14 Commits

Author SHA1 Message Date
Robin Fernandes 51e39af967 feat(free-tier): ruled behaviour for every welcome-api failure, with friendly copy and a fault-injecting rehearsal server
The free tier depends on the account service (NAS) and the welcome inference
host, and Hermes had no honest answer for most of the ways either can refuse
or fail: the NAS codes it matched were never sent, the tier-dark 403 carried
no message to match, a single boot-time blip disabled minting for the whole
process, and a structured rate-limit refusal never reached the cross-session
guard, so the "sign in for a bigger allowance" prompt was dead code.

Backend
- anon_auth: classify what NAS actually sends (404 not_found, 503
  temporarily_disabled, 429 + Retry-After, 428 pow_*, 403 account_locked)
  into one ANON_* code each, carrying retry_after / retryable on AuthError.
- Replace the process-lifetime mint memo with a per-profile cooldown that
  honours the server's wait, climbs a short ladder when the service is
  unreachable, never retries terminal codes, and yields to the user's own
  retry (force=True).
- Bootstrap record carries error_code / retryable / retry_after; a bounded
  background loop retries transient failures and re-announces setup.ready.
  setup.status and free_tier.status expose the block; free_tier.provision is
  the forced retry.
- Inference: a generic 403 from a welcome host is the tier refusing (keyed on
  the route); model_not_free moves onto the gateway's alternate once;
  anon_on_paid_host re-reads the route once; a long rate_limited refusal
  trips the cross-session guard; a locked account is retired but never
  replaced; terminal copy on the free route is one plain sentence.
- Sign-in: Failed keeps the service's code and wait; account_busy is
  retryable; the OAuth poll reports retryable / retry_after.
- All user-facing copy rewritten for first-time users: never "the free
  service is off" (what is unavailable is using Hermes without signing in,
  and signing in is free), no jargon, spoken waits.

Desktop
- A setup-failure notice above the provider picker: one sentence per code,
  a retry when the backend says one can work, the sign-in pointer only when
  the account service answered at all. The overlay re-checks readiness on
  setup.ready so a background success dismisses it.
- Sign-in dialog gains busy / unreachable / unavailable screens.

Rehearsal
- scripts/free_tier_fault_server.py stands in for both services with the
  real wire contract and a CORS-open scenario switch; HERMES_EXTRA_WELCOME_HOSTS
  (dev-only, env-only) lets the route rules treat it as the welcome host.
  Walkthrough in website/docs/developer-guide/free-tier-fault-rehearsal.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-15 20:44:42 +05:30
teknium1 79007efc48 fix(agent): a no-fallback verdict wins over the local-ValueError fallback allowance
`MoAPresetNotFoundError` subclasses ValueError, so `is_local_validation_error`
re-opened the fallback the classifier had just refused (#55933). Only an
UNCLASSIFIED (reason=unknown) local error keeps the historical fallback.
Test exercises the real exception through settlement, not the classifier bool.
2026-09-12 08:27:11 -07:00
teknium1 293cb54f28 fix(agent): keep MoA verdicts fallback-free; nest the gated fallback under one if
Two CI regressions from the previous commit, both mine:

- `_moa_special_cases` was switched to `_ABORT_FALLBACK`, which flips
  `should_fallback` to True for the MoA adapter-shape and missing-preset
  verdicts. #55933 made those deliberately NOT fall back (a fallback would
  silently replace the MoA route with a single model); restore
  `retryable=False` only. The gate in `settle_unrecovered_error` now honours
  that for real: on main these verdicts never reached the fallback branch
  because the flag was never consulted.
- `tests/agent/test_prompt_cache_ttl_propagation.py` pins every
  `_try_activate_fallback` reference to a direct `if agent._try_activate_fallback():`
  site (#84733 restart discipline); `fallback_allowed and agent._try_activate_fallback()`
  broke that shape. Nest the two calls under one `if should_fallback or local_validation:`
  block instead.
2026-09-12 08:27:11 -07:00
teknium1 dfd4aa4a94 fix(agent): malformed tool-call-argument 400s no longer walk the fallback chain
When a proxy (Ollama, OpenRouter) rejects the MODEL's own unparseable
tool-call JSON with `400 invalid tool call arguments`, the classifier returned
the generic format_error verdict (`should_fallback=True`) and the non-retryable
client-error path cascaded through every fallback provider: 4-5 sequential
calls, 20-60s per occurrence, ending on a model that produced the same broken
JSON (#12770).

- error_classifier: explicit `_MALFORMED_TOOL_ARGS_PATTERNS` checked before the
  request-validation and overflow heuristics, returning format_error with
  `retryable=False, should_fallback=False`.
- turn_api_error: the client-error settlement honours `should_fallback`; the
  verdicts that legitimately reach that branch (policy block, TLS chain, MoA
  shape/preset errors) now state `should_fallback=True` explicitly, so the gate
  changes behaviour only for the new verdict. Local validation errors keep
  their historical fallback.

Fixes #12770. Pattern list and gating approach from #16022 by @cuyua9 (stale
base); tests trimmed to two invariants.

Co-authored-by: cuyua9 <2114364329@qq.com>
2026-09-12 08:27:11 -07:00
teknium1 6c89cb032e refactor(agent): move the entitlement rejection marker into agent/fallback_cooldown
The two facades post-#102117 (chat_completion_helpers, agent_runtime_helpers) must not grow
behaviour; the marker/predicate belong with the sibling that already owns primary-cooldown
state shared by the fallback walk and restore_primary_runtime. Also drops the two
try/except-return-False wrappers around pool.entries() and normalize_model_for_provider
(neither raises for a live pool / the never-raising normalizer).

Tests trimmed to the two invariants (#106475): the marker fires only on the single-credential
Codex entitlement 400 and the walk skips the rejected slug in either form; restore is gated on
a rejected primary and still restores an unrelated one.
2026-09-09 11:29:56 -07:00
liuhao1024 808c5b30aa fix(agent): fail closed when Codex account-model entitlement 400s exhaust the chain
A Codex ChatGPT-account 400 ('The X model is not supported when using Codex
with a ChatGPT account.') names the model, so with a single credential the
slug is dead for that account. The fallback walk still re-selected it and
restore_primary_runtime switched back to the primary at the start of every
turn, announcing an unverified 'Primary model restored' — the two warnings
alternated forever with zero delivered answers (#106475).

Record the rejected (provider, model) pair on the non-retryable client-error
path (only when no multi-credential pool exists — rotation covers that case,
#71970), skip rejected entries during the fallback walk, and gate
restore_primary_runtime on the primary's slug so the session fails closed
with the terminal entitlement error instead of oscillating. Fixes #106475.

(cherry picked from commit 471435b10288f15387b2549a8b02551d82c0f670)
2026-09-09 11:29:56 -07:00
Teknium 2f4534eaaa refactor(agent/turn): _NONRETRYABLE_LABELS table shared by terminal status + fallback announce; docstring trims 2026-09-02 19:39:27 -07:00
Teknium 82fc85a8d6 refactor(agent/turn_api_error): keep direct _verdict("break") at fallback sites (#84733 guard) 2026-09-02 19:23:48 -07:00
Teknium b925acb5a9 refactor(agent/turn_recovery): abort_turn_on_interrupt shared by backoff sleep and handle_api_error 2026-09-02 18:55:11 -07:00
Teknium e50afc20bb refactor(agent/turn_api_error): _is_local_validation_error predicate, _RETRYABLE_CLIENT_REASONS table, _fallback_break helper, verdict passthrough; trim turn_loop_errors/turn_retry_state 2026-09-02 18:42:15 -07:00
Teknium c94ced6225 refactor(agent/turn): AST-neutral bracket/signature packing across r3-08 slice 2026-09-02 18:01:27 -07:00
Teknium 7dc43c94d1 refactor(turn): sub-split handle_api_error / check_api_response / run_tool_round so no new turn_* function exceeds 300 LOC 2026-09-02 17:28:22 -07:00
Teknium 2769937936 refactor(turn): lift iteration entry/announce, Nous rate guard, API interrupt, retry-restart consumer and preflight-timeout result out of run_conversation 2026-09-02 16:37:14 -07:00
Teknium 9fda4e5bac refactor(turn): extract retry-loop API error handler, request build, provider call and response check into agent/turn_api_*.py + agent/turn_response_check.py 2026-09-02 16:07:51 -07:00