- _submit_background and _prefetch_provider: replace unreadable
(lambda inner: (lambda: ctx.run(inner)))(fn) with functools.partial(ctx.run, fn)
- from_env(): set config_path=resolve_config_path() so bound_config_path()
doesn't re-resolve from ContextVar on daemon threads (the exact bug
the PR fixes for from_global_config)
Review follow-ups for salvaged PR #83525.
MemoryManager dispatches provider sync_turn/queue_prefetch work on a
single-worker executor and hot prefetch on a plain thread. Neither
carried the caller's contextvars, so in multi-profile processes the
provider work ran outside the profile's ContextVar-scoped HERMES_HOME
override — any ambient resolution inside a provider landed on the
default profile.
Wrap the submitted callable and the prefetch thread target with
contextvars.copy_context().run, mirroring the gateway's
_run_in_executor_with_context pattern. Provider-agnostic: benefits
every external memory provider, not just Honcho.
save_context_length() and _invalidate_cached_context_length() did an
unguarded read-modify-write into $HERMES_HOME/context_length_cache.yaml.
The plain `open(path, "w")` truncates the file before the dump runs. If
the process is killed mid-dump, the file is left empty or partial. The
next _load_context_cache() swallows the YAML error and returns {} —
silently wiping every persisted context length. A concurrent process
reading between truncate and dump-complete also sees a torn file.
After the cache is lost, every model re-probes the network, and when a
probe fails it falls back to the generic 256K default — so a user on a
1M-window model ends up with a wrong, short context window.
Hermes routinely runs several processes against one shared $HERMES_HOME
(a cron agent plus an interactive session, multiple gateway sessions),
so this is hit in normal use.
Switch both writers to the existing utils.atomic_yaml_write helper
(temp file + fsync + os.replace, symlink- and mode-preserving). The real
file is only ever swapped from a fully written temp file, so an
interrupted write leaves the previous cache intact and readers never see
a partial file. Matches the atomic-write pattern already used for
auth.json, config.yaml, and other persisted state.
Makes the persistent model context-length cache write crash-safe. The
old non-atomic write could truncate or wipe the entire cache on an
interrupted or concurrent write, which then forces models onto the wrong
fallback context window. The fix routes both cache writers through the
repo's atomic temp-file + os.replace helper.
N/A
- [x] 🐛 Bug fix (non-breaking change that fixes an issue)
- [ ] ✨ New feature (non-breaking change that adds functionality)
- [ ] 🔒 Security fix
- [ ] 📝 Documentation update
- [ ] ✅ Tests (adding or improving test coverage)
- [ ] ♻️ Refactor (no behavior change)
- [ ] 🎯 New skill (bundled or hub)
- `agent/model_metadata.py`: `save_context_length()` and
`_invalidate_cached_context_length()` now write via
`utils.atomic_yaml_write` instead of a truncating `open(path, "w")`.
Added the `atomic_yaml_write` import.
- `tests/agent/test_model_metadata.py`: added
`test_write_failure_leaves_existing_cache_intact` — simulates a crash
during the atomic swap and asserts the existing cache survives
byte-for-byte with no stray temp file.
1. `pytest tests/agent/test_model_metadata.py -q` — 98 pass, including
the new crash-safety test.
2. The new test seeds a valid cache, forces the swap step to raise, and
confirms the file is not truncated and no `.cache_*.tmp` is left.
3. `ruff check agent/model_metadata.py` passes.
- [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
- [x] I've run the affected tests (`pytest tests/agent/test_model_metadata.py -q`) and they pass
- [x] I've added tests for my changes
- [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) — the helper uses os.replace, which is atomic on both
- [x] I've updated tool descriptions/schemas if I changed tool behavior — or N/A
Reapply the non-positive context-length guards onto the post-history-replacement
mainline without carrying any stale branch history. save_context_length() now
refuses to persist length <= 0 (keeping upstream's normalized _context_cache_key),
and get_model_context_length() drops non-positive cache hits at the head of the
invalidation chain (Codex/Kimi/MiniMax/Grok branches become elif) so a poisoned
entry re-resolves instead of short-circuiting to 0.
Refresh of PR #25812; original head d62ed5eb92f057d8c707ba937b44f168f2df0677.
An empty/blank model id reaching get_model_context_length() can't be
meaningfully resolved — and it's worse than a miss: the endpoint
metadata fuzzy matcher ('model in key or key in model') is vacuously
true for "", so it matches an ARBITRARY catalog entry from the live
/v1/models response and returns whatever context length that entry
happens to have, persisting it under a junk '@<base_url>' cache key.
This started failing CI on main when the Nous portal catalog changed:
tests/run_agent/test_primary_runtime_restore.py constructs agents with
model='' against the live portal URL, the arbitrary match now lands on
a 32K entry, and init_agent raises the 64K-floor ValueError
(test_allowed_for_nous_anthropic_messages, red on every PR's slice).
Guard early: a blank model id falls back to DEFAULT_FALLBACK_CONTEXT
immediately, before any cache write or network probe.
Salvaged from #65515 by @whirmill (rebased onto current main; the
guard now sits after the malformed-base_url normalization added since,
and carries an explanatory comment for the fuzzy-match footgun).
Fixes the red slice on #85444, #85452 and every other open PR.
Co-authored-by: whirmill <5079591+whirmill@users.noreply.github.com>
1. Use open_credentialed_url() instead of bare urlopen() in
templates.py apply_template() and probe_existing_customization().
Both send Authorization: Bearer headers; bare urlopen forwards
credentials on cross-origin redirects. The codebase has
open_credentialed_url() in hermes_cli/urllib_security.py that
strips credentials on cross-origin redirects — used by 4 other
modules.
2. Guard unavailable_reason() with the dedup set check before
calling it. The gateway builds a fresh AIAgent per message, so
without this guard unavailable_reason() (which calls _load_config()
→ stat + file read + JSON parse, and _check_local_runtime() →
importlib probes) runs on every gateway turn for an unavailable
provider, even though the warning is deduped after the first.
3. Move INDICATOR_GLYPH from Hindsight's eye emoji to a generic
brain (🧠) in core (agent/memory_provider.py). Hindsight overrides
with its own _HINDSIGHT_GLYPH (👁️) in recall_status() and
_emit_saving_indicator(). Other memory providers no longer inherit
Hindsight's brand mark as the default glyph.
Bundles previously-separate Hindsight/memory PRs into a single review surface:
- opt-in synchronous recall (recall_sync) — recall the injected memory in-turn instead of next-turn prefetch (#5820)
- actionable error when local_embedded runtime is missing — tells the user which package to install (#7718)
- default retain_source to 'hermes' so every stored memory self-identifies its provenance
- offer a starter memory template during hermes memory setup, plus warn before overwriting an already-configured bank
- warn when a configured memory provider reports unavailable (#2765)
- deterministic 'recalled N memories' recall indicator — Hermes itself emits a status line when auto-recall injects memory
- 'saving to memory' retain indicator — emitted the moment a turn is dispatched to the writer
Authored by @benfrank241 (ben.bartholomew@vectorize.io).
Salvaged from PR #74379.
notify_session_compacted closed the old session scope immediately on a
legacy rotating compaction. A compaction can complete while a turn is
still live on the old session; closing then pops the session scope under
the live turn scope, violating the stack's LIFO order — the exact
invariant the rest of the segmentation feature protects.
Now: when the old session has an active turn, set close_pending instead;
that turn's end_turn consumes the flag after its own turn scope pops and
it unregisters from the active-turn table. Sabotage-verified: the new
test fails without the fix.
Continuous gateway sessions keep the Relay session scope open for days;
close-driven export means the session root span and out-of-turn marks
never export until /new or idle-end, and a crash loses the open segment
entirely.
Opt-in segmentation (both defaults OFF => scope lifecycle byte-identical
to today):
gateway.telemetry.session_segments.on_compaction: false
gateway.telemetry.session_segments.max_turns: 0
Rotation closes the current session scope and pushes the next segment
(same session_id attribute, plus hermes.session.segment=N and
segment_reason=compaction|max_turns) ONLY at a turn boundary in
begin_turn — never mid-turn (scope stack is LIFO). Compaction completion
just flags rotate_pending (observer semantics, nothing on the compaction
critical path); legacy rotating compaction closes the orphaned old
session scope so its segment exports. Both native calls ride the
existing bounded scope-op executor: a wedged rotation costs one segment
span, never the agent. Segment bookkeeping advances even on native
failure so a degraded rotation cannot retry every turn.
The diff-apply salvage introduced stale-base revert hunks — the PR was 1246
commits behind main, and its diff for conversation_loop.py and moa_loop.py
silently dropped symbols added after the PR's base (e.g.
_CODEX_ACK_CONTINUATION_NUDGE, _INTERRUPT_SCAFFOLD_MARKER, cache_ttl plumbing,
finalize_turn import, _restore_user_after_reference_handoff).
Restored both files to origin/main and re-applied only the PR's additive
changes: _moa_reference_metrics_for_hook, _system_prompt_for_hooks, the
system_prompt= and moa_references= hook kwargs, _last_reference_metrics
attribute and accessors, and the slot_metrics population in the fan-out path.
Fixes CI ImportError: cannot import name '_CODEX_ACK_CONTINUATION_NUDGE' from
'agent.conversation_loop'.
Follow-up fixes from /hermes-pr-review + /simplify-code on PR #83437:
1. Replace _redact_secrets with agent.redact.redact_sensitive_text(force=True)
— the plugin's 11-pattern list was a strict subset of the 50+ patterns in
agent/redact.py. Secrets like Stripe keys, Google API keys, GitLab tokens,
HuggingFace tokens, DB connection strings, and Telegram bot tokens would
all leak through the plugin's list but are caught by the existing redactor.
Added pk-lf- (Langfuse public key) to _PREFIX_PATTERNS in agent/redact.py.
2. Remove dead 'not isinstance(client, object)' check in on_session_finalize —
always False for any Python value.
3. Fix MoAClient.last_reference_metrics() to call the public
self.chat.completions.last_reference_metrics() instead of reaching into
the private _last_reference_metrics attribute via getattr.
4. Deduplicate _coerce_request_messages call in on_pre_llm_request — pass
pre_coerced=input_messages to _messages_for_langfuse_input to avoid
double-coercion + double _capture_content serialization per API request.
5. Add HERMES_LANGFUSE_CAPTURE to OPTIONAL_ENV_VARS in hermes_cli/config.py
for consistency with the other HERMES_LANGFUSE_* env vars.
6. Fix test_sanitized_mode_redacts_secrets test data — the old samples
('sk-abc...1234', 'sk-ant...1234', 'Authorization: Bearer ***') were too
short to match the regex thresholds and never actually tested redaction.
Updated to realistic-length secrets and changed assertions to check that
the output differs from input (redact_sensitive_text masks rather than
inserting the literal string 'REDACTED').
Salvaged from PR #83437 by @erosika, with adopted fixes from @bgodlin (#81054),
@aldoeliacim (#82332), @nftpoetrist (#42326), @rodboev (#39653), @FnExpress
(#64292, supersedes #32175 by @db-aeon), @Per0-1 (#61166), @NaMinhyeok (#64797),
and @liuhao1024 (#43130).
Widens the bundled Langfuse plugin from 6 to 11 hooks and fixes two
attribution bugs. Also adopts shutdown/atexit lifecycle fixes and composes
8 prior community PRs with interaction-fix follow-ups.
Model attribution: on_pre_llm_request and on_post_llm_call now prefer the
wire value (request body model, response model) over the agent attribute,
which goes stale after /model switch or provider fallback.
Cost total: both cost paths now send a summed total alongside the per-type
breakdown, since Langfuse does not derive calculatedTotalCost from
cost_details keys. Subscription-included routes send no cost keys at all.
New coverage: api_request_error closes failed generations with ERROR level;
on_session_finalize/on_session_end close dangling traces for tool-only and
interrupted turns; subagent_start/subagent_stop trace delegated children as
spans; MoA advisor fan-out emits one generation per advisor priced at the
advisor's own model.
Capture modes: HERMES_LANGFUSE_CAPTURE=metadata|sanitized|full (default
sanitized). Sanitized mode redacts secret patterns before truncation.
Adopted lifecycle fixes: shutdown client at session finalize when
reason=shutdown (not on session rotation); atexit finalizer ends open root
spans for short-lived processes; root context manager exited to prevent
interpreter-teardown TypeError; TOCTOU on _get_langfuse() fixed with lock;
reasoning_content surfaced in traces; system prompt included in generation
input for Anthropic/Codex/Bedrock; SDK v3 update_trace replaces set_trace_io.
Closes#29482, #43129, #72661.
Supersedes #81054, #82332, #42326, #39653, #64292, #32175, #61166, #64797, #43130.
Partially addresses #67544 (capture modes + secret redaction; user_id remains open).
The custom + explicit_base_url branch of resolve_provider_client()
unconditionally rewrote a trailing /anthropic to /v1 via
_to_openai_base_url(), even when api_mode was anthropic_messages. The
Anthropic wrapper then never saw the real /anthropic path, so auxiliary
tasks (title generation, compression, vision, web_extract,
session_search) hit .../v1/chat/completions on a Messages-only endpoint
and failed.
Guard the wrap base on api_mode: for anthropic_messages, pass the raw
/anthropic base to _wrap_if_needed (which builds the Anthropic wrapper),
while the plain OpenAI client keeps the /v1-rewritten base so the
OpenAI-wire fallback (used when the anthropic SDK is unavailable) never
lands on /anthropic/chat/completions.
Refs #16254
Replaces the per-model _model_name_suggests_grok_4_3/_grok_4_6/
_minimax_m3 stale-cache predicates with one generic
_stale_pre_catalog_cache_entry() guard driven by
_PRE_CATALOG_STALE_KEYS. A cached context length is dropped when the
model resolves (longest-key-first, same as step 8) to a listed catalog
key and the cached value is at or below what the old resolution path
could have produced (largest shorter matching catch-all, or the 256K
fallback).
Also covers qwen3.6-plus, grok-4-fast, and grok-4.20 (the models
PR #37684 requested guards for), absorbing that PR.
_model_name_suggests_minimax_m3 is kept for its two non-cache callers
(models.dev underreport guard, cache-control gating in
agent_runtime_helpers).
docs.x.ai (2026-08-12): grok-4.6 is the flagship, 500K context.
Live GET /v1/models lists grok-4.6 at context_length 500000
(no grok-4.6-latest alias).
#84661 landed the catalog. Main already lists native grok-4.6
on the xAI picker. This is only the leftover cache guard
(same pattern as grok-4.3): pre-catalog builds persisted the
grok-4 catch-all (256K).
'' is a substring of every catalog key, so _resolve_endpoint_context_length
with an empty model name "matched" whatever the endpoint listed first —
on the Nous portal that is currently a 32K embedding model, which poisoned
the resolved context length and made AIAgent init fail the 64K minimum.
This is what turned tests/run_agent/test_primary_runtime_restore.py::
TestTryRecoverPrimaryTransport::test_allowed_for_nous_anthropic_messages
red on every PR (CI slice 7/12) after the portal catalog reordered.
Single-model endpoints still resolve with an empty name (unambiguous);
non-empty names keep the substring fuzzy match.
Applies the batch-disposition SALVAGE conditions from #64231: the hook id
moves to the taxonomy transform-family name, and run-all-then-pick-first
dispatch now logs a runtime warning when a valid-but-losing classification
is skipped (the #64714 skipped-transform rule). Chaining semantics are
stated explicitly at the VALID_HOOKS entry, the dispatch helper docstring,
and the hooks.md catalog row and detail section.
Rebased onto current main, where the OpenRouter tool-use 404 is now
handled natively (the bundled demo's exact reason to exist), so the demo
plugin is removed per the standalone-repo policy and every test now uses
a synthetic unclaimed error (fake provider, neutral message, no status
code) that no present or future built-in rule can claim.
classify_api_error is now explicitly Python-plugin-only: VALID_HOOKS
doubles as the shell-hook allow-list, but the shell response parser has
no channel for the classification directive, so shell registrations are
refused at config parse with a warning instead of being silently
ignored (new SHELL_UNSUPPORTED_HOOKS set + regression test).
The hook is documented in the hooks reference as the third
behavior-changing hook, with the full kwargs contract, return shape,
and the Python-only note.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PnMCvi2vXqfs996AjVeF2F
Adds a plugin seam at the top of agent/error_classifier.classify_api_error()
(step 0, before the built-in pipeline) so model-provider plugins can classify
their provider's error quirks without patching core:
- New "classify_api_error" entry in VALID_HOOKS. Callbacks receive the parsed
error context (provider, model, status_code, error_type, error_code,
error_message, error_body, error, approx_tokens, context_length,
num_messages), self-scope on `provider`, and return None to pass or a dict
{"reason": "<FailoverReason name>", ...optional recovery-hint overrides}.
- get_plugin_error_classification() helper mirrors
get_pre_tool_call_block_message(): first valid result wins, invalid dicts
and unknown reasons are skipped, callback exceptions are isolated — a
broken plugin can never break classification. Zero behavior change when no
plugin claims the error (all 179 existing classifier tests pass untouched).
- Bundled reference plugin `openrouter-tool-use-404` (opt-in, like all
bundled standalone plugins) re-implements PR #58451: OpenRouter's
"No endpoints found that support tool use" 404 carries no
_MODEL_NOT_FOUND_PATTERNS signal, so it classifies as unknown/retryable
and the retry loop burns 3-5 attempts on a deterministic rejection.
The plugin classifies it as model_not_found (retryable=False,
should_fallback=True) so the fast-fallback path fires immediately —
demonstrating a waiting core PR converted to a publishable plugin.
Motivation: ~10 open PRs are single-provider error-classification patches
(#58451, #58355, #58502, #58474, #58366, ...). This hook turns that whole
class of contribution into plugin territory.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FWMcB7RPSYUpsXDfBgwjzM
delegate_task gains a control plane: action='list' / 'steer' / 'stop'
let the parent agent see, redirect, and early-stop its own running
subagents mid-flight — the model-facing counterpart of the TUI's
delegation.pause / subagent.interrupt / subagent.steer RPCs.
- action='list': live children of this conversation's spawn tree
(ids, goal, status, running_seconds, accepting_steer, live
transcript path). Ownership is enforced via a _delegate_parent_ref
weakref chain stamped at child build time, so a conversation can
only control its own descendants, never a sibling tree.
- action='steer': queues text into a running child via the existing
steer_subagent() registry path (delivered at the child's next tool
boundary; missed steers surface as missed_steer in the completion).
- action='stop': interrupt_subagent() — child stops at its next
iteration boundary, partial result still re-enters as a completion.
- Spawn dispatch response now includes subagent_ids + control hint.
- Control actions run synchronously (never backgrounded) and bypass
the spawn pause gate and depth limit; they also never consume the
per-turn subagent spawn cap, and remain usable once the cap is hit
(that is when stop matters most).
- Small-model robustness (found live with gpt-5.4-mini on Nous
Portal): tasks=[] alongside goal no longer trips the "Batch mode
requires at least 2 tasks" gate — treated as single-goal.
- CLI display: control calls render as "steer sa-…" / "list" instead
of an empty goal.
Live-tested E2E on Nous Portal (fable-5 + gpt-5.4-mini): full
spawn→list→steer→stop cycle, plus a steer-efficacy run where the
child acked the steer mid-essay and switched topics before finishing.
A type="compaction" item is the server-side stand-in for history that has
already been pruned, and it rides the same codex_reasoning_items sidecar as
per-turn reasoning. e00965a7e taught compaction pruning to filter that
sidecar instead of popping it so checkpoints survive on every retained
message.
The thinking-only sanitizer reaches the same sidecar from the other
direction and asks a coarser question: does any item have type ==
"reasoning"? A commentary turn carrying both a reasoning item and a
checkpoint answers yes, so the whole message is dropped from the wire copy
and the only copy of the checkpoint goes with it. The request then carries
neither the compacted history nor the checkpoint standing in for it.
Extract has_compaction_checkpoint() into agent/native_compaction.py — the
module that owns the concept, and where merge_interim_reasoning_items()
already spelled the same predicate inline — and consult it before the
thinking-only verdict. A reasoning-only carrier is still dropped.
Two reliability gaps from #82777:
1. Rejection matcher required only a field-name mention, so a transient
5xx/timeout whose body echoed the request (which contains
context_management) permanently downgraded native compaction for the
session. Now requires rejection language (unknown/unsupported/invalid/...)
alongside the field name, and when a parsed HTTP status is available,
400 specifically — non-400 statuses never match. Message-only transports
(no status attribute) keep working unchanged.
2. compression.codex_responses_native was coerced with bool(), so the
strings "false"/"off" enabled the feature. Now uses the shared
utils.is_truthy_value helper.
Conversation-loop call site passes api_error.status_code through.
Sabotage-verified: reverting the matcher to field-name-only fails the new
echo and non-400 tests.
Simplify-pass follow-ups on the salvage stack (all guard tests re-run,
mutation-checked):
1. conversation_loop.py: moved `_preflight_compression_blocked = False`
from 9 per-site copies into the restart_with_rebuilt_messages handler
(its single consumer). Besides removing the 9 duplicated blocks, this
fixes a 10th pre-existing retry-loop site (content-filter stall
failover, #32421) that set the flag and broke WITHOUT clearing the
preflight block — a content-filter failover previously restarted with
preflight compression still blocked against the fallback's smaller
window, the same #84733 bug class. The outer-loop empty-response site
keeps its own clear (it never passes through the handler). New AST
guard test_restart_handler_clears_preflight_block pins the hoisted
clear (mutation-checked).
2. agent_runtime_helpers.py: extracted _raw_cache_ttl_from_config() —
prompt_caching_disabled_from_config and configured_cache_ttl were
verbatim copies of the same config read. Added VALID_CACHE_TTLS.
3. prompt_caching.py: added is_qwen_model() next to
ALIBABA_FAMILY_PROVIDERS; effective_cache_ttl and
anthropic_prompt_cache_policy now share both the family set and the
qwen predicate — neither can desync.
4. Guard-test hardening: assert every _try_activate_fallback reference
is a direct `if agent._try_activate_fallback(...):` site, so a future
`activated = ...` form can't silently escape the restart-discipline
guard.
Follow-ups on the salvaged #84782 (webtecnica):
1. conversation_loop.py: the empty-response fallback site sits directly
in the OUTER iteration loop, not the retry loop. The salvaged commit's
`break` there exited the conversation loop and ended the turn without
ever calling the just-activated fallback (caught by CI:
test_empty_response_triggers_fallback_provider). Restored `continue`
(which already re-runs the pre-API preflight at the top of the next
outer iteration) while keeping the `_preflight_compression_blocked`
reset. The other 9 sites are inside the retry loop, where `break` to
the restart_with_rebuilt_messages handler is correct.
2. test_prompt_cache_ttl_propagation.py: made the AST guard loop-aware —
retry-loop sites must break, outer-loop sites must continue (the old
assertion pinned the bug in (1)). Mutation-checked both directions.
3. test_failover_identity.py: added `model` to the SimpleNamespace agent
fixture — _redecorate_prompt_cache_for_provider now reads agent.model
for the per-destination TTL clamp (2 CI failures).
4. prompt_caching.py / agent_runtime_helpers.py: single source of truth
for the alibaba-family provider set — ALIBABA_FAMILY_PROVIDERS lives
in prompt_caching and anthropic_prompt_cache_policy imports it, so the
cache-policy opt-in and the TTL clamp can never desync.
5. auxiliary_client.py: threaded the configured tier into
_replan_synchronous_cache_sections via new configured_cache_ttl()
(no live agent on that path) — the aux half of #84733's report also
stopped regressing 1h to 5m. Guarded by
TestAuxFallbackReplanThreadsTtl (mutation-checked).
6. Dropped the redundant `or "5m"` at the two threaded call sites —
effective_cache_ttl already resolves None to "5m", and the `or`
masked the cache-disabled (None) semantics.
OpenCode identifies clients by request headers, the same way OpenRouter
does. Our opencode-zen and opencode-go profiles never set any, so every
request went out with the OpenAI SDK default "OpenAI/Python x.y.z"
User-Agent and OpenCode had no way to tell the traffic was Hermes Agent.
Two changes:
- Add HTTP-Referer, X-Title, and a HermesAgent User-Agent to both
OpenCode profiles through profile.default_headers, the same path
Fireworks uses. This covers chat_completions, codex_responses,
auxiliary clients, model switches, and the models catalog fetch.
- Merge the same headers in build_anthropic_client for opencode.ai
base URLs. The Anthropic Messages route (Claude on Zen, MiniMax and
Qwen on Go) builds its client there and never sees profile headers.
Verified against the live Go relay with a real key. Both wire formats
return HTTP 200 and the requests now carry X-Title "Hermes Agent",
HTTP-Referer, and User-Agent HermesAgent/0.20.0.
Live verification (gpt-5.6 @ api.openai.com) proved the Responses server
renders NOTHING placed before a replayed compaction checkpoint: a fact
stated in a pre-checkpoint input item is invisible to the model, while the
same item after the checkpoint recalls perfectly. Hermes was replaying the
full pre-checkpoint transcript anyway — dead upload weight, and worse, every
plaintext user ask from before the boundary silently vanished from the
model's view, surviving only inside the opaque server summary. That is the
goal-drift failure mode reported against native compaction sessions.
Codex CLI never hits this because it rebuilds history client-side after
compaction, retaining user messages verbatim under a token budget. This
change is the wire-level equivalent: when a replayed checkpoint is present,
_chat_messages_to_responses_input restructures the input as
[newest checkpoint run] + [retained pre-checkpoint user messages,
newest-first within a 64K-token budget] + [post-checkpoint tail]
Histories without a checkpoint are returned unchanged, so non-native
sessions see a byte-identical wire.
New desktop_ui tool: the agent proposes an MCP server (install/enable/
authorize + a one-line reason) and blocks on mcp.setup.request until the
renderer's consent card answers mcp.setup.respond with the outcome
(installed/enabled/authorized/declined/unanswered/error). Same lifecycle
as clarify: 10-min timeout, allow_expired late answers, tool lifecycle
events forced on so the card mounts even with tool progress off. Desktop
prompt hint steers the model to the tool instead of hand-editing config;
every other surface keeps the schema out and is pointed at hermes mcp
install.
Adds a 'council' synthesis style to MoA (per preset via synthesis_style,
one-shot via the new /council command on CLI + gateway). Reference models
answer independently; the aggregator chairs the deliberation and produces
a user-facing report of consensus, per-model disagreements (with the
differing assumptions behind them), unique contributions, and a
recommendation with an explicit confidence level.
Inspired by Perplexity's Model Council rollout to Perplexity Computer
(changelog 08/04/26): pick a board of 2-8 models, run them independently,
synthesize where they agree/disagree and what each uniquely surfaces.
Port from openai/codex#37527: Terminate timed-out hook process trees.
A shell hook that forked helpers (scanners, watchers, "cmd &") and then hit
its timeout left those descendants running forever — subprocess.run() only
kills the direct child. Worse, descendants holding the inherited pipe write
ends could stall run()'s post-kill communicate() drain.
- agent/shell_hooks.py _spawn(): spawn hooks in their own process group on
POSIX (process_group=0, Python >=3.11); on timeout/error, reap the whole
tree via the shared kill_process_tree() helper, then drain bounded (1s).
Hooks that complete in time keep their descendants, so intentionally
detached helpers survive successful runs (mirrors codex semantics).
- hermes_cli/_subprocess_compat.py: rename _kill_git_process_tree ->
kill_process_tree (it was never git-specific; taskkill /T /F on Windows,
ownership-gated os.killpg on POSIX). Backward-compat alias retained.
- tests/agent/test_shell_hooks_tree_kill.py: real-subprocess regression
tests (descendant killed on timeout, preserved on success, own-group
spawn, fast-path contract, fail-open). Sabotage-verified: reverting the
process_group spawn fails exactly the two new behavior tests.
Gap proven live on main first: a forking hook timed out at 2s and its
descendant survived; same probe against this branch shows it reaped.
Salvaged from PR #64188 (@Bartok9), re-reviewed against the #64229
ownership ledger (landed in #84923).
Delivery parity (survived):
- Module-level invoke_hook/invoke_middleware/has_hook/has_middleware
lazily run plugin discovery via _delivery_manager(), so surfaces that
never import model_tools (dashboards, TUI slash workers, query mode,
cron, gateway platform events) deliver plugin callbacks instead of
silently dropping them (#50776, #67597, #67890, #50937).
- _delivery_manager() joins any in-flight background discovery first and
tolerates test doubles that monkeypatch get_plugin_manager().
Symmetric force-reload (survived):
- agent/shell_hooks.py gains re_register_config_hooks(); the force branch
of discover_and_load() calls it after a successful sweep, restoring
config.yaml shell hooks that the ledger-driven unload wiped but cannot
restore (they are config-owned, not plugin-owned) (#60036).
- unload(plugin=None) now sweeps pre-ledger _plugin_tool_names entries
out of the process-global tools.registry, mirroring the platform-name
sweep that already existed, so zombie tools cannot survive a force
reload in long-lived pre-ledger processes (#60050).
Superseded by the ownership ledger (dropped from #64188):
- _unload_global_plugin_registrations() bulk tool/platform teardown —
the ledger's reverse-order handle disposal with previous-entry
restoration covers it more precisely.
- tools.registry/platform_registry displaced-entry LIFO restore stacks —
the ledger's restore_registration() identity-checked previous-entry
restoration made them redundant.
- Discovery serialization lock + double-checked singleton — main already
has _discovery_lock on every discover/unload path and a keyed,
lock-guarded per-home manager cache (#24714 concern is covered).
Fixes tracked under #64178 (#50776, #60036, #60050, #24714, #67798,
#50937, #67597, #67890, #31480 — #31480 already handled on main by
_parse_hooks_block warn+suggest).
CI caught the file hanging AFTER '6 passed in 4.32s' until the runner's
300s SIGKILL. Two defects, same class the PR fixes:
1. The executor-refused (interpreter shutdown) fallback ran the native
call UNBOUNDED on the calling thread — a wedged pipeline would block
process exit forever. Now runs on a bounded daemon exit-thread with
the same timeout/abandon semantics as the executor lane.
2. The wedge tests left daemon workers parked on Event.wait() and live
sessions registered on the atexit shutdown hook; exit re-ran the
wedged pops (bounded, 10s each) and the per-file runner timed out.
Autouse teardown now releases every wedge and drains each runtime.
Canonical runner: 4.4s (was 300s file-timeout kill). Bare pytest was a
false green for this class — it exits before atexit replay cost shows.
The NeMo Relay native binding's scope.pop/push are synchronous and
unbounded ('returns after the scope is closed successfully'). When the
native pipeline cannot make progress, the session coordinator's turn and
session finalization block forever inside run_conversation: delegated
children finish their turns but never return, and delegation batches die
on the stall watchdog. Proven live 2026-08-10 on the staging fleet — a
falsification probe (plugin disabled, identical config) completed the
same delegation batch that wedged with the plugin active.
Bound every scope lifecycle operation that gates turn/session completion
(session push, turn push, turn pop, logical-LLM pops, session pop,
subscriber flush) by running the native call on a shared
DaemonThreadPoolExecutor and honoring a 10s result timeout. On breach a
TimeoutError propagates into each call site's existing exception
handling — warn, retain the unclosed-prefix diagnostics, continue — so
the worst case is one lost span, never a blocked agent. timeout=None
preserves byte-identical synchronous behavior for all other callers, and
interpreter-shutdown paths fall back to the synchronous call so the
atexit flush still exports.
Observability must never block the product.
Rebase over the capability-model merge dropped two behaviors the tests
pin: (1) unload_all must still unregister every _plugin_platform_names
entry from the global platform registry (pre-ledger state has no
handles); (2) list_plugin_sources() must see profile-scoped
registrations — scoped entries are plugin-registered by definition.
Adds a pre_transcription transform hook (prompt/language/model mutable,
file_path read-only, last-writer-wins per the transform_* convention)
fired before any STT backend, threads prompt to faster-whisper
(initial_prompt) and OpenAI/Groq/Mistral/DeepInfra (prompt), adds an
optional stt.prompt config key on the same plumbing, and keeps the
no-hook dispatch path byte-identical. Fixes#64168.
Documents the new surface for users: a "Transcription prompt
(vocabulary hints)" subsection in the configuration guide (composition
order, per-provider support matrix, length contract, privacy warning),
a pre_transcription entry in the hooks reference, and the mirrored row
in the plugins hook table.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AG6LyYMvHC2o6HbVUozmVR
Two review items raised on #65449 (thanks @hansai-art):
1. Explicit test that post-module-load registration REBUILDS the
_PREFIX_SUBSTRINGS pre-screen tuple — plugin patterns flow through
the same fast path as built-ins, never around it. This was covered
implicitly by the masking tests; now it is asserted directly.
2. Plugin patterns are now stored keyed by registration source, giving
the #64229 lifecycle/ownership-ledger work a clean seam to drop one
plugin's patterns on unload. No public removal API is added —
additive-only stands; unload remains a host-owned lifecycle concern.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PnMCvi2vXqfs996AjVeF2F
Nested unbounded quantifiers ((a+)+, (?:x*)*, (a{2,})+) backtrack
catastrophically, and registered patterns run against every log line
and tool output, so a pathological pattern from a buggy plugin would
stall the host process. Registration now rejects the structural
nesting shape with a logged warning, same fail-soft contract as the
other validators.
Detection is a hand-rolled scanner matching the top-level-alternation
check's idiom: escapes and character classes skipped, group stack
tracks whether each group body contains an unbounded repeat, reject
when such a group closes into an unbounded quantifier. Overlapping
alternation ambiguity ((a|aa)+) is documented as out of scope.
Also refreshes the test module docstring left stale by the demo-plugin
unbundling.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PnMCvi2vXqfs996AjVeF2F
'ab|.*' compiled and carried the accepted 'ab' literal prefix while its
'.*' branch stayed unprefixed, escaping the no-redact-everything
guarantee (_extract_literal_prefix stops at '|'). Registration now
rejects top-level alternation with a regression test for exactly that
shape; grouped alternation after the prefix, escaped pipes, and
character-class pipes remain accepted.
The bundled nvapi-redaction reference plugin is removed per repo policy
(vendor integrations ship as standalone plugin repos); the end-to-end
register() coverage now uses a synthetic plugin written at test time.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PnMCvi2vXqfs996AjVeF2F
Every new vendor token format has required a core PR appending to
_PREFIX_PATTERNS in agent/redact.py (fw_, retaindb_, hsk-, mem0_, brv_
all landed that way; #58466/#58501 are the latest of the class). This
adds an additive-only registry so provider plugins own their format:
- agent/redact.py: register_redaction_patterns(patterns, source) —
validates each pattern (must compile; must start with >=2 literal
characters so the pre-screen substring gate keeps working and
redact-everything patterns like `.*` are structurally impossible),
dedupes against built-ins and prior registrations, then atomically
rebuilds _PREFIX_RE and _PREFIX_SUBSTRINGS. Registered patterns get
identical treatment to built-ins everywhere: same head/tail masking,
same non-reusable «redacted:label…» sentinel on file_read, same
security.redact_secrets operator opt-out. Additive-only by design —
a plugin can extend masking, never weaken it. Includes a
test/teardown reset helper.
- hermes_cli/plugins.py: PluginContext.register_redaction_patterns()
delegating with per-plugin attribution; warns and returns 0 on any
failure so a broken plugin can never break startup.
- Bundled reference plugin `nvapi-redaction` (opt-in): masks NVIDIA
API keys (nvapi-, used by NIM / build.nvidia.com) — a real format
missing from core, shipped as the one-liner plugin that previously
would have been a one-line core PR.
13 new tests: baseline gap, masking + built-ins unaffected, invalid
regex / no-literal-prefix / dedupe / non-string rejection, file_read
sentinel labeling, reset semantics, PluginContext wiring incl.
exception isolation, and a no-mocks end-to-end through the demo
plugin. Existing redaction suites (tests/agent/test_redact.py,
tests/tools/test_kanban_redaction.py) pass untouched.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FWMcB7RPSYUpsXDfBgwjzM
Closes#26193
Adds ContextReferenceProvider ABC so plugins can register custom
@-prefixes (e.g. @issue:ENG-123) with autocomplete and expansion.
Plugin output flows through existing token-limit guards. Zero
breaking changes.
Salvage of PR #64317 (@deaneeth) onto current main, implementing #64161:
observer-only on_stream_start / on_stream_delta / on_stream_end /
on_interim_message plugin hooks dispatched through a host-owned bounded
queue (one worker per callback) so plugin callbacks never run inline on
the token path. Reasoning deltas are opt-in via
plugins.stream_reasoning_deltas.
Salvage the plugin-owned static prompt idea from PR #51589 into the constrained #64167 contract: stable IDs, deterministic placement, bounded fail-open rendering, and full-prompt resume recovery without new session columns.
Co-authored-by: Topher Ross <biz@topherross.com>
Wire an optional `task=<key>` kwarg through the PluginLlm facade so a
plugin can route an LLM call through an auxiliary model slot it
registered via `ctx.register_auxiliary_task`. Registration already
existed; this adds the missing consumption half. Closes#44673.
Sub-issue 08/14 of the plugin-interface expansion tracking issue #64182.
- New optional `task:` kwarg on complete/acomplete/complete_structured/
acomplete_structured. Unset or "auto" keeps today's main-model path
byte-for-byte (task=None reaches call_llm exactly as before), so no
prompt-cache or default-behavior change.
- A set task resolves provider/model through `auxiliary.<task>` via the
existing auxiliary_client path, identical to built-in aux tasks.
- Trust gate (per the round-2 design correction): a plugin may only pass
a key it registered itself; a built-in key additionally requires
`plugins.entries.<id>.llm.allow_task_override: true`. A foreign or
unknown key is rejected with a PluginLlmTrustError and a logged warning
naming the offending plugin and key -- fail loud, NOT a silent fallback
to auto (which would mask misconfiguration and could route to the main
model the user steered elsewhere).
- The plugin_llm audit dict and audit-log line gain a `task` field.
- register_auxiliary_task now stores the plugin's canonical id
(`key or name`, the same id ctx.llm is bound to) as the slot owner, so
the trust gate matches ownership even when a manifest sets a distinct
key. For the common no-key case this equals the name (unchanged).
Tests (tests/agent/test_plugin_llm_task_routing.py, 24): _check_task
resolution incl. own/foreign/unknown/built-in-gated keys and loud
rejection; end-to-end routing sync+async+structured; production-path
forwarding into call_llm/async_call_llm (covers the task=None->task line);
and ownership resolution against the real plugin registry incl. the
name/key reconciliation.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013b1XyXitAxV7phGmKWigJX
