- python.nix: release venv loads the uv2nix workspace from pythonSrc.
The editable venv keeps an unfiltered ./.. root —
mkEditablePyprojectOverlay calls lib.path.splitRoot, which rejects
a cleanSourceWith set, and the editable install reads the live
checkout anyway.
- hermes-agent.nix: skills ship exclusively via HERMES_BUNDLED_SKILLS
/ HERMES_OPTIONAL_SKILLS (same mechanism as Homebrew packaging;
setup.py's _data_file_tree returns [] for missing dirs), so
SKILL.md edits no longer rebuild the venv. optional-mcps stays in
the wheel — pyproject.toml lists its manifests as explicit
data-files. Bundled assets are symlinked instead of copied, making
the wrapper drv near-instant when only an input changed.
__pycache__ filtered from bundled skills.
- checks.nix: find -L through the new symlinks; assert
optional-skills presence + HERMES_OPTIONAL_SKILLS in the wrapper.
- run_tests.sh: fall back to $HERMES_PYTHON when no local venv
exists, guarded by an `import pytest` probe (HERMES_PYTHON from a
wrapped hermes binary points at the release venv, which has no
pytest — without the guard every test file dies with "No module
named pytest" while the runner exits 0).
Verified: nix flake check exit 0; built .#default .#tui .#web
.#desktop; SKILL.md and flake.nix edits leave the venv drvPath
unchanged; .py edits leave the tui drvPath unchanged; .tsx edits
leave the venv drvPath unchanged (and do change the tui drv);
scripts/run_tests.sh runs 299 tests green through both the venv and
HERMES_PYTHON paths, and rejects a pytest-less HERMES_PYTHON.
* refactor(nix): overlay aliases the flake's own package instead of re-instantiating
The overlay previously re-called callPackage against the consumer's
nixpkgs (final), so pkgs.hermes-agent could be a different derivation
than nix build .#default and the NixOS module's default — an untested
build matrix against arbitrary consumer nixpkgs versions, for a
package whose Python side is uv2nix-locked anyway.
Now the overlay is a pure alias for the flake's own locked package:
one callPackage site (packages.nix), everything else references it.
.override { ... } still works — callPackage's makeOverridable travels
with the derivation.
Verified: direct drvPath == overlaid drvPath; .override produces a
distinct drv.
* fix(nix): dedupe extraPlugins assertions, replace MESSAGING_CWD with terminal.cwd
- Delete the duplicated extraPlugins duplicate-name assertions block
(same assertion declared twice back to back).
- Stop setting the deprecated MESSAGING_CWD env var, which made the
module trip hermes' own startup deprecation warning. The working
directory is now injected as terminal.cwd into the generated
config.yaml; cfg.settings wins via recursiveUpdate, and container
mode maps to the in-container mount path.
* fix(computer-use): target Linux app windows reliably
Resolve app filters through the canonical cua-driver MCP app metadata and join running app PIDs back to windows. Preserve an exact selected window across capture_after, support direct capture by pid/window_id, and send the active window ID for coordinate pointer actions on Linux.
Co-authored-by: annguyenNous <annguyenNous@users.noreply.github.com>
Co-authored-by: grimmjoww578 <willies578@gmail.com>
Co-authored-by: ai-ag2026 <261867348+ai-ag2026@users.noreply.github.com>
* fix(computer-use): address review on PR #63725
Address three review comments from @f-trycua:
1. type_text, press_key, and hotkey now carry _active_window_id and
fail closed when it is missing. Previously they sent only the PID,
so CUA Driver fell back to the first window for that PID — input
could reach the wrong window in multi-window apps.
2. Coordinate scroll x/y are now capability-gated behind
input.scroll.coordinates. CUA Driver 0.7.1 Linux schema rejects
x/y on scroll; omitting them when the driver doesn't advertise
support avoids the schema rejection while still routing via
window_id.
3. Windows are sorted by z_index descending (higher = front, per CUA
Driver semantics) instead of ascending. Null z_index (Wayland) is
coerced to 0 in _ingest_windows so it doesn't crash the sort and
sorts to the back instead of being selected as the capture target.
---------
Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Co-authored-by: annguyenNous <annguyenNous@users.noreply.github.com>
Co-authored-by: grimmjoww578 <willies578@gmail.com>
Co-authored-by: ai-ag2026 <261867348+ai-ag2026@users.noreply.github.com>
Follow-up to the salvaged #63690: when the interim assistant message is
too empty to append (no content and no reasoning of any kind), the last
message in history is still the prior user/tool turn — appending the
user-role nudge there would create a user→user or tool→user sequence
that strict providers reject. Only append the nudge when the last
message is an assistant turn. Also add IpastorSan to AUTHOR_MAP.
The remote model catalog (website/static/api/model-catalog.json) now labels
exactly one entry per provider block with "default": true — z-ai/glm-5.2 for
both OpenRouter and Nous Portal. That labeled entry is the model Hermes
silently lands on when the user never picked one, and it can be rotated by
editing the manifest alone: no release needed.
- model_catalog.py: get_default_model_from_cache() reads the label from the
in-process/disk cache only — never triggers a network fetch, so hot
resolution paths (agent build, gateway session setup) stay network-free.
- models.py: get_preferred_silent_default_model() resolves catalog label
first, PREFERRED_SILENT_DEFAULT_MODEL constant second (offline/fresh
install). _PROVIDER_SILENT_DEFAULT_OVERRIDES dict replaced by
_SILENT_DEFAULT_PROVIDERS routing through the shared resolver.
fetch_openrouter_models() preserves the "default" badge through live
/v1/models refreshes so the picker shows it.
- scripts/build_model_catalog.py: generator emits the default label so
regeneration can't drop it.
- website/docs/reference/model-catalog.md: schema documents the new field.
- Salvaged from PR #61141 (@HumphreySun98): bare-provider /model switches
(/model nous) route through the cost-safe default instead of curated
entry [0].
- tests: catalog-label precedence, constant fallback, stale-label fallback,
cache-only (no network) guarantee, and a shipped-manifest contract test
pinning the labeled entry to PREFERRED_SILENT_DEFAULT_MODEL.
E2E (temp HERMES_HOME): fresh-install constant fallback, shipped-manifest
label read, release-free rotation (relabeled cache -> new default across
models.py, tui_gateway, and gateway empty-model paths) all verified.
Include the Hermes client name and version with Gemini inference, model and tier checks, and TTS requests. Add focused coverage for the request headers and keep the Gemini-specific context scoped to Google Gemini endpoints.
Salvage of #63862. is_output_cap_error() returns False for vLLM/LM Studio
error messages that contain 'prompt contains ... input tokens' (treated as
input-overflow signal). But parse_available_output_tokens_from_error() CAN
extract a valid available_tokens from those same messages. The
compression-disabled guard only checked is_output_cap_error(), so vLLM/LM
Studio users with compression off still got a terminal failure instead of
the max-tokens retry.
Fix: also exempt when parse_available_output_tokens_from_error() returns a
value — that function determines whether the retry path can actually handle
the error, so it's the right predicate for the exemption.
Added test: verify vLLM-format error with compression_disabled=False still
triggers the max-tokens retry path.
Co-authored-by: dmabry <dmabry@users.noreply.github.com>
Baseline bars were positioned at their absolute timeline offset, which
included the baseline run's own wait time — making duration comparisons
hard since the bars were visually offset. Now each baseline bar starts
at the same left position as its corresponding current job, so the two
bars directly overlap for at-a-glance duration comparison.
Also removed the now-unused bl_t0 / bl_max / bl_jobs_timed variables
that tracked the baseline timeline position.
Add wait time computation: for each job, wait_s = started_at - max(completed_at
of all jobs that finished before it started). This is a timestamp heuristic
(no workflow YAML dependency parse needed) that's accurate for pipeline-shaped
CI where the critical path is linear at each stage.
Shows up in:
- Job table: new Wait + Δ Wait columns
- Gantt chart: hatched bar segment before the run bar
- Step details: '(wait Xs)' annotation in the summary line
- Markdown summary: Total wait row with delta vs baseline
- Stats: total_wait / bl_total_wait in compute_stats
Also completes the skipped-jobs UI:
- Skipped stat card in stats cards
- Skipped row in markdown summary table
Backward compatible: old cached baselines without wait_s annotate on load.
Skipped jobs (conclusion == 'skipped') have null/zero-duration timestamps
that polluted every downstream computation: they counted as 'unchanged'
(0 vs 0) in faster/slower tallies, showed meaningless '0.0s (0%)' deltas
in the job table, rendered phantom gantt bars, and inflated wall/compute
totals.
Add is_skipped() helper and apply it consistently:
- compute_stats: exclude from wall/compute + faster/slower/unchanged;
add 'skipped' and 'bl_skipped' counts
- _gantt_bars: filter from current bars, baseline bars, and axis calc
- _job_table: show 'skipped' label instead of durations/deltas
- _step_details: skip entirely (no meaningful step data)
- _regressions: exclude from both current and baseline sides
Normalize Anthropic setup-token metadata for every PooledCredential construction path, persist corrected manual entries, heal legacy rows on load without copying global fallback credentials into profiles, and map the contributor email for release attribution.
Align the workspace status-bar dropdown with the rest of the status bar: drop
the per-item icons (they mixed lucide size-4 with a Codicon 1rem glyph and were
the only status-bar menu carrying item icons), leaving text-only items on the
shared DropdownMenuItem primitive with default typography. The status-bar
trigger keeps its FolderOpen glyph, consistent with sibling items.
Also map true@supersynergy.de → Supersynergy in AUTHOR_MAP.
scripts/desktop-sandbox.sh runs a Hermes desktop instance in an isolated
sandbox — separate HERMES_HOME, separate Electron userData, and a
distinct
app name (HERMES_DESKTOP_APP_NAME) so it doesn't compete with the main
desktop instance's single-instance lock.
Two modes:
- Ephemeral (default): temp dir, cleaned up on exit
- --persistent: stored under .hermes-sandbox/ in the worktree git root,
survives restarts for repeat testing
In the Nix devShell the script is available as 'sandbox'.
Also makes APP_NAME overridable via HERMES_DESKTOP_APP_NAME in main.ts —
app.setName() runs before requestSingleInstanceLock(), so the overridden
name changes the lock key. collectRelaunchEnv already preserves
HERMES_DESKTOP_* vars through self-update relaunches; test updated to
cover the new env var.
Follow-ups for salvaged PR #43819: the registry key was
str(Path(db_path).expanduser()) — a symlinked or relative path to the
same DB file got its own connection, silently reintroducing the exact
multi-writer contention the registry prevents. Key on Path.resolve()
(OSError-tolerant fallback). Adds a symlink regression test and the
AUTHOR_MAP entry for adambiggs.
Structural completion of the malformed-job freeze fixes (#61382 id-less,
#61525 non-dict schedule, #61581 bad next_run_at): wrap the per-job body
of _get_due_jobs_locked in try/except so any FUTURE malformed-field
variant degrades to skipping that one job for the tick instead of
aborting the scan before save_jobs() and freezing the whole profile's
scheduler.
Also: restore test_repeated_concurrent_runs_accumulate_completed_count
to TestMarkJobRunConcurrency (accidentally re-parented by the #61581
diff), add a containment regression test, and AUTHOR_MAP for hydracoco7.
E2E: one jobs.json carrying all five malformed shapes (drifted job_id,
missing id, null schedule, garbage next_run_at, non-string last_run_at)
plus a healthy sibling — single tick contains all five, sibling fires,
repairs persist, second tick stable. 670 cron tests green.
The salvaged fix sets HERMES_YOLO_MODE in main()'s dispatch path before
_prepare_agent_startup(); this follow-up also sets it inside
_prepare_agent_startup() itself so every launcher that triggers plugin/tool
discovery (incl. the Termux fast-CLI path) gets the same ordering guarantee
before tools.approval freezes _YOLO_MODE_FROZEN (#60328).
Structured review (2a/2b/2c) findings, all fixed:
- MAJOR: detect_local_server_type memo was process-lifetime with no
invalidation, permanently pinning a URL's server type. Now a bounded
1h TTL ((type, monotonic) tuples) so a backend swap on the same port
is re-detected. Test covers ollama->lm-studio swap after expiry.
- MAJOR: legacy disk-row compat was one-way. get_cached_context_length
and _invalidate_cached_context_length now consult the same key-shape
set {canonical, literal, canonical+slash} in both directions, so an
old slashed row is found (and cleared) when the runtime passes the
normalized URL. Tests pin both migration directions.
- MINOR: _localhost_to_ipv4 did whole-string replacement, which could
corrupt a proxy URL embedding http://localhost in its query. Now a
scheme-anchored host-only regex; localhost.example.com and embedded
substrings pass through. Tests added.
- MINOR: _invalidate_cached_context_length now also drops the
in-memory TTL probe rows for the pair, so a resolution inside the
TTL window can't re-persist the value just declared stale.
- Test gaps closed: detect-type cache hit + TTL-expiry re-detection,
ollama-show TTL expiry re-probe, reverse legacy-row lookups.
- Attribution gate: added zhchl@hermes-agent.local -> 8294 (PR #50572
author) to AUTHOR_MAP; the strict CI grep needs bare non-plus emails
literal in release.py.
Gates: ruff clean; targeted suites 202 passed / 0 failed; full
tests/agent 5426 passed with 17 failures identical on clean
upstream/main (pre-existing env-dependent anthropic/bedrock/credpool
tests); mypy delta vs base: 0 new errors; live smoke 6/6 PASS.
Every 5 minutes fetch_endpoint_model_metadata() re-runs the full server-type
waterfall (LM Studio -> Ollama -> llama.cpp -> vLLM), spraying 404s at
endpoints the server never exposes (e.g. /api/v1/models and /api/tags on a
vllm backend).
Add _endpoint_probe_path_cache (base_url -> server type) so the first
successful probe's result is reused for the lifetime of the process.
Subsequent refreshes skip straight to the known-good path.
Fixes#29971.
(cherry picked from commit f3d7a8960a)
- derive the compact_rows projection from SCHEMA_SQL (parse once, cache)
instead of a hardcoded column list: the original #47437 list was cut
against a June schema and silently dropped session_key/chat_id/chat_type/
thread_id/display_name/origin_json/expiry_finalized/git_branch/
git_repo_root/compression_failure_* — including desktop sidebar fields.
Schema-derived means declaratively reconciled new columns are included
automatically; only system_prompt is excluded.
- guard test pinning the schema<->projection contract (mutation-verified:
dropping a column from the projection fails it)
- wire compact_rows=(not full) into /api/sessions and /api/profiles/sessions
so the SQL projection pairs with the API-level field strip (?full=1 still
returns complete rows end-to-end)
- pass compact_rows at the remaining hot list callers: /api/status active
count, _session_latest_descendant fallback, /api/sessions/stats by-source
- thread compact_rows through the compression-tip projection
(_get_session_rich_row) so projected tips can't reintroduce the blob
- add pagination tests for get_messages (#60347 shipped none): paging order,
offset-past-end, active-flag interaction; add tip-projection compact test
- AUTHOR_MAP entries for mahdiwafy + CodeForgeNet (plain emails)
- run_route_script shells out with subprocess.run (up to 30s timeout); wrap
the call in asyncio.to_thread so a slow script can't stall every other
webhook and gateway task on the loop.
- scripts/release.py: map grace@weeb.onl -> evelynburger for the salvaged
contributor commit.
The April 2026 pin to WhiskeySockets/Baileys#01047deb existed only to
pick up the abprops bad-request fix (Baileys PR #2473) before it was
released. That fix shipped in v7.0.0-rc11 (May 2026); our pinned commit
is now 48 commits behind rc13.
The git pin forced npm to clone the repo and compile Baileys from
TypeScript source on every fresh install (~3 min), which blew past the
dashboard pairing flow's timeout. Registry install takes ~3s.
Validation: all 9 bridge.js imports present in rc13, bridge.native.test.mjs
passes (13/13), live bridge boot renders pairing QR against real WA servers.
Salvage follow-up integrating PR #30481 (@simplast) and PR #57683
(@catbearlove1-lang) into the unified export surface:
- --format html: standalone self-contained HTML transcript (single
session or multi-session with sidebar), works with all shared filters
and --redact; requires a file output path.
- --only user-prompts: prompt-only export (jsonl records or md sections)
via the shared session_export renderer; the separate export-prompts
subcommand from the original PR is subsumed by this flag.
- AUTHOR_MAP entries for both contributors; docs EN + zh-Hans.
Replaces the parallel export-md subcommand from the salvaged commit with
a --format jsonl|md|qmd flag on the existing export subcommand, so all
session export formats share one surface. Adds AUTHOR_MAP entry.
Salvage follow-up for PR #59542 by @web3blind.
npm postinstall hooks spawn cmd.exe child processes that could not resolve
`node` even when the installer found npm — causing desktop workspace npm
install to fail with exit 1 (#48130).
Discord thread names share the same UTF-16 component budget as select
labels and buttons — route the sanitizers in gateway/run.py and the
adapter's rename_thread through utf16_len/_prefix_within_utf16_limit
instead of code-point slices. Adds rungmc357 to AUTHOR_MAP.
* fix(gateway): use process-level HERMES_HOME for identity files
Gateway identity files (PID, lock, runtime status, takeover/stop markers)
were written via get_hermes_home() which honours the _HERMES_HOME_OVERRIDE
contextvar used for per-session profile dispatch. When a profile-context
task happened to be active at write time, files landed in the wrong profile
directory.
Add _get_process_hermes_home() that skips the contextvar and uses only the
HERMES_HOME env var or platform default, and route all gateway identity file
paths through it.
Fixes#56986
* chore(release): map liuhao1024 author email for PR #56993 salvage
---------
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Co-authored-by: Ben <ben@nousresearch.com>
* fix(dashboard): use loopback host for in-container WebSocket client (#58993)
Fixes#58993 - the in-container Dashboard's WebSocket client was dialing
the bind host (0.0.0.0) instead of 127.0.0.1, hijacking the host browser
when the container port was exposed.
* `hermes_cli/web_server.py::resolve_dashboard_ws_url()` now substitutes
127.0.0.1 for any 0.0.0.0 bind host discovered via the existing
`find_unused_port` / `get_listen_address` path. LAN IPs and explicit
`DASHBOARD_WS_HOST` overrides pass through unchanged.
* Existing tests preserved (no regression on the explicit-bind case).
Tests in `tests/dashboard/test_ws_client_host.py` cover:
- Bind host 0.0.0.0 → ws URL uses 127.0.0.1
- Bind host 127.0.0.1 → ws URL uses 127.0.0.1 (no regression)
- Bind host 192.168.1.5 → ws URL preserves the LAN IP
- DASHBOARD_WS_HOST env override wins over auto-detection
AI-assisted fix by https://github.com/SquabbyZ/peaks-loop
(cherry picked from commit 5501dd38d6)
* chore(release): map SquabbyZ email for AUTHOR_MAP attribution (#59682)
---------
Co-authored-by: SquabbyZ <601709253@qq.com>
* fix(auth): resolve Anthropic OAuth file per-profile + close port-binding platform gaps
Two focused pieces salvaged from PR #57563:
1. _HERMES_OAUTH_FILE was computed at module import time — frozen before
HERMES_HOME/profile overrides, so multiplexed profile turns read and
wrote the DEFAULT profile's .anthropic_oauth.json (OAuth path hijack).
Replaced with a lazy _get_hermes_oauth_file(); all web_server.py call
sites updated.
2. _PORT_BINDING_PLATFORM_VALUES was missing whatsapp_cloud and line —
both bind aiohttp TCP listeners, so a secondary multiplex profile
enabling them would collide with the primary's listener instead of
failing fast at startup.
Original work by @austinlaw076. The rest of #57563 was redundant on
main (adapter routing sweep superseded by #56854's salvage; cron secret
scope landed in fdab380a1; nested-config fallback in from_dict).
* chore(release): map austinlaw076 author email for PR #57563 salvage
* test(hermes_cli): patch _get_hermes_oauth_file instead of removed _HERMES_OAUTH_FILE constant
---------
Co-authored-by: Austin <austin@openvm067.space>
Co-authored-by: Ben <ben@nousresearch.com>
* fix(gateway): scope reset banners' session info to the serving profile
The auto-reset notice and the manual /reset //new banner both appended
_format_session_info() outside any profile scope, so a multiplexed
gateway advertised the base config's model/provider/context while the
session actually ran on the profile's.
Route both call sites through a new _reset_notice_session_info(source),
which enters _profile_runtime_scope for the source's profile when
gateway.multiplex_profiles is on (mirroring _run_agent's gating), so
_load_gateway_config()/_resolve_gateway_model() resolve the profile's
config.yaml via the existing context-local home override. Single-profile
gateways never enter the scope — behavior unchanged.
Both call sites invoke the helper via asyncio.to_thread: under the
scope, resolution can do blocking work (credential refresh,
context-length HTTP probes) that previously failed fast unscoped and
must not run on the event loop.
Fixes#59003
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(release): map irresi author email for PR #59048 salvage
---------
Co-authored-by: irresi <blueirobin02@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The stage2-hook auth.json seed is first-boot-only ([ ! -f auth.json ]) to avoid
clobbering rotated refresh tokens on restart. That guard means a container whose
Nous bootstrap session took a terminal invalid_grant (tokens cleared,
providers.nous.last_auth_error.relogin_required stamped) cannot recover from a
restart — it stays unauthenticated until the credential is replaced.
Add a self-heal path: an orchestrator that manages the container supplies a
freshly-issued session via HERMES_AUTH_JSON_REBOOTSTRAP (distinct from the
create-only *_BOOTSTRAP var). On boot, scripts/docker_rebootstrap_nous_session.py
swaps ONLY the providers.nous entry, and ONLY when the on-disk entry is provably
terminal (quarantine marker + no usable tokens). Healthy/rotating/absent/
unparseable auth.json is always a no-op, so the env is safe to leave set across
restarts and never clobbers a good token. Pure stdlib, runs as its own
subprocess, always exits 0 so a re-seed error never fails the boot.
Reuses the same terminal predicate as get_nous_session_validity() so we re-seed
only a session that is genuinely dead.
The salvaged commits from #32824 use a bare
spiky02plateau@users.noreply.github.com (no numeric-id + prefix), which the
contributor-check.yml gate does not auto-resolve (it only skips the
<id>+<user>@users.noreply form). Add the explicit mapping so attribution CI
passes and release notes credit @spiky02plateau.
The 'CI timing report' job is pure observability — it collects per-job/step
durations from the GitHub API after the run and publishes an HTML gantt
report + PR-vs-main timing diff. It gates nothing (all-checks-pass does not
include it), yet it could redden a PR: the script makes dozens of paginated
API calls with the shared repo GITHUB_TOKEN and had zero retry handling, so
a single 403 (rate-limit burst when several PRs run CI concurrently) failed
the job. Observed twice in a row on PR #59805.
- api_get(): retry 403/429/5xx and connection errors with exponential
backoff, honoring Retry-After / X-RateLimit-Reset (max 5 attempts, 120s
cap). Non-transient statuses (404 etc.) still fail fast.
- main(): exhausted retries raise TimingsUnavailable, caught to emit a
degraded summary line + placeholder HTML artifact and exit 0 — a metrics
collector must never fail the PR's checks. No timings JSON is written on
the degraded path so an empty baseline can never be cached.
- ci.yml: baseline-save steps on main skip gracefully when no JSON exists.
Verified with a mocked urlopen harness: retry-then-success (3 attempts),
exhausted-retries -> TimingsUnavailable, 404 fails fast without retry,
degraded main() exits 0 with summary + placeholder and no JSON, and the
--from-json happy path is unchanged.
Follow-up on the cherry-picked #36896 commits, wiring 1Password into
the new registry as the reference *mapped* source:
- OnePasswordSource adapter (shape=mapped, scheme=op): fetch-only —
precedence, override semantics, conflict warnings, and env writes
move to the orchestrator; apply_onepassword_secrets kept as legacy
shim like Bitwarden's.
- Registered in _ensure_builtin_sources; mapped op:// bindings now
outrank bulk Bitwarden project dumps on contested vars.
- _cache.py FetchResult/is_valid_env_name re-exported from base so
there is exactly one canonical definition; bitwarden.py re-adapted
onto the contributor's DiskCache substrate.
- ErrorKind classification for op failures (auth/binary/empty/network).
- Registry + conformance coverage for OnePasswordSource, incl. the
headline multi-source test: both vaults claim the same var, mapped
1Password wins, conflict surfaced, provenance correct.
- env_loader tests migrated off the legacy apply_* mocks onto the
fetch layer; AUTHOR_MAP entry for @hwrdprkns.
check-attribution CI fails on unmapped bare (non-noreply) contributor
emails. isheng-eqi's commit email (ishengeqi@163.com) has no + so it does
not auto-resolve — add the explicit mapping.
register_mcp_servers now nudges cached entries whose session is None
via _signal_reconnect, so a new agent session recovers a parked server
immediately instead of waiting up to _PARKED_RETRY_INTERVAL for the
next self-probe (#50170). Gate-check idea credit: @izumi0uu (#50184),
@LeonSGP43 (#37772), @Tranquil-Flow (#37899).
Port from nanocoai/nanoclaw#2895's never-silently-drop guarantee.
Before: saveMedia() in scripts/whatsapp-bridge/bridge_helpers.js awaited
downloadMedia() with no try/catch. A failed CDN fetch (expired media URL,
transient network error — Baileys throws 'Failed to fetch stream from
https://mmg.whatsapp.net/...') rejected out of extractBridgeEvent, which
bridge.js awaits inside its messages.upsert for-loop with no per-message
guard — dropping the failed message AND every remaining message in the
same upsert batch, silently.
After:
- saveMedia catches download/write failures, records the media type, and
logs a console.warn instead of rejecting.
- appendMediaFailureNote() (exported pure helper, mirroring the file's
testable-helper convention) surfaces '[<type> could not be downloaded]'
in the event body, so the agent learns media was sent rather than the
attachment vanishing. Applied before the '[<type> received]' fallback
so an uncaptioned failed image reads as a failure, not an arrival.
The reuploadRequest recovery half of nanoclaw#2895 is already wired in
bridge.js (downloadMediaMessage(..., { reuploadRequest:
sock.updateMediaMessage })); this ports the containment half hermes was
missing.
Tests: 3 new cases in bridge.native.test.mjs (note formatting, uncaptioned
failure containment, captioned failure note). All 5 bridge test files pass.
ruff check --fix --select F541 . on current main. Pure prefix removals;
adjacent-string concatenations keep the f only on interpolating fragments.
No string content or live placeholder altered.
Follow-up to the salvaged #58696 (devatnull) + #41343 (annguyenNous)
commits: instead of fully suppressing commentary/analysis-phase stream
deltas, fire on_reasoning_delta so the CLI/gateway display them like
thinking text. Matches Codex CLI semantics where commentary is never
the turn's final answer, while keeping the narration visible in the
reasoning display. Adds devatnull to AUTHOR_MAP.
- bridge: only enqueue poll_update events for polls Hermes itself created
(tracked via recentlySentIds when /send-poll returns) so arbitrary human
polls in group chats don't inject agent-visible messages on every vote
- update test_already_whatsapp_italic for the new markdown-italic mapping
- AUTHOR_MAP entry for @devatnull (PR #58704 salvage)
* fix(cli): set correct x-initiator header per Copilot turn
copilot_default_headers() always hardcoded x-initiator: agent, but
GitHub Copilot billing requires "user" for user-initiated prompts and
"agent" for tool/follow-up calls. This caused premium requests to never
be consumed correctly, risking billing issues or account bans.
Adds is_agent_turn param to copilot_default_headers() and injects
extra_headers={"x-initiator": "user"} on the first API call of each
user turn when targeting Copilot URLs. The flag flips to False after
injection so subsequent calls (tool use, streaming fallback) default
back to "agent".
Fixes#3040
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore(release): add AUTHOR_MAP entry for @tjp2021 (PR #4097 salvage)
---------
Co-authored-by: Tim <tim@iteachyouai.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- _normalize_to_supported_image: ensure cache/vision exists before writing
the converted PNG (fresh HERMES_HOME had no dir -> FileNotFoundError).
- resolver: SVG passes through as image/svg+xml instead of erroring; the
call sites rasterize to PNG via the salvaged normalize step (cairosvg /
svglib / rsvg-convert / inkscape, best-effort with actionable error).
- normalization offloaded via asyncio.to_thread at both call sites.
- tests: resolver pass-through + rasterization + no-converter error paths.
- AUTHOR_MAP: jonathan@mintrx.com -> JAlmanzarMint (PR #52688 salvage).
Contributor of the salvaged PR #58276 fix commit. Required so the
contributor attribution CI check passes on the rebase-merge that
preserves their authorship.
Follow-up to @msh01's wall-deadline init-timeout fix.
- Resource leak: on timeout the initialize() task is abandoned without
awaiting its (shielded, possibly-never-completing) cancellation, so the
half-built PTB app's httpx client / connection pool was never closed —
up to 8x across the retry ladder. Add an optional on_abandon cleanup to
_await_with_thread_deadline that best-effort app.shutdown()s the abandoned
app, run detached + exception-swallowed so it can never re-block or re-hang
the ladder (mirrors _close_client_on_timeout in agent/auxiliary_client.py).
- Cover the helper itself: the salvaged test monkeypatched out the real
_await_with_thread_deadline, so its abandonment/cleanup path was untested.
Add direct tests for happy-path return, prompt-timeout-with-cleanup, and
cleanup-error-swallowed; the wedged coroutines swallow cancellation for a
bounded window (proving the helper returns before cancellation completes,
the #58236 shielded-scope behavior) without leaving an immortal task that
would wedge pytest teardown. Widen the salvaged stub to accept on_abandon.
- Attribution: add yingwaizhiying@gmail.com -> msh01 to AUTHOR_MAP (bare
gmail does not auto-resolve the check-attribution gate).
Known follow-up (not addressed here): the retry ladder reuses the same
self._app across all 8 attempts; a fresh app per attempt would fully close
the coherence risk if an abandoned initialize() completes in the background.
That is a larger restructure of the ~130-line builder+handler setup, left
for a separate change.
check-attribution requires every contributor author email to be in
AUTHOR_MAP; the salvaged commit is authored by
huanshan5195 <huanshan5195@users.noreply.github.com>.
Salvage of PR #57893 (envelope-layout prompt-cache marker fix, #57845)
uses the contributor's local git identity lavya@loom.local, which is not
GitHub-resolvable. Add the mapping so contributor_audit passes when the
salvage PR lands.
Five follow-ups to #57659 from post-merge review:
1. install.ps1: gateway scheduled-task re-enable now runs in a finally
(a thrown Remove-Item/uv venv failure previously stranded the user's
gateway autostart disabled), and tasks that were already disabled
before the install are no longer blindly re-enabled.
2. The venv-python holder guard is no longer bypassed by plain --force
(which the desktop bootstrap passes on every update while its lock
probe only checks hermes.exe/app.asar). New explicit --force-venv is
the escape hatch; --force keeps bypassing only the hermes.exe shim
guard.
3. _detect_venv_python_processes now also catches uv/base-interpreter
trampolines whose exe is outside the venv, via cmdline (venv path or
'-m hermes_cli.main' tied to this install root) and cwd.
4. Missing venv python is now UNHEALTHY on managed installs
(.hermes-bootstrap-complete / .update-incomplete markers) so the
repair lane runs instead of 'Already up to date!'; the repair branch
recreates the venv first when it's gone entirely. Dev checkouts keep
reporting healthy.
5. install.ps1 comment no longer claims a Startup-folder disarm the
code doesn't perform (logon-only, not a mid-install respawner).
Root-causes the July 2026 Windows incident chain (locked _brotlicffi.pyd /
_sodium.pyd during install, then 'No module named annotated_doc' with
'hermes update' insisting 'Already up to date!'):
- hermes update: probe venv core imports even when the checkout is current;
a half-updated venv (dep sync killed mid-flight by a locked .pyd) is now
detected and repaired instead of being reported as up to date
- hermes update (Windows): after pausing gateways, refuse to mutate the venv
while other processes run from the venv interpreter (the Desktop backend
runs as python.exe so the hermes.exe shim guard never saw it); --force
keeps the old behavior
- install.ps1 venv stage: disarm gateway autostart Scheduled Tasks before
the kill sweep (they respawn the gateway inside the kill->delete window),
make the sweep a bounded loop requiring 3 clean passes, and rename-then-
delete the old venv (a rename succeeds even with mapped DLLs) with stale-
dir cleanup on the next run
- desktop updater: 'venv shim still locked after 15s' now ABORTS the update
hand-off (restarting our backend, surfacing the holder to the user)
instead of 'proceeding anyway (force)' into guaranteed venv corruption;
the unlock wait also re-kills respawned backends each poll tick
Per-session /model overrides (_session_model_overrides) were in-memory only,
so a gateway restart silently reverted every session to the global default
model. Persist the non-secret parts (model/provider/base_url ONLY — never
api_key) into the session entry in sessions.json and lazily rehydrate them
on first use after a restart, re-resolving credentials through the normal
runtime provider resolution.
- gateway/session.py: SessionEntry.model_override field with
sanitize_model_override() (allowlist: model/provider/base_url) applied on
both serialization and deserialization; SessionStore.set_model_override /
get_model_override accessors. reset_session() already creates a fresh entry,
so /new keeps its clear-on-reset semantics — a restart cannot resurrect an
override the user reset away.
- gateway/slash_commands.py: write-through at both /model set sites (text
command + picker) after storing the in-memory override.
- gateway/run.py: _rehydrate_session_model_override() called from
_resolve_session_agent_runtime(); in-memory state always wins, credentials
are re-resolved per provider (credential-less fallback on failure). Session
expiry finalization also drops the persisted override.
- tests/gateway/test_session_model_override_persistence.py: restart
round-trip, /new clearing, api_key-never-serialized (including tampered
sessions.json), rehydration + live-state precedence + credential-failure
degradation.
Salvaged from #3659 by @Git-on-my-level, narrowed to the restart-persistence
gap confirmed in triage.
Named providers / custom_providers entries in config.yaml now accept an
extra_headers dict scoped to that endpoint — for reverse proxies, API
gateways, and custom auth schemes (e.g. Cloudflare Access service tokens).
- hermes_cli/config.py: normalize extra_headers on provider entries
(_normalize_custom_provider_entry + providers-dict translation), add
get_custom_provider_extra_headers /
apply_custom_provider_extra_headers_to_client_kwargs helpers keyed on
base_url (case/trailing-slash insensitive, no substring bypass —
mirrors the TLS helpers)
- hermes_cli/runtime_provider.py: surface extra_headers in the resolved
runtime for named custom providers (providers dict, legacy
custom_providers list, and the credential-pool path)
- run_agent.py / agent/agent_init.py: merge per-provider extra_headers
onto the OpenAI client default_headers at construction and on every
_apply_client_headers_for_base_url re-application (credential swaps,
rebuilds), most-specific level wins; OpenAI-wire only (native
Anthropic/Bedrock scoped out)
- agent/auxiliary_client.py: accept model.extra_headers as an alias of
model.default_headers for the global variant
- cli-config.yaml.example: documented commented example
- Header values are treated as secrets and never logged
Salvaged from PR #3526 by @jneeee, reimplemented against current main.
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
Adds a no-code routing layer to the OpenAI-compatible API server so one
Hermes deployment can map different API clients to different
model/provider backends. Clients pick a backend by sending a configured
alias as the OpenAI 'model' field; unmatched values fall back to the
global model. Configured aliases are listed by GET /v1/models.
Precedence (highest first): session /model override > model_routes
route > global config. Route provider credentials resolve through
_resolve_runtime_agent_kwargs_for_provider (same seam as
channel_overrides); per-route api_key/base_url are upstream provider
credential overrides — never caller auth, never logged.
Salvaged and rebased from PR #3176 by @Mibayy onto current main.
Salvaged from PR #3243 by @Mibayy, reimplemented against current main
(the original diff targeted a removed gateway/run.py handler).
- /compact is now a first-class alias of /compress (CLI, gateway,
Telegram/Slack/Discord command lists, autocomplete) — also fixes the
dangling '/compact' references in gateway error messages
(gateway/run.py context-exhausted banners).
- --preview / --dry-run: report what WOULD be compressed (message
counts, token estimate, 'here [N]' boundary) without touching the
transcript. Flags coexist with the existing 'here [N]' / focus-topic
args on both the CLI and gateway surfaces via shared pure helpers in
hermes_cli/partial_compress.py.
- --aggressive (LLM-free hard truncation) is intentionally NOT
implemented: it would need its own transcript-persistence branch
outside the guarded _compress_context rotation machinery (#44794
data-loss class). The flag is recognized and returns an explanatory
message pointing at '/compress here [N]' and /undo instead of being
mis-parsed as a focus topic.
- locales: gateway.compress.aggressive_unsupported added to all 16
catalogs (parity test enforced).
- release.py: AUTHOR_MAP entry for contributor credit.
Salvage of #3459 by @keslerm, reimplemented against the restructured
progress-callback block in gateway/run.py (resolve_display_setting,
needs_progress_queue, thinking-relay). Duplicate PR #3458 by @dlkakbs was
submitted 4 minutes earlier with the same feature — both credited.
Co-authored-by: Dilee <uzmpsk.dilekakbas@gmail.com>
tool_progress: log keeps the chat silent and appends timestamped tool-call
lines to ~/.hermes/logs/tool_calls.log via a dedicated queue drained by an
async writer (RotatingFileHandler 5MB x 3, RedactingFormatter so secrets
never land on disk). Gateway-only by design; thinking_progress relaying and
the webhook gate are unaffected. /verbose now cycles
off -> new -> all -> verbose -> log.
Salvage of the surviving hunk of #3296 by @Mibayy. The PR's gateway
_handle_provider_command hunk targets code removed on main (/provider was
absorbed into /model + /status, which already read model.base_url); the
hermes status mislabel was the remaining live symptom:
_effective_provider_label() only checked the legacy OPENAI_BASE_URL env var,
so a custom endpoint configured canonically in config.yaml still displayed
as OpenRouter.
WhatsApp has migrated to Linked Identity Device (LID) format for user
IDs (e.g. 244645917392975@lid instead of 18505551234@s.whatsapp.net).
The bridge already resolves LIDs to phone numbers for its own allowlist
check via buildLidMap(), but the senderId field in the message payload
sent to the gateway still contained the raw LID. This caused the
gateway's WHATSAPP_ALLOWED_USERS check to reject all messages as
unauthorized, since the LID numbers don't match the phone numbers in
the allowlist.
Fix: resolve LID → phone in the senderId, senderName, and chatName
fields of the event payload before sending to the gateway, using the
existing lidToPhone mapping.
Adds the AUTHOR_MAP entry for CrazyBoyM (ai-lab@foxmail.com) so the
contributor-attribution CI check passes when PR #55828's commits are
rebase-merged with authorship preserved.
Salvage of the surviving piece of #2696 by @tarunravi. The PR's other two
changes (tool progress streaming, SSE None-sentinel fix) were independently
superseded on main by the structured hermes.tool.progress SSE events and the
rewritten queue-drain loop.
Remote OpenAI-compatible frontends can't read server-local file paths, so
MEDIA:<path> tags (browser screenshots, generated images) were dead text.
_resolve_media_to_data_urls() now inlines small (<=5MB) local images as
markdown data URLs across all four response surfaces: chat completions
(non-streaming), session chat, session chat stream final event, and the
Responses API. Non-image, missing, or oversized paths pass through
untouched.
Salvage of #2794 by @CharmingGroot, ported to the relocated
plugins/platforms/email/adapter.py:
- Guard raw_email = msg_data[0][1] against IndexError/TypeError and
non-bytes payloads. UIDs are added to _seen_uids before fetch, so an
exception mid-batch permanently skipped every remaining message in
the batch — now the bad message is logged and skipped instead.
- Message-ID domain generation falls back to 'localhost' when
EMAIL_ADDRESS lacks '@' (now via a shared _message_id_domain() helper
covering all 3 send paths; the PR fixed 2 of 3).
Attribution audit gate: the salvaged contributor commits carry
kiljadn@gmail.com (Nick Mason / @designnotdrum). Add the mapping so
contributor_audit.py resolves the author on this PR.
Map the two contributor emails whose commits are cherry-picked into the
compression-routing-integrity salvage so scripts/contributor_audit.py
attributes them at release time:
- jvsantos.cunha@gmail.com -> plcunha (PR #55300)
- jakepresent1@gmail.com -> jakepresent (PR #55721)
r266-tech (PR #50517) is already mapped.
With the default busy_input_mode=interrupt, a burst of rapid gateway
messages arriving while context compression is in flight could interrupt
the current turn and start a fresh turn against the pre-rotation parent
session. Because compression is interrupt-immune (#23975), the still-
running compression later rotates the id out from under that new turn,
and if the new turn also grew past the compression threshold it started
its own uncancellable compression on the same stale parent — forking
multiple orphaned one-shot sibling continuations (#56391).
While a state.db compression lock is held for the session, demote
'interrupt' busy-input mode to 'queue' semantics (mirroring the subagent
protection in #30170), so the follow-up message waits for the in-flight
compression + its id rotation to land instead of racing a new turn
against the stale parent. Ack copy explains the compression demotion.
Fixes#56391.
Adds Vertex AI as a first-class provider for Gemini models via Vertex's
OpenAI-compatible endpoint. Vertex authenticates with short-lived OAuth2
access tokens (service-account JSON or ADC), not a static API key — the
missing piece behind the recurring requests (#13484, #12639, #56259).
- agent/vertex_adapter.py: OAuth2 token minting + refresh-on-expiry
(5-min margin), ADC->service-account fallback, global vs regional
endpoint URLs. Config precedence: env var > config.yaml > default.
- plugins/model-providers/vertex/: provider profile (auth_type=vertex),
reuses Gemini's extra_body.google.thinking_config translation.
- runtime_provider: vertex short-circuit BEFORE the credential pool so a
credentials-file path is never mistaken for a static API key; mints a
fresh token + computes base_url per resolve.
- run_agent + conversation_loop: _try_refresh_vertex_client_credentials()
re-mints the token and rebuilds the client on a mid-session 401, so a
long-lived gateway agent survives token expiry (~1h).
- auxiliary_client: vertex auth_type branch for side-LLM tasks.
- config.yaml: vertex.project_id / vertex.region (non-secret, bridged to
env); credential path stays in .env (VERTEX_CREDENTIALS_PATH).
- setup wizard + model picker: dedicated _model_flow_vertex; curated
google/gemini-* model list; --provider choices.
- pricing/metadata: Vertex prices off the gemini docs snapshot; endpoint
host auto-maps to the vertex provider (no probe spam).
- lazy_deps + pyproject [vertex] extra: google-auth, opt-in only.
- docs: guides/google-vertex.md + providers page; tests for adapter +
runtime resolution.
Salvages and modernizes #8427 by @slawt onto current main: rewired from
the legacy PROVIDER_REGISTRY path to the provider-profile architecture,
moved non-secret config out of .env into config.yaml, and added the
per-turn 401 token-refresh the original lacked.
- Correct the exit-75 comment: Hermes-generated units set
StartLimitIntervalSec=0 (rate limiting disabled), so StartLimitBurst
does not bound loops. The real bound is that genuine crashes exit
non-zero-but-not-75, and RestartForceExitStatus=75 only whitelists
the planned code.
- Add randomuser2026x AUTHOR_MAP entry (CI blocks unmapped emails).
Wrap each Telegram initialize() attempt in asyncio.wait_for(HERMES_TELEGRAM_INIT_TIMEOUT,
default 30s). When api.telegram.org and all fallback IPs are unreachable, the connect
chain has no outer bound, so a single initialize() blocks for minutes and the
retry-on-exception loop never fires — the gateway appears to hang after the banner.
The timeout guarantees each attempt is bounded, then retries with backoff, then fails
with an actionable error. Also adds WARNING-level progress logs before DoH discovery
and each connect attempt (visible at default log level).
Salvaged onto plugins/platforms/telegram/adapter.py (Telegram moved from
gateway/platforms/ since the PR was opened). Adds env var to docs + AUTHOR_MAP.
Co-authored-by: Hermes Agent <127238744+teknium1@users.noreply.github.com>
Follow-up on the salvaged #49830 hardening. The contributor's sensitive
query-param set included bare English words (code, key, auth, session,
sig) that double as ordinary page facets — ?code= on promo/challenge
pages, ?key= as a search facet, ?session= on blogs — so web_extract and
cloud browser_navigate would refuse a large slice of normal browsing.
Narrow the set to unambiguously credential-named params (access_token,
authorization, client_secret, password, token, x-amz-signature, ...).
Prefix-based vendor-key redaction (is_safe_url) still catches recognizable
key shapes; this set is the belt-and-suspenders for opaque secrets carried
under an explicit credential-named parameter.
Also fixes two intra-PR-staleness test breakages surfaced by salvaging onto
current main:
- web_extract_tool() no longer accepts use_llm_processing= (signature
changed since the PR was authored) — dropped the invalid kwarg.
- agent.redact now fully masks keyed 'token=<secret>' to 'token=***'
instead of partial 'sk-...'; the console-redaction test now asserts the
real invariant (secret body gone) rather than the exact mask format.
Added a regression test that generic English-word query params are NOT
blocked by the credential guard.
Add tmp_path symlink regression tests for both generate_systemd_unit and
generate_launchd_plist (~/.local/bin/node -> profile node install must not
leak the profile target into the generated unit PATH). Register
jearnest11's AUTHOR_MAP entry for the salvage cherry-pick.
Register the Matrix room-message, reaction, and invite handlers with
mautrix's wait_sync=True. mautrix's handle_sync() only returns the tasks
for handlers registered as sync-awaited; non-waited handlers are
fire-and-forget via background_task.create() and are NOT returned. Since
_dispatch_sync() awaits only the returned tasks (await asyncio.gather),
the inbound handlers previously had no completion point, so Tuwunel/
mautrix homeservers connected and completed initial sync but dispatched
zero inbound messages.
Fixes#46142.
Co-authored-by: Zeheng Huang <153708448+hunjaiboy@users.noreply.github.com>
Think-enabled models (MiniMax M2.7, DeepSeek, etc.) emit inline
<think>...</think> reasoning even for simple prompts like title
generation, and the raw XML was leaking into session titles. Route the
title-model response through the canonical strip_think_blocks scrubber
before cleanup so every tag variant — closed pairs, unterminated blocks,
orphan closes, mixed case — is handled, not just a single literal
<think> pair.
- 2 regression tests: closed <think> pair stripped, unterminated block
at start yields no title.
Salvaged from PR #44126 by @shawchanshek.
Maps the two plain-email contributors whose PRs are being salvaged so
contributor_audit.py passes:
- info@djimit.nl -> djimit (PR #48034)
- lubos@komfi.health -> lubosxyz (PR #49225)
The other two PRs in the batch (#50405 sasquatch9818, #48764 srojk34)
use users.noreply.github.com emails, which check-attribution auto-skips.
Slack Workflow Builder posts (and other app/bot messages) arrive as
subtype=bot_message with user=None. _is_user_authorized rejected them at
the `if not user_id: return False` guard, which runs *before* the #4466
{PLATFORM}_ALLOW_BOTS bypass — so @mentioning the bot from a Slack
workflow silently did nothing, even with SLACK_ALLOW_BOTS (or
SLACK_ALLOW_ALL_USERS) set. The chat-scoped allowlist for Telegram/QQ
already runs before that guard for the same reason (channel broadcasts
with no from_user); Slack was both missing from the bot-bypass map and
had the bypass running too late.
- gateway/authz_mixin: move the {PLATFORM}_ALLOW_BOTS bypass ahead of the
no-user-id guard and add Platform.SLACK -> SLACK_ALLOW_BOTS.
- plugins/platforms/slack/adapter: set is_bot=True on inbound
bot_message events so the gateway can identify workflow/app senders
(they carry no user_id to match against the allowlist).
Tested: new tests/gateway/test_slack_bot_auth_bypass.py plus the existing
Discord/Feishu bot-auth and gateway authz/gating suites all pass.
Follow-up on the salvaged resume_pending fix: the empty-turn safety net
now emits the same reason-aware recovery note as the _is_resume_pending
branch (reason phrase + 'session restored' guidance + no-re-execute
instruction) instead of a second, differently-worded note. Also adds the
AUTHOR_MAP entry for the salvaged commit.
The standalone thread-pool fallback in _deliver_result() runs inside the
`except RuntimeError:` block (taken when asyncio.run() sees a running loop).
When future.result() raised there (SMTP ConnectionError, timeout, etc.), the
exception was NOT caught by the sibling `except Exception:` — it escaped
_deliver_result() and crashed the whole delivery loop, silently skipping every
remaining target. Multi-target delivery (e.g. deliver: 'email:a,email:b') is a
documented feature, so this broke a promised contract.
Wrap the fallback in its own try/except so a per-target failure is logged with
exc_info and the loop continues to the next target.
Fixes#47163
The streaming think-tag suppressors in cli.py (_stream_delta) and
gateway/stream_consumer.py (_filter_and_accumulate) matched tag names
with case-sensitive str.find(), so only the exact-case literals in the
tag tuples were caught. Mixed-case variants a model may emit — <Think>,
<ThInK>, <REASONING>, <Thought> — slipped through and leaked raw
reasoning into the user-visible stream.
Match against a lowercased view of the buffer with lowercased tag names
at all three sites (open-tag boundary search, partial-tag hold-back,
close-tag search) in both paths. Only KNOWN tag names are matched — no
substring matching — and the block-boundary gating that protects prose
mentions of <think> is preserved.
- 6 parametrized case-insensitive regression tests in each of
tests/gateway/test_stream_consumer.py and
tests/cli/test_stream_delta_think_tag.py.
Salvaged from PR #27289 by @YLChen-007.
When a model emits an inline <think>...</think> block but the opening
tag is dropped upstream (thinking-mode toggle, truncated stream, or
incomplete upstream filtering), the bare </think> close tag leaked
through to the user in the live progressive edit. The agent-side final
scrubber (agent/think_scrubber.py) already had _strip_orphan_close_tags;
this ports the same logic into GatewayStreamConsumer so the streaming
display stays clean too.
- _filter_and_accumulate: strip orphan close tags before appending the
'no-opening-tag' branch text to _accumulated.
- _flush_think_buffer: same on stream end for held-back partials.
- 14 regression tests (TestStripOrphanCloseTags): all 6 close-tag
variants, multi-tag, partial-tag-untouched, trailing whitespace,
and end-to-end through _filter_and_accumulate / _flush_think_buffer.
Only strips KNOWN close-tag names (case-insensitive) — never arbitrary
tag-shaped substrings — so comparison operators and unrelated prose are
preserved.
Salvaged from PR #43192 by @testingbuddies24.
scripts/release.py AUTHOR_MAP is greped by the Contributor Attribution
Check to resolve a commit author's email -> GitHub username. Add
huangsen365@gmail.com -> huangsen365 so this PR's commits pass the check.
(This commit originally also carried a gateway race-test flake fix; that
edit is now dropped because main independently hardened the same test with
a superior server._sessions snapshot/restore isolation, making ours
redundant.)
`@file` / `@folder` context-reference expansion enforced its own narrow
deny-list (`_ensure_reference_path_allowed` in `agent/context_references.py`)
that only covered `~/.ssh` keys, a handful of shell dotfiles, `~/.hermes/.env`,
and `skills/.hub`. It never blocked the credential stores that the canonical
read guard (`agent/file_safety.get_read_block_error`) protects: provider API
keys (`~/.hermes/auth.json`), Anthropic OAuth tokens
(`~/.hermes/.anthropic_oauth.json`), MCP OAuth material (`~/.hermes/mcp-tokens/`),
webhook HMAC secrets, and project-local `.env` files.
This matters because the messaging gateway feeds **untrusted** remote text
straight into reference expansion: `gateway/run.py` calls
`preprocess_context_references_async(..., allowed_root=_msg_cwd)` where
`_msg_cwd` defaults to the operator's HOME when `TERMINAL_CWD` is unset. A chat
peer (Telegram/Discord/Slack/...) could send `@file:~/.hermes/auth.json`, pass
the `allowed_root` check (it resolves under HOME), slip past the narrow list,
and have the operator's live keys read into the agent's context — where the
model would typically echo or act on them.
Rather than duplicate and re-sync a second secret list, this routes the guard
through the existing single source of truth. A reviewer might ask "why not just
add `auth.json` to the local list?" — because the local list has already drifted
once (a prior commit had to add `.config/gh`); anchoring to
`get_read_block_error` means every future addition there protects this path too.
The narrow checks are kept as a fallback since they also cover dirs that guard
does not (`.aws`, `.gnupg`, `.kube`, etc.), and the canonical lookup is wrapped
so it can never crash reference expansion.
N/A
- [x] 🔒 Security fix
- `agent/context_references.py`: `_ensure_reference_path_allowed` now also
consults `agent.file_safety.get_read_block_error` after its existing checks
and refuses the reference when that canonical guard flags the resolved path.
The lookup is wrapped so guard-resolution failures fall back to the explicit
checks instead of breaking expansion.
- `tests/agent/test_context_references.py`: added
`test_blocks_canonical_read_denylist_credential_stores`, asserting that
`@file` attaches for `auth.json`, `.anthropic_oauth.json`, `mcp-tokens/*`, and
a project-local `.env` are all refused and their secret bodies never reach the
expanded message.
- `scripts/release.py`: added the contributor email to `AUTHOR_MAP` (release
gate).
1. `scripts/run_tests.sh tests/agent/test_context_references.py` — all 15 tests
pass, including the new credential-store case.
2. Regression proof: stash `agent/context_references.py`, run the suite with
`-- -k canonical`, and confirm the new test fails (secrets leak into the
message) without the fix; restore and confirm it passes.
3. `ruff check agent/context_references.py tests/agent/test_context_references.py`
and `python scripts/check-windows-footguns.py agent/context_references.py
tests/agent/test_context_references.py` both pass.
- [x] I've read the Contributing Guide
- [x] My commit messages follow Conventional Commits (`fix(scope):`, etc.)
- [x] I searched for existing PRs to make sure this isn't a duplicate
- [x] My PR contains **only** changes related to this fix (plus the AUTHOR_MAP release gate)
- [x] I've run the test suite for the touched area and all tests pass
- [x] I've added tests for my changes (required for bug fixes)
- [x] I've tested on my platform: macOS 15 (Darwin 25.5)
- [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) — or N/A
- [x] I've updated tool descriptions/schemas if I changed tool behavior — or N/A
models_dev.py's fetch uses a synchronous requests.get(timeout=15). Called
from the async gateway message handlers, it blocked the event loop for up
to 15s, starving Discord heartbeats and causing ClientConnectionResetError
disconnects.
Adds get_model_context_length_async() which offloads the entire sync
resolution chain to a worker thread via asyncio.to_thread(), and switches
the two async gateway call sites (_prepare_inbound_message_text,
_handle_message_with_agent) to await it. The loop stays responsive; the
sync path remains the single source of truth for the cache.
Salvaged from PR #22753 by @itenev. Follow-up: dropped the unused
fetch_models_dev_async/lookup_models_dev_context_async aiohttp variants
from the original PR (dead code with zero callers that had drifted from
the sync cache logic) — the to_thread wrapper already runs the sync path
off-loop, so they were redundant.
Path(raw).name reduces '..'/'.'/'' to themselves, so basename
extraction alone still let a Graph-provided display_name of '..' or
'../' escape the temp recording directory (tmp_dir / '..' resolves to
the parent). Reject the dot-only basenames explicitly and fall back to
the artifact id. Extends @outsourc-e's regression coverage with the
dot-only cases.
Teknium
Gille
Erosika
brooklyn!
szafranski
Drexuxux
kshitijk4poor
ethernet
Ben Barclay
Vishal Dharmadhikari
Jeffrey Quesnelle
Kshitij Kapoor
uzaylisak
Shannon Sands
Ronald Reis
HexLab98
hmirin
konsisumer
devatnull
David Zhang
Jneeee
Mibayy
Morgan K
Roger Smith
Tarun Ravikumar
CharmingGroot
crazywriter1
nankingjing
Steve Lawton
Brett
Zeheng Huang
shawchanshek
Tao Chen
Swissly
YLChen-007
testingbuddies24
Wing Huang
mrparker0980
itenev