Commit Graph

5021 Commits

Author SHA1 Message Date
Teknium e69b8e561d feat: consolidate 'hermes version' into 'hermes --version', remove the subcommand
'hermes --version' (and -V) now prints the full version report — banner
version line with upstream SHA, install directory, authoritative install
method, Python and OpenAI SDK versions, and update status — making the
separate 'hermes version' subcommand redundant. The subcommand is removed.

- _startup_fast.print_fast_version_info() is now THE canonical version
  printer: static lines print instantly from stdlib probes, then the
  banner label, install-method resolver, and update check lazy-import
  after the first line is on screen (each degrades gracefully).
- main.py _print_version_info() delegates to it (used by /version in the
  CLI chat surface and the --version flag path); the old duplicate
  implementation is deleted.
- hermes_cli/subcommands/version.py removed; parser wiring, subcommand
  sets, console-engine extraction entry, and tests updated. Hermes
  Console keeps a 'version' command wired to the shared printer.
- Termux fast paths now include update status too (previously
  check_updates=False).
- Docs/i18n, CONTRIBUTING, SECURITY, and nix checks updated to
  'hermes --version'.
2026-08-20 03:05:46 -07:00
Teknium d425658d27 Merge pull request #90688 from NousResearch/feat/keyed-failure-one-shot-rescue
feat: failing keyed web backends rescue onto the keyless ring for one call, never sticky
2026-08-20 03:05:40 -07:00
Teknium 1647d030cf fix(update): call out GitHub rate limiting/outage on fetch 429 instead of a generic failure
A GitHub-side HTTP 429 during 'hermes update' printed only
'Failed to fetch updates from origin.' — and the curl
'unable to access ... returned error: 429' shape even matched the
network-error branch, blaming the user's connection for a GitHub
outage.

- new _classify_fetch_failure(): 429/rate-limit -> 'GitHub is rate
  limiting requests or having an outage — try again in 5 minutes';
  5xx -> outage message with githubstatus.com; ordered BEFORE the
  generic 'unable to access' network check
- both fetch-failure sites (update apply + --check) now share the
  classifier via _print_fetch_failure(), and both always print the
  first raw stderr line so the wire error stays diagnosable
- tests: classifier matrix + E2E against a live local HTTP server
  returning 429 through real git

Fixes #89287
2026-08-20 02:45:57 -07:00
Teknium aca40d1d63 fix(sessions): error paths return non-zero exit codes (delete/rename/prune/import) 2026-08-20 02:06:05 -07:00
Teknium d1eefe6acc feat: keyed web backends get a one-shot keyless rescue on failure — never sticky
When the chosen/keyed backend fails a web_search or web_extract call
(bad key, upstream outage, 5xx, raised exception), that single call
retries on the keyless free-tier ring instead of erroring. The next
call attempts the chosen backend again — no sticky failover, no state.
Resolves the keyed half of #78984/#32159 (keyless half landed in the
ring PR).

- tools/web_tools.py: _rescue_eligible (keyed ring vendors + non-ring
  backends eligible; keyless-mode calls excluded — they already walked
  the ring), _rescue_search/_rescue_extract (search annotates
  rescued_from + backend_error naming the original failure and the
  retry-next-call semantics; extract rescues only whole-batch failures,
  partial failures pass through untouched; rescue failure preserves the
  ORIGINAL backend error with the rescue note appended)
- both dispatchers wrap the provider call: failure-results AND raised
  exceptions rescue; ineligible paths re-raise unchanged
- web.keyless_rescue config key (default true; implicitly off when
  keyless_fallback is off); docs updated

Live E2E: keyed Tavily with an invalid key 401'd and the call was
served by the real ring with the rescue annotation; a second call
re-attempted Tavily first (statelessness proven); whole-batch extract
rescue returned real page content. 13 new tests; 67 green across the
keyless suites.
2026-08-20 02:04:32 -07:00
Teknium 0a8a4cdb3d fix(backup): friendly error on unwritable output path instead of raw traceback 2026-08-20 01:47:06 -07:00
Teknium 138e482ed0 fix(config): set coerces negatives/whitespace/null and rejects malformed keys 2026-08-20 01:46:54 -07:00
Teknium 76653a8eba fix(sessions): prune/archive spare pinned sessions by default (data loss) 2026-08-20 01:46:20 -07:00
Teknium f796239c6b Merge pull request #90572 from NousResearch/feat/keyless-tavily-firecrawl-failover
feat: keyless web tier is now a 5-vendor free rotation (Exa/Parallel/Tavily/Firecrawl/Keenable) with ring failover + honest doctor readiness
2026-08-20 01:46:16 -07:00
Teknium 3f67921fca fix(cli): /undo typo no longer quits the CLI; +3 slash-command papercuts 2026-08-20 01:46:08 -07:00
Teknium 90e477d3ed Merge remote-tracking branch 'origin/main' into feat/keyless-tavily-firecrawl-failover 2026-08-20 00:18:29 -07:00
Teknium 4ea69d9d2c feat: keyless web tier becomes a 5-vendor round-robin ring (adds Tavily, Firecrawl, Keenable)
Fresh installs with zero web credentials now rotate web_search/
web_extract across FIVE vendors' public free tiers — Exa, Parallel,
Tavily, Firecrawl, Keenable — instead of a 2-vendor 50/50 split, with
next-in-line ring failover on rate limits (multi-hop until a vendor
serves or the ring is exhausted; served_by marks the actual vendor).

- plugins/web/keenable/: new bundled provider (search via /v1/search,
  fetch via /v1/fetch; keyed Bearer or keyless with the mandatory
  X-Keenable-Title app header). Credit: integration proposed by
  Ilya Gusev (Keenable) in #49758; Free/Paid picker rows included.
- keyless_mcp: tavily/firecrawl/keenable keyless search+extract
  wrappers, _KEYLESS_RING + per-process round-robin cursor (seeded by
  the random session id, advances per unpinned request), pinned-vendor
  entry (pin = start there; rotation off), paid-pinned vendors excluded
  from the ring entirely.
- Tavily/Firecrawl providers route keyless traffic through the ring;
  both are now default-on ring members (no longer selection-gated).
- web_tools/registry: keenable in backend sets, auto-detect, availability
  probes; _keyless_preference() delegates to the ring cursor.
- KEENABLE_API_KEY in OPTIONAL_ENV_VARS; docs updated (ring semantics).

Live E2E: all 10 vendorXcapability paths (5 search + 5 extract) served
real results keyless; rotation cycled all five vendors over 5 dispatch
calls; double-throttle failover walked exa->parallel->tavily.
2026-08-20 00:17:25 -07:00
Teknium f309f92d30 feat: hermes worktree list/prune — attended reclaim for accumulated worktrees and merged branches
The startup pruner is deliberately conservative (unattended, pre-banner),
so real installs accumulate what it can never touch: trees preserved for
untracked-only scratch, and orphaned local branches beyond the two
auto-generated prefixes it deletes. A measured multi-agent box: 35 trees /
15GB / 244 local branches, 120 of them fully merged.

New attended surface (hermes_cli/worktree_gc.py + worktree_cmd.py):
- hermes worktree list — audit every tree: age, size, verdict, reason,
  plus deletable-branch count
- hermes worktree prune [--dry-run|--trees-only|--branches-only]
- /worktree prune [--dry-run] — same engine in-session; never touches the
  session's own active tree
- startup escalation: one WARNING when .worktrees/ exceeds 10 trees or
  5GB, naming the reclaim commands (silence is how boxes hit 15GB)

Safety invariants (shared with the startup pruner via cli.py primitives):
tracked modifications and unique unpushed commits never deleted at any
age; live-locked trees untouched; branch deletion gated on worktree
removal success; untracked-only scratch ARCHIVED to
~/.hermes/archive/worktree-prune/ before its tree is reaped.

Branch GC is content-gated, not name-gated: any local branch fully merged
or git-cherry patch-equivalent upstream is safe to delete (rebase merges
rewrite SHAs, so --merged alone misses the dominant leak); unique-commit,
checked-out, protected, and stale-base (>50 ahead) branches are kept.
Classification is parallel (8 workers) — 244 branches audit in ~64s live.

git timeouts degrade to keep (returncode 124) instead of crashing the
audit — live-verified failure on a 746MB .git repo.

16 behavior-contract tests against real git fixtures; live dry-run on the
production repo: 12 trees reclaimable, 120 branches deletable, 0 false
positives among kept trees.
2026-08-19 23:55:20 -07:00
kshitijk4poor 9ed06ca2b6 refactor(cli): fold lock-bit review findings - docstrings, dead tilde forms, _lock_twins idiom
Post-review cleanup on the salvage: update the three alias-installer docstrings to mention lock twins (and fix ctrl-enter's stale 'stock maps none of these' claim - stock maps the tilde form to plain ControlM, which the overwrite fixes); skip the never-emitted modifier-1 tilde forms in _install_paired; name the twins-only idiom as _lock_twins() and use it at the legacy-nav + PUA sites; route the Esc loop through _lock_variants; hoist the per-base table lookup out of the lock loop in the legacy-nav section.
2026-08-20 12:16:20 +05:30
kshitijk4poor 446da3ef56 fix(cli): widen lock-bit coverage to alias installers, legacy nav keys, and PUA functional keys
Follow-up to the salvaged #89676 + #90291 lock-bit fixes: extract a shared _lock_variants() helper and cover the sites both PRs missed - install_shift_enter_alias / install_ctrl_enter_alias / install_cmd_backspace_alias CSI-u spellings, legacy CSI-letter and CSI-tilde navigation twins derived from the existing table for ALL modifiers 1-16 (not just plain/shift), plain F1-F4 SS3 fallback, unmodified CSI-u keys (Tab/Enter/Space/Backspace), and kitty PUA functional keys (keypad, F13-F24, Ignore range) under lock bits. 8 new tests.
2026-08-20 12:16:20 +05:30
grahf 6471f53619 fix(cli): map NumLock/CapsLock modifier-bit variants under kitty protocol
With the kitty keyboard protocol push active (CSI >1u disambiguate), kitty
encodes lock-key state into the CSI modifier field of function keys: a
plain Down with NumLock on arrives as ESC[1;129B (NumLock), ESC[1;65B
(CapsLock), or ESC[1;193B (both) instead of the legacy ESC[B. Stock
prompt_toolkit maps none of these, so the parser fires Escape and
inserts the remainder as literal text in the input line.

03bf85d83 restored the kitty push and completed the extended-key alias
table but left these lock-bit variants unmapped, so kitty + NumLock
still leaks [1;129A/B for arrow/nav keys.

Map modifier 129/65/193 (plain) and 130/66/194 (+shift) for arrows,
Home/End, Insert/Delete/PageUp/PageDown, and CSI-u Enter/Tab/Backspace/
Space to their plain keys.
2026-08-20 12:16:20 +05:30
liuhao1024 118dbe871f fix(cli): map kitty CSI-u lock-bit variants so key combos survive NumLock
kitty and ghostty OR the CapsLock (64) / NumLock (128) state into the
CSI-u modifier parameter. With NumLock on, Ctrl+C arrives as
ESC[99;133u (5 + 128) instead of ESC[99;5u; the alias table had no
entry for it, so every key combo leaked as literal text like
[127;133u (#89651). Install every CSI-u alias with the lock-bit
variants (+64/+128/+192); the xterm modifyOtherKeys encoding never
carries lock bits, so the ESC[27;N;CP~ form is left untouched. The
Esc-key registration now covers modifier 1 as well (1+128=129 is a
lone Esc with NumLock on).
2026-08-20 12:16:20 +05:30
Cassie Gray b38c40319d fix(cli): align hermes memory status and docs with memory tool gate 2026-08-19 23:15:01 -07:00
MindDragonLabs 5c03fbedc6 fix(config): recognize memory nudge interval 2026-08-20 11:36:54 +05:30
Teknium 797bc4bf9b Merge remote-tracking branch 'origin/main' into feat/keyless-tavily-firecrawl-failover 2026-08-19 23:04:36 -07:00
Slobaka 6ff341c4d6 fix(doctor): web readiness reflects the selected provider's real state (#78412)
Salvaged from #78434 by @Slobaka (also the issue reporter; earlier than
the competing #78436). hermes doctor no longer paints a green web check
when the explicitly selected provider cannot initialize — web splits
into per-capability rows (web search / web extract) resolved through
the same registry resolvers the dispatchers use, with readiness from a
true availability probe (_provider_is_ready).

Keyless-tier integration on top of the salvage:
- _provider_is_ready counts is_keyless_available() as ready — keyless
  mode is a working state, not a misconfiguration (zero-config installs
  and selected-keyless Tavily/Firecrawl show ok, not warn)
- Tavily/Firecrawl gain is_keyless_available() (True only when
  explicitly selected — they stay out of the zero-config fallback)
- doctor triggers plugin discovery before reading the registry (fresh
  doctor processes saw an empty registry and warned on everything)

E2E: searxng-selected-without-URL warns (the #78412 repro);
zero-config, tavily-keyless, firecrawl-keyless all read ok;
parallel pinned paid without a key warns.
2026-08-19 23:03:58 -07:00
Lakshya Agarwal 6bf4375755 feat(onboarding): enhance Tavily backend support for keyless access
- Added support for keyless Tavily integration in the onboarding flow, allowing it to be recognized as available without an API key.
2026-08-19 22:44:11 -07:00
Lakshya Agarwal ee37f3d897 feat(tavily): update Tavily integration to support keyless access
- Updated the Tavily API key description to clarify that it is optional and keyless access is supported.
- Modified the Tavily plugin and provider to handle requests with or without an API key, using Bearer authentication when the key is provided.
- Enhanced documentation to reflect the new keyless functionality and updated environment variable descriptions.
- Added tests to ensure correct behavior for both keyed and keyless requests.
2026-08-19 22:42:58 -07:00
Teknium fa89d87ea6 fix(checkpoints): bare /rollback falls back to a labeled all-directories view (#10505, reapply #10633) 2026-08-19 22:41:13 -07:00
Brooklyn Nicholson b4f978d983 fix(nous): treat "takes no reasoning parameter" as a definitive no
Both the wire path and the picker only consulted the catalog's
`mandatory` flag, so a route the Portal lists as accepting no reasoning
parameter at all still got sent a disable, and still offered a Thinking
toggle in the model picker.

For a route it serves, the aggregator's own catalog outranks the
models.dev inference: `supports_reasoning: false` now suppresses the
disable on the wire and drops reasoning controls from the picker
entirely, so there is no disable left to describe.
2026-08-19 23:28:14 -05:00
Brooklyn Nicholson 9c0cd1add2 fix(nous): make "thinking off" stick on a cold start
Portal reasoning capabilities were held only in memory, so a process that
had not yet fetched them answered "unknown" — and on that answer the Nous
profile drops the disable rather than risk a 400. A short-lived process
(`hermes -p`, a cron job, a freshly booted gateway) is always in that
state, so every one of those runs silently ignored "thinking off" and
billed the user for reasoning they had turned off.

The parsed catalog is now mirrored to `cache/reasoning_caps.json`, keyed
by the URL it came from, and hydrated on a cold lookup without touching
the network. Every picker and pricing fetch already pulls that same
document, so they seed the mirror for free.

The catalog URL itself now resolves through the same ladder as the rest
of the Nous catalog reads (`NOUS_INFERENCE_BASE_URL` → credential base →
production) instead of being pinned to production, which had a staging
profile deciding the reasoning-mandatory question from prod's answers.
Keying the mirror by URL keeps those deployments apart.
2026-08-19 23:28:14 -05:00
Brooklyn Nicholson d15cd18fa1 feat(desktop): hide the Thinking toggle where a disable is rejected
The picker offered an off switch for every reasoning model, including routes
whose upstream answers a disable with HTTP 400 — so "thinking off" was a
control that could not work. Carry the catalog's mandatory verdict through
model.options as can_disable_reasoning and hide the toggle when it is false.

Effort levels are left alone. The catalog's supported_efforts under-reports
what the Portal serves (z-ai/glm-5.3 publishes max, high, low yet honors
minimal at its lowest thinking), so filtering the scale by it would hide
levels that work.
2026-08-19 22:14:56 -05:00
Brooklyn Nicholson 608fa9c7af feat(models): read Nous Portal reasoning capabilities from its catalog
The Portal serves OpenRouter's catalog schema, so the existing parser and
cache-only tri-state contract carry over unchanged. Only the HTTP fetch is
generalized across the two catalogs; each keeps its own cache because they
list different models.

The Portal 403s a catalog read with no User-Agent, so the shared fetch now
sends one.
2026-08-19 22:14:56 -05:00
Teknium aebab05f9e Merge pull request #90313 from NousResearch/feat/keyless-web-search-fallback
feat: web search works keyless on fresh installs (Parallel + Exa free tiers)
2026-08-19 19:47:12 -07:00
Teknium 258410a184 fix(cli): first launch banner shows the seeded skill catalog, not "No skills installed" 2026-08-19 19:44:42 -07:00
Teknium 76bf6c7c40 fix(cli): bare /hatch no longer freezes input with an invisible raw input() prompt 2026-08-19 19:42:31 -07:00
GarlicGo 466665282b fix(cli): Fix oneshot skills preload 2026-08-19 19:41:52 -07:00
Teknium 1fa66f2577 Merge remote-tracking branch 'origin/main' into feat/keyless-web-search-fallback
# Conflicts:
#	website/docs/user-guide/configuration.md
2026-08-19 19:36:12 -07:00
Teknium d0132b5821 fix(cli): give every wizard free-text prompt arrow-key and Ctrl+A/E editing
Widens #90327's line_input() to the whole bug class: all 46 bare input()
free-text prompt sites across the setup wizards (model_setup_flows, setup,
config, gateway, auth, auth_commands, plugins_cmd, skills_hub, bundles,
setup_whatsapp_cloud, main) now route through line_input(), and the shared
cli_output.prompt() / setup.prompt() helpers do too — so every CLI wizard
gets cursor editing, not just the custom model prompt.

Redirected stdin and missing prompt_toolkit keep builtin input() behavior.
E2E: real PTY with raw escape bytes through line_input, cli_output.prompt,
and setup.prompt (arrows + Ctrl+A/E edit correctly); redirected-stdin
fallback verified.
2026-08-19 19:34:36 -07:00
Gille fa62b22ee7 fix(cli): enable editing in custom model prompt 2026-08-19 19:34:36 -07:00
Teknium f7d90c9410 refactor: single canonical reasoning-effort vocabulary ends the per-vendor clamp drift
The #89503/#70058/#74295/#87279 bug class kept regenerating because every
transport and provider profile hand-rolled its own effort translation map
(9 sites, 4 distinct policies). New agent/reasoning_effort.py is the single
source of truth:

- EFFORT_LADDER: canonical low->high ordering (superset check against
  VALID_REASONING_EFFORTS pinned by test)
- clamp_effort(): one policy — supported passes verbatim, otherwise nearest
  WEAKER supported level (never escalate, never invert the ladder), floor
  when nothing weaker, 'none' never a degradation target, declared
  vendor-documented overrides win, bespoke names pass through
- declared wire vocabularies as data: OpenAI-compat, Codex Responses,
  xAI (4.6/legacy), Actual relays, Kimi K3/K2, TokenHub, GLM-5.2,
  DeepSeek V4, Ollama Cloud, Meta, Solar

Converted sites (all behavior-preserving except noted):
- chat_completions chokepoint, Kimi + TokenHub paths
- codex transport (backend branches now pick a declared set)
- auxiliary_client Responses path
- hermes_cli.models clamp_reasoning_effort_to_supported -> thin wrapper
- plugins: kimi-coding, zai, opencode-zen, deepseek, ollama-cloud,
  meta-ai, upstage, custom (copilot already routes via the wrapper)

Behavior fixes the shared policy surfaces:
- ollama-cloud/opencode-go 'minimal' now degrades to 'low' instead of
  being dropped (drop left the server default = MORE thinking than asked)

New tests: ladder contract (every configurable level is clamped by every
declared wire set; monotonicity across the full ladder for every set).
2026-08-19 19:29:10 -07:00
fangliquanflq cfc55d3487 fix(config): remove obsolete cwd warning parameter 2026-08-19 19:24:41 -07:00
fangliquanflq a93f1b2bec fix(config): warn for all deprecated dotenv cwd entries 2026-08-19 19:24:41 -07:00
fangliquanflq 31561e37ed fix(config): read deprecated cwd settings from dotenv 2026-08-19 19:24:41 -07:00
Teknium 98b6f8676d fix(desktop): Models/Providers settings no longer hang 20s when gh CLI is signed out
/api/model/options probed Copilot auth via `gh auth token` four separate
times per payload build. When gh has no credential store for the backend's
HOME (fresh profile, desktop-spawned backend, CI), each probe blocks its
full 5s subprocess timeout on keyring/D-Bus, so every open of the Desktop
Models or Providers settings page took 20s — past the renderer's 15s IPC
budget, painting 'Error invoking remote method hermes:api: Timed out'.

Fix: cache the gh-CLI probe result (hit or miss) for 5 minutes with an
invalidation hook, feed gh stdin=DEVNULL, and disable gh interactive
prompts/update notifier in the probe env.

Measured on the failing profile: 20.5s -> 5.3s cold (one bounded probe),
0.03s warm.
2026-08-19 19:22:48 -07:00
Jeffrey Quesnelle 612b3633d2 Merge pull request #77915 from bbednarski9/feat/relay-native-plugin-init
feat(relay)!: initialize static/dynamic plugins via native integration, remove opt-in plugin
2026-08-19 22:11:13 -04:00
Teknium 095f003377 Merge remote-tracking branch 'origin/main' into feat/keyless-web-search-fallback
# Conflicts:
#	hermes_cli/tools_config.py
2026-08-19 16:48:40 -07:00
Teknium 449471c334 feat: runtime stall guards — identical-call loop breaker and continue-intent recovery (agent.stall_guards)
Composio eval traces showed Hermes wasting turns re-issuing identical tool
calls (same tool, same args, same result — 3x/4x in one run) and ending
turns by announcing an action it never took. Two conservative, config-gated
guards (agent.stall_guards, default true):

- Identical-call loop breaker: ToolCallGuardrailController.observe_identical_call
  tracks the consecutive streak of (tool, canonical args, result-hash); on
  the 3rd identical call a compact one-line notice is appended to that tool
  RESULT at construction time (cache-safe — tool results are append-only).
  Never blocks the call. Pollers (process, *_get_result, *_poll) are exempt
  via STALL_GUARD_REPEATABLE_TOOLS. Streak resets on any different call,
  changed result, or new turn. Observed on the raw result before the
  tool-loop warning suffix so its changing count can't defeat matching.

- Said-continue-but-stopped recovery: trailing_continue_intent() detects a
  short reply ENDING on an announced next action ('Let me now…', 'I will
  now…', 'Next, I…'); the conversation loop feeds it into the EXISTING
  intent-ack continuation path (same interim-assistant + user-nudge
  mechanism, same codex_ack_continuations cap of 2), preserving message
  alternation — no parallel recovery machinery.

Config: agent.stall_guards in DEFAULT_CONFIG; docs in configuration.md;
unit tests for streak/allowlist/reset/gate and detector pos/neg cases.
2026-08-19 16:34:21 -07:00
Teknium 803397ecc3 feat: wall-clock run budget — wrap-up injection at 80% and deadline-scaled stale timeouts (agent.run_budget_seconds / --run-budget) 2026-08-19 16:32:17 -07:00
Teknium d762ed9b3c feat: execution-discipline guidance now reaches all tool-capable models (config model.execution_guidance)
Un-fences OPENAI_MODEL_EXECUTION_GUIDANCE from the gpt/codex/grok substring
check and gives it its own injection gate, independent of
tool_use_enforcement, controlled by config.yaml `agent.execution_guidance`
(auto/true/false/list — same semantics as tool_use_enforcement). The "auto"
list (EXECUTION_GUIDANCE_MODELS) now also covers deepseek, kimi, qwen, glm,
minimax, mimo, and mistral.

Composio agentic-eval traces showed Hermes+DeepSeek/Kimi failing where
competitors passed: financial math done in prose, no read-back after
external writes, malformed identifiers "repaired", completeness claimed
despite count mismatches. The discipline block existed but those models
never received it.

The block is extended with compact clauses distilled from that analysis:
- external-write read-back (tool-call success is not task success; internal
  file edits already confirmed by the tool are not re-verified)
- count reconciliation (declared totals/has_more are hard assertions)
- literal preservation (never normalize identifiers that fail a stated
  format; lookup success does not validate a malformed token)
- retry-differently (empty/partial/suspiciously narrow results get a
  broader retry before concluding)
- completion gated on verification (done = every named acceptance
  criterion verified, never a plausible subset)

The todo tool description now encourages enumeration-as-checklist for
"all N items" tasks and gates completed status on verified work, never
intent.

Guidance is chosen once at session start keyed on model name, so the
system prompt stays byte-stable for the life of a conversation.

Supersedes/absorbs prior contributor proposals: #20588, #35087, #41874
(MiMo), #53847 (GLM tool-calls-as-text stall).

Co-authored-by: Mat-London <56627804+Mat-London@users.noreply.github.com>
Co-authored-by: intelac <8803887+intelac@users.noreply.github.com>
Co-authored-by: 6ylqq <51219463+6ylqq@users.noreply.github.com>
Co-authored-by: tauros1983 <267660491+tauros1983@users.noreply.github.com>
2026-08-19 16:16:37 -07:00
Teknium aa3c5e59d3 fix(tools): honor raw stt.provider: local; finish _reconfigure_provider provider-string migration
Two real gaps the CI-red sibling tests exposed:

- read_selection() treated EVERY raw stt.provider: local as the legacy
  DEFAULT_CONFIG seed and reported no-selection — but the seed never
  reached config.yaml (save_config strips schema defaults), so a
  picker- or hand-written local pick was silently discarded and the
  autodetect ladder could route an explicit local user to cloud STT.
  A raw 'local' is now a genuine selection; the merged-view ambiguity
  note replaces the over-broad shim (mirror comment updated in
  nous_subscription._selected_provider and _get_provider).

- _reconfigure_provider was half-migrated: the tts/stt/browser/web
  branches and the managed-category fallthrough still wrote
  use_gateway flags and vendor names for managed rows. They now write
  the single provider string ('nous' for managed rows) and pop the
  legacy key, matching _write_provider_config.
2026-08-19 16:10:01 -07:00
Teknium b10c5a8084 fix(cli): persist one provider string per picker row; mirror strict routing in status
Every hermes tools row now writes exactly one selection value per
category — managed 'Nous Subscription' rows write 'nous', BYOK rows the
vendor name (including the historically-unset BYOK-FAL image row) — and
use_gateway is no longer written; fresh picks drop any legacy key so the
read-time shim cannot override them. The non-managed clear now resolves
the category from the row's own markers, covering plugin-injected rows
the TOOL_CATEGORIES loop missed. Setup-flow writers (managed defaults,
gateway enablement) store 'nous', and the feature-state mirrors in
nous_subscription.py compute per-category selections with the same
legacy interpretation so hermes status matches runtime: a stored vendor
selection pins direct (managed availability no longer lights it up) and
an explicit non-camofox selection beats a stray CAMOFOX_URL.
2026-08-19 16:10:01 -07:00
Teknium 099258ef48 fix(voice): route TTS/STT OpenAI audio on the stored selection, not credentials
Both _resolve_openai_audio_client_config resolvers now switch on the
stored provider string: 'nous' (or legacy use_gateway: true) => managed
openai-audio gateway only, erroring by selection name when unentitled —
the STT twin previously never read the stored gateway intent at all, so
a direct OPENAI_API_KEY silently overrode the Nous Subscription pick;
stored vendor => direct credentials only with a selection-naming error
on missing keys (no silent managed fallback); never-configured keeps the
legacy ladder. DEFAULT_CONFIG stops seeding stt.provider: local, and the
seeded value on existing configs is treated as no-selection so autodetect
keeps working for that installed base.
2026-08-19 16:10:01 -07:00
Teknium f08d3e400f feat: hermes tools lets Exa/Parallel users pick the free keyless or paid keyed endpoint
Exa and Parallel now each render as two picker rows in hermes tools —
'Free (keyless)' and 'Paid (API key)'. Selection persists to
web.provider_tier.<name>:
- free: always the anonymous public endpoint, even with a key set
- paid: always the keyed SDK path; missing key errors instead of
  silently downgrading to the free tier (is_keyless_available also
  returns False so the auto-fallback walk can't route there)
- unset: auto (key present -> paid, else keyless)

Mechanism: get_setup_schema() gains a 'variants' list the picker
flattens into sibling rows sharing one web_backend; selection writes
the tier via both _write_provider_config sites; active-row detection
matches the tier (auto mirrors use_keyless). Routing goes through a
single use_keyless() chokepoint shared by search+extract in both
providers.

Live E2E: tier=free with a fake key present searched keyless OK (a
keyed call would have 401'd); tier=paid without key errored naming
PARALLEL_API_KEY; picker rows verified for both vendors x both tiers.
2026-08-19 15:36:20 -07:00
Teknium 96c2fd3c04 feat: web search/extract now work keyless on fresh installs via Parallel + Exa free tiers
With zero web credentials configured, web_search/web_extract previously
resolved to the nonfunctional firecrawl sentinel and errored. Now the
backend resolution walks a strictly-last keyless tier: Parallel's and
Exa's public anonymous MCP endpoints (the same free tiers opencode ships
as its default search path).

- plugins/web/keyless_mcp.py: minimal JSON-RPC tools/call client for
  mcp.exa.ai + search.parallel.ai (SSE + plain JSON parsing, typed
  errors, per-process random session id, no user identifiers)
- WebSearchProvider.is_keyless_available(): separate weaker tier that
  never leaks into is_available(), so keyed setups are never pre-empted
- Exa/Parallel providers: route to keyless endpoints when their key is
  absent; keyed SDK path unchanged
- registry + _get_backend(): keyless walk (parallel -> exa) strictly
  after every keyed/importable candidate; check_web_api_key() lights
  the tools up on zero-credential installs
- web.keyless_fallback config key (default true) to disable the tier
- docs: web-search.md + configuration.md

E2E-verified against both live endpoints from an isolated HERMES_HOME
(search + extract via the real dispatchers, disable-flag negative path).
2026-08-19 15:15:27 -07:00