grok-4.x on the xAI /v1/responses surface sometimes ends a turn with only
reasoning items — no message output item, no tool calls — and those
reasoning items carry no encrypted_content. Two compounding problems:
1. The model occasionally emits its final answer INSIDE the reasoning
channel, delimited by grok's internal "<response>" tag. The answer
exists but is classified reasoning-only → finish_reason=incomplete.
2. An interim assistant message holding only plain-text reasoning replays
as nothing in _chat_messages_to_responses_input, so every continuation
request is byte-identical to the one that just failed. The model
deterministically repeats the reasoning-only response until the retry
budget is exhausted and the turn dies with "Codex response remained
incomplete after 3 continuation attempts".
Fixes:
- _normalize_codex_response (xai_responses only): salvage the
<response>-delimited tail from the reasoning text and promote it to
assistant content; the untagged prefix stays as thinking text.
- Codex-incomplete continuation path: when the interim message has
nothing the input converter will replay (no content, no encrypted
reasoning items, no message items), append a user-role nudge so the
retry actually differs and explicitly asks for the final answer /
pending tool call. Mirrors the existing _get_continuation_prompt
pattern used for length truncation.
Observed live with grok-4.20 on xai-oauth (2026-07-13); sibling of the
grok-composer web_search incomplete-loop fix in transports/codex.py.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The #64434 change makes unrecognized issuers trust
response.status='completed' for reasoning-only turns, so this sibling
test (which exercised the old default-path behavior) now pins the Codex
backend explicitly — the surface where reasoning-only still means
'still thinking'.
The aggregator is MoA's acting model, but the main loop's reasoning
gates key off the virtual moa://local identity and never fire — so with
no per-slot reasoning_effort the aggregator silently ran at the backend
default, ignoring the user's reasoning config entirely (#64187).
New _aggregator_reasoning_config(): slot value > full acting-model
resolution via the shared chokepoint (agent.reasoning_overrides for the
slot's model > global agent.reasoning_effort; YAML False stays
'disabled'). Applied to both aggregator call sites (acting turn +
one-shot /moa synthesis).
Reference advisors intentionally keep slot-or-default: inheriting a
global xhigh into every advisor fan-out would silently multiply cost.
Fixes#64187.
Consolidation follow-up on top of @liuwei666888's compressor fix (#52431)
and @Frowtek's ACP render guard (#62588) — completes the class fix across
every display-layer consumer of tool-call arguments:
- agent/context_compressor.py: wrap _summarize_tool_result in a
never-raises backstop (same pattern as get_cute_tool_message and the
ACP guard). The per-branch _str_arg coercions keep summaries
informative; the wrapper guarantees compression can never crash-loop
on a summary branch we didn't anticipate. Also reject non-dict parsed
args (a JSON list/scalar would crash every args.get call).
- agent/display.py: build_tool_preview's process branch sliced
session_id/data without coercion — crashed build_tool_preview and
build_tool_label on the live tool-progress callback (probed live:
TypeError 'int' object is not subscriptable). Coerce like the
sibling branches.
- tests: backstop fuzz matrix (16 tools x 6 hostile value shapes),
fallback-shape contracts, display process-preview regressions,
non-dict args guard.
Fixes#64025
The hermes-tools MCP server was fetching each tool's JSON schema
into params_schema but never passing it to FastMCP's add_tool(),
so all published tools had an empty **kwargs signature. MCP clients
couldn't see parameters and arguments were dropped at dispatch.
This fix:
- Adds _signature_from_schema() to convert JSON schemas to Python
function signatures with type annotations
- Attaches the generated signature/annotations to each handler closure
so FastMCP introspects the real parameter structure
- Filters out None values before dispatch to avoid forwarding unset
optional parameters
Impact: web_search, browser automation, vision, and other Hermes tools
are now properly callable from the codex_app_server runtime.
The just-merged auxiliary.<task>.reasoning_effort shorthand applied
ensemble-wide to MoA (one value for every advisor) — wrong granularity.
Per-slot preset config supersedes it:
moa:
presets:
deep_review:
reference_models:
- {provider: ..., model: ..., reasoning_effort: low}
- {provider: ..., model: ..., reasoning_effort: xhigh}
aggregator:
{provider: ..., model: ..., reasoning_effort: high}
- Remove reasoning_effort from the moa_reference/moa_aggregator
DEFAULT_CONFIG blocks; _get_task_extra_body now warns-and-ignores the
key on MoA tasks, pointing at the preset config
- Guard tests: MoA aux blocks must not regrow the key; task-level value
is rejected with the pointer warning
- Docs: configuration.md notes the MoA exception and links the MoA page
Every auxiliary task block (vision, web_extract, compression,
title_generation, curator, background_review, moa_reference, ...) now
accepts a reasoning_effort shorthand:
auxiliary:
compression:
reasoning_effort: low
vision:
reasoning_effort: none
_get_task_extra_body() folds it into extra_body.reasoning, which every
auxiliary wire already translates: chat.completions passes it through,
the Codex Responses adapter maps it to top-level reasoning/include, and
the Anthropic auxiliary adapter now forwards it into
build_anthropic_kwargs(reasoning_config=...) (previously hardcoded None).
An explicit extra_body.reasoning on the same task wins over the
shorthand. Invalid levels are ignored with a warning. Empty string
(the shipped default) is a no-op — zero behavior change.
Config: reasoning_effort added to all 16 auxiliary task blocks in
DEFAULT_CONFIG (no version bump — deep-merge handles new keys).
The platform hint in PLATFORM_HINTS['telegram'] always encouraged rich
Markdown constructs (tables, task lists, math, collapsible details) even
when rich_messages: false (the default). This caused the agent to produce
formatting that MarkdownV2 cannot render, especially broken on Telegram Web.
Split the hint into a base hint (MarkdownV2-compatible) and a
TELEGRAM_RICH_MESSAGES_HINT extension. The extension is conditionally
appended in system_prompt.py only when
platforms.telegram.extra.rich_messages is true.
Fixes#57122
Return actionable errors when HERMES_WRITE_SAFE_ROOT blocks a path instead of
labeling every denial as a protected credential file. Wire the helper through
write_file, patch, delete/move, and the Copilot ACP shim; sync docs examples.
- Nudge text now warns that repeated protocol violations will block the
task and require manual intervention, so the model understands the
consequence of ignoring the nudge.
- Kanban docs restructured to clearly separate the two defense layers:
agent-side prevention (nudge, from #64350) and dispatcher-side
recovery (bounded retry, from this PR).
- Two new integration tests verifying the nudge mentions blocking and
that the agent-side and dispatcher-side budgets are independent.
scan_skill_commands() had two collision bugs in the same loop body:
1. Core-command collision: a skill whose normalized slug matches a core
Hermes command name or alias (e.g. "skills", "learn", "bg") would
get an auto-generated /command that shadows the core command in the
gateway dispatch path (skill map is consulted before built-in
handlers). The skill command silently overrode the core command.
2. Inter-skill slug collision: the seen_names set deduped on the raw
frontmatter name, but the command map was keyed by the normalized
slug. Two distinct names collapsing to the same slug (e.g.
"git_helper" vs "git-helper") both passed the dedup, and the second
silently clobbered the first.
Fix: add two guards in scan_skill_commands() after slug normalization:
- resolve_command(cmd_name) check skips skills colliding with any core
CommandDef (name or alias), logging a warning. Uses the existing
resolve_command() API so aliases and case variants are covered
without a separate cache. The skill remains loadable via /skill.
- cmd_key in _skill_commands check dedups on the resolved slug,
first-wins (preserving local-before-external precedence), logging
a warning naming the shadowed skill.
Combines and supersedes #31204 (@cyrkstudios), #53450 (@Gridzilla),
#50304 (@petrichor-op), and #63305 (@Vissirexa).
Co-authored-by: cyrkstudios <cyrkstudios@users.noreply.github.com>
Co-authored-by: Gridzilla <Gridzilla@users.noreply.github.com>
Co-authored-by: petrichor-op <petrichor-op@users.noreply.github.com>
Co-authored-by: Vissirexa <Vissirexa@users.noreply.github.com>
Add a bounded turn-end stop guard for kanban workers. When a worker
tries to exit with finish_reason=stop without having called
kanban_complete or kanban_block, inject up to two synthetic nudges
so the conversation loop continues instead of exiting cleanly (which
the dispatcher records as protocol_violation).
Mirrors the existing verify-on-stop pattern: same ephemeral scaffolding
flag (_kanban_stop_synthetic), same role-alternation contract, same
_pending_verification_response fallback for budget exhaustion.
Disabled by default (gated on HERMES_KANBAN_TASK env var set by the
dispatcher); kill switch via HERMES_KANBAN_STOP_NUDGE=0.
Salvaged from #62262 by @mdc2122. The original branch was 272 commits
behind main with ~538 files of stale-base reversions; this salvage
applies only the 4 substantive files (agent/kanban_stop.py,
conversation_loop.py insertion, run_agent.py _EPHEMERAL_SCAFFOLDING_FLAGS,
tests/agent/test_kanban_stop.py).
OpenAI lets ChatGPT-plan Codex users bank rate-limit reset credits, but
until now they could only be redeemed from the Codex CLI/app or the
website. This wires the same backend API into Hermes:
- /usage on the openai-codex provider now shows "You have N resets
banked - use /usage reset to activate" (parsed from the
rate_limit_reset_credits field the /usage endpoint already returns).
- New /usage reset subcommand (CLI + gateway) redeems one banked
credit via POST .../rate-limit-reset-credits/consume with a UUID
idempotency key, mirroring codex-rs backend-client semantics
(PathStyle /wham vs /api/codex, ChatGPT-Account-Id header,
reset/nothing_to_reset/no_credit/already_redeemed outcomes).
- Guard: redemption is refused while no rate-limit window is fully
exhausted, since a banked reset restores the FULL 5h + weekly
allowance and spending it early wastes it. /usage reset --force
overrides. Zero banked credits and non-codex providers are refused
with clear messages; nothing_to_reset reports the credit was NOT
spent.
- i18n: new gateway.usage.unknown_subcommand / reset_wrong_provider
keys across all 16 locales; docs updated (cli.md, messaging index).
Tested with unit tests plus a real-socket E2E against a local fake
Codex backend exercising redeem/guard/force and the /usage hint.
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.
Preserve one durable staged input across terminal close and the worker's early turn flush, without duplicating resumed transcripts or creating a session with a null prompt. Fixes#63766.
Splits the single broad `except Exception` in the compression-lock
acquire path into two handlers: AttributeError/TypeError (version skew —
the lock method is missing, or predates the `ttl_seconds=` kwarg) still
fails OPEN as before, since that's known-safe to proceed without a lock.
Any other exception now fails CLOSED (skips compression this cycle)
instead of treating every failure as "no lock subsystem present" and
letting a second compressor run concurrently and fork the session.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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.
_custom_provider_model_matches() only compared the session model
against the entry's single 'model' field. A custom provider declaring
a multi-model catalog (providers.<name>.models mapping / models list)
whose default model differed from the session model silently failed to
match — dropping the entry's extra_body entirely. Real impact: an
OpenAI custom provider pinning service_tier=flex via extra_body ran
every request at STANDARD tier (~2.3x billing) with zero signal.
- Model matching now accepts the session model when it appears in the
entry's models catalog (dict keys or list), case-insensitive;
single-model 'model' field behavior unchanged; entries with neither
still match everything.
- Usage report ('hermes -z --usage-file') now carries service_tier
(the tier requested via request_overrides.extra_body) so batch
pipelines can audit the billed tier per run.
Validation: 8 new tests; live E2E via real 'hermes -p sweeper -z'
with httpx-level wire capture — service_tier=flex present in the
outgoing /v1/responses body and in the usage report.
Retain the provider-boundary core of #52799 while reusing the pool reload and handoff paths already landed in #53591 and #62417.
Co-authored-by: Flownium <157689911+itsflownium@users.noreply.github.com>
Third correction, and the load-bearing one. The previous commit put the
"did compaction clear the threshold?" verdict inside should_compress(). But
conversation_loop calls should_compress() TWICE per turn with two different
measures (turn_context.py / conversation_loop.py:1033 and :4789):
* pre-API : request_pressure_tokens -- a rough estimate that can dip BELOW
the threshold
* post-API: real prompt tokens -- which stay above it
So the rough reading reset the strike every turn and the loop never stopped.
Reproduced: 8 compactions in 8 turns under the real two-call pattern, even
with the previous fix applied. (My earlier repro only called should_compress()
once per turn, which is why it looked contained.)
Move the verdict to update_from_response(), the one place that sees the
provider's real prompt_tokens for the just-compacted conversation, guarded by
the existing awaiting_real_usage_after_compression flag so it fires exactly
once per compaction. Real-vs-real: it cannot be fooled by a rough sub-threshold
reading, and (from the previous commit's lesson) never subtracts an estimate
from a real count. should_compress() goes back to a plain threshold test plus
the pre-existing cooldown and anti-thrash guards.
New test test_rough_preflight_reading_does_not_reopen_the_loop drives the real
two-call-per-turn pattern and fails on the prior should_compress()-based commit.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Follow-up to the previous commit, whose futility check was unsound:
incompressible_floor = max(0, display_tokens - pre_estimate)
`display_tokens` is the provider's real prompt count; `pre_estimate` is
`estimate_messages_tokens_rough(messages)`. Subtracting an estimate from a real
count folds the tokenizer skew into "floor" and misreads it as incompressible
overhead. With a 1.6x skew on a 200K window (threshold 150K, true floor 30K):
rough_msgs=253,804 real_prompt=436,086
computed floor = 182,282 <-- mostly skew; exceeds the threshold
after compaction: 401 -> 77 msgs, real prompt = 106,361 (CLEARS 150,000)
verdict: ineffective_count = 1 <-- false positive
Two such passes would permanently disable compaction on a healthy session --
worse than the loop this PR set out to fix.
Move the check into should_compress(), where both sides of the comparison are
the caller's own token count:
* prompt under the threshold -> not thrashing; reset the counter
* a compaction just ran and we are STILL over -> one strike
Real-vs-real, so tokenizer skew can never be mistaken for a floor, and nothing
subtracts an estimate from a real count. compress() now only ever increments the
counter; the reset lives with the one measure the trigger uses.
Adds `test_no_false_positive_under_tokenizer_skew` (the case above) and
`test_counter_resets_once_the_prompt_fits_again` (one failed pass must not
disable compaction forever). Against upstream, 5 of the 7 cases fail; the 2 that
pass are the regression guards, which is the intended shape.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
`should_compress()` documents anti-thrashing protection ("if the last two
compressions each saved less than 10%, skip compression to avoid infinite
loops"). In practice `_ineffective_compression_count` reset on every pass,
so the guard was dead code and a mis-sized context window presented as a
hung CLI instead of a warning.
Two defects:
1. Mixed measurement bases. Effectiveness was
`(current_tokens - estimate(compressed)) / current_tokens`, where
`current_tokens` is the provider's FULL prompt (system prompt + tool
schemas + messages) but `estimate(compressed)` covers messages only.
Every compaction therefore reported ~96% savings and reset the counter.
Savings is now scored messages-vs-messages.
2. Message shrinkage is the wrong yardstick. `should_compress()` trips on
the full prompt, but compaction can only shrink messages -- the system
prompt and tool schemas are an incompressible floor. When that floor
alone meets the threshold, each pass shrinks messages by a healthy
margin, legitimately resets the counter, and still leaves the prompt
over the line; the next turn compacts again, forever. Observed in the
wild: 45+ consecutive compactions, one auxiliary-LLM call each, zero
progress. Effectiveness is now scored against the goal -- did the
projected prompt get under the threshold? -- and a futile pass warns
with the numbers that prove it.
Also record an ineffective pass on the "only N messages (need > M)" early
return, which previously returned the transcript unchanged without moving
any anti-thrash state -- the same class of bug the neighbouring
"no compressable window" branch was already fixed for.
Tests: 4 of the 5 new cases fail on main and pass here; the fifth pins
that effective compaction still resets the counter (121 -> 15 messages,
88.9% savings).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Preserve deletability, route identity, stored costs, aggregate reconciliation,
and zero-usage Codex route accounting on top of the salvaged per-model usage
work.
The `sessions` table records only the initial (model, billing_provider)
for a session, so when a user switches models mid-session (via `/model`
or programmatically) every token — including the switched model's — is
attributed to the first model. Insights/billing reports then hide the
cost of the new model entirely (e.g. a session that started on deepseek
and switched to opus shows $0 for opus).
Add a `session_model_usage` table keyed (session_id, model,
billing_provider) that accumulates each per-API-call delta under the
model active at the time of the call. `update_token_counts()` is the
single chokepoint every per-call delta flows through (CLI, gateway,
cron, delegated, codex), so recording there captures accurate
attribution on every platform. Only the incremental path records — the
gateway's `absolute=True` summary overwrite is skipped to avoid
double-counting cumulative totals that can't be split per model. When a
call omits the model, it falls back to the session's recorded model,
matching the existing COALESCE-from-session summary behaviour.
Insights `_compute_model_breakdown` now aggregates tokens and cost from
`session_model_usage`, so a switched session splits correctly across
models, with a defensive fallback to the per-session aggregate for any
session lacking usage rows. A v17 migration backfills one usage row per
existing token-bearing session from its aggregate totals (idempotent via
INSERT OR IGNORE), validated lossless against a 1.3 GB production DB.
Tests: per-model recording, mid-session split, model fallback, absolute
no-double-count, v17 backfill, and an insights-level switch breakdown.
Fixes#51607.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
_CodexCompletionsAdapter (agent/auxiliary_client.py) is a second,
independent producer of Codex Responses input — used by auxiliary
calls (context compression, flush_memories, MoA aggregation,
session_search) that route through CodexAuxiliaryClient instead of
the main agent's ResponsesApiTransport.build_kwargs. It calls
_chat_messages_to_responses_input() directly without is_github_responses,
so the previous commit's fix didn't cover it: an auxiliary call made
against a Copilot-backed session could still replay a connection-scoped
codex_message_items id and hit the same HTTP 401.
Detect the Copilot host from the adapter's own client.base_url (same
check the adapter already does further down for prompt_cache_key
opt-out) and pass is_github_responses through, closing the gap.
Still #32716.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
