Flip the state.db retention defaults per Teknium's decision on #54189:
- sessions.auto_prune: false -> true. A stock install now prunes ENDED
sessions inactive for retention_days at CLI/gateway/cron startup
(at most once per min_interval_hours). Open, pinned and mid-turn
sessions are never deleted; the only open rows touched are stale
automation sessions (#100903 sweep), which are closed, not deleted,
and aged a further full window before removal.
- sessions.retention_days stays 90 (already the default; verified).
- Auto-VACUUM is now additionally gated on the reclaimable fraction of
the file: PRAGMA freelist_count / page_count must exceed 25%
(AUTO_VACUUM_MIN_FREELIST_RATIO) on top of the existing
min_vacuum_interval_days throttle. Pruning a few small sessions on a
dense multi-GB DB no longer rewrites the whole file to reclaim a few MB.
Unknown ratio (pragma read failure) falls back to the time throttle.
Existing installs that explicitly set any sessions.* key keep their
values (load_config deep-merges DEFAULT_CONFIG under user YAML); only
unset keys pick up the new defaults. No _config_version bump needed.
cli-config.yaml.example documents the section commented-out so
installers that copy it verbatim never pin these as explicit settings.
Tests: ratio gate (below/above/at-threshold/unknown/override), real-DB
freelist ratio, default assertions, fresh-config startup hook reaches
the prune call, explicit opt-out respected, template-does-not-pin-keys.
- display.bell_on_approval (default false): same BEL mechanism as
bell_on_complete, rings when a dangerous-command approval prompt
opens (_approval_callback / approval.request event). Complements
bell_on_clarify from the previous commit.
- fix(ui-tui): eslint curly error in useConfigSync.applyDisplay
(if without braces) that failed the CI JS & TS checks job.
Same BEL mechanism as display.bell_on_complete (\a / \x07), gated by
display.bell_on_clarify (default false). CLI rings in _clarify_callback
and _clarify_callback_batch before _paint_now(); TUI rings on
clarify.request when bellOnClarify && stdout.isTTY. Docs in
cli-config.yaml.example and website/docs/user-guide/configuration.md.
Posts made with a user token (xoxp-) arrive with app_id and no
client_msg_id, so _event_declares_bot_sender dropped them as app traffic;
the only workaround was allow_bots: all. Adds
platforms.slack.extra.api_human_users (SLACK_API_HUMAN_USERS fallback), a
users-only allowlist consulted inside the predicate.
Salvaged from #100964 (users only: an app-id allowlist would also admit
the app's own xoxb bot posts, which share the user+app_id shape).
Adds two bounded fast modes on top of the static /fast toggle, default OFF:
- `auto`: every user turn opens a `agent.fast_auto_seconds` (default 60s)
window; requests inside it carry the provider fast param, later tool-loop
requests fall back to standard pricing.
- `cold`: the same window, but only on the first turn of a session (no prior
user/assistant/tool history).
agent/fast_mode.py holds the whole policy: `begin_turn()` at the
run_conversation ingress arms `agent._fast_until`; `effective_request_overrides()`
is consumed in the ONE place request_overrides feed the transports
(build_api_kwargs), so the fast param is a per-request kwarg only. System
prompt, tools and messages are untouched — the prompt cache is preserved.
resolve_fast_mode_overrides() is now the single gate for static and bounded
modes and accepts provider/base_url: OpenRouter, Nous, Copilot, Azure,
Bedrock and custom base_urls never receive service_tier/speed (#34308's
route gating). Both existing callers (CLI turn route, gateway turn route)
and the TUI config.set path pass the route.
Surfaces: config `agent.service_tier: auto|cold` + `agent.fast_auto_seconds`,
`/fast auto|cold` in CLI, gateway (picker gains both entries), TUI/desktop
config.set; status shows the mode; web dashboard select lists the real
values. Docs: configuration.md Fast Mode section with mode table + cost note,
slash-commands, cli-config.yaml.example, locale strings for the two picker
entries.
Salvages #89991 (bounded fast modes) and #34308 (route gating).
Fixes#64785, #74730.
Co-authored-by: Eva <239388517+100yenadmin@users.noreply.github.com>
Co-authored-by: kbaicai <kbaicai@qq.com>
Every gateway/plugin platform adapter hard-coded aiohttp.ClientSession(trust_env=True)
(~20 sites), so a gateway launched by a Windows Scheduled Task that inherits a stale
HTTP_PROXY (Clash/V2Ray on 127.0.0.1:7890) looped on 'Cannot connect to host' with no
way to opt out short of NO_PROXY hacks per vendor host.
- gateway/platforms/base.py: gateway_trust_env() reads gateway.trust_env (default true);
resolve_proxy_url() skips generic HTTP(S)_PROXY/ALL_PROXY + macOS system-proxy
auto-detect when false (explicit per-platform vars still win).
- All aiohttp ClientSession sites in weixin, qqbot, matrix, line, wecom, slack, sms,
teams, google_chat now pass trust_env=gateway_trust_env(); mattermost + homeassistant
bare sessions gain the same kwarg (intent of #70119 / #56229).
- DEFAULT_CONFIG + cli-config.yaml.example + messaging docs.
- tests/gateway/test_gateway_trust_env.py: config flip + no-bare-literal sweep.
Reported-by: @ranlingfeng (#48820), @frontnopipe-cloud (#76309)
Co-authored-by: rcarrata <rcarratalasanchez@gmail.com>
Co-authored-by: Backroads4Me <TEDLANHAM@GMAIL.COM>
The 10s hygiene_max_turn_hold_seconds budget (#92318) releases the arriving
user turn while the summary model is still streaming. For thinking summary
models (DeepSeek-V4-Flash etc.) whose reasoning prefix alone exceeds 10s,
the abandonment path ALWAYS cancelled the commit fence — 100% of the summary
attempt (including the full thinking prefix) was discarded on every turn,
permanently disabling auto-compression while paying the summary model 10s
of thinking per turn, and the flat 60s retry-after then blocked the
agent-side preflight from a fresh chance.
Structural fix (maintainer-chosen direction in #97963): decouple the turn
from the compression instead of holding the turn longer or making the hold
progress-aware (which would reintroduce the #90845 frozen-turn bug):
- CompressionCommitFence gains mark_commit_watermark_fenced() /
commit_watermark_fenced; compress_context marks the fence right after
capturing get_active_message_watermark() under the durable compression
lock (#75316/#87484) — the property that makes a LATE commit safe: rows
appended after compression start survive both commit paths verbatim as
cloned concurrent tail (archive_and_compact watermark= and
publish_compression_child watermark/watermark_ceiling).
- gateway hygiene turn-hold handler: when the fence is watermark-fenced,
the detached worker (already kept alive via
_defer_agent_cleanup_until_future_done) KEEPS its commit admission; the
user's turn proceeds on the uncompressed transcript at the same 10s
budget, and the summary is adopted at the worker's own watermark-fenced
commit boundary. Unfenced workers are cancelled exactly as before —
never worse than the status quo.
- No retry-after is armed while the kept-admission attempt runs (it would
block preflight adoption via the same-session cooldown); re-attempt
spacing is covered by the durable compression lock
(_session_has_compression_in_flight). If the worker ends WITHOUT
committing, a done-callback restores the flat non-escalating 60s
retry-after; a successful adoption resets the hygiene failure streak.
The streak never advances for a deferral either way.
- Docs: configuration.md hygiene_max_turn_hold_seconds one-liner updated
to describe deferred adoption and the thinking-model case;
config_defaults.py comment updated. Knob stays config.yaml-only.
Invariants preserved:
- 10s user-latency cap stays hard (#90845/#92318):
test_session_hygiene_turn_hold_budget_abandons_streaming_wait passes
UNMODIFIED (its worker is not watermark-fenced, so it pins the cancel
path through the public surface).
- Stale-clobber impossible: adoption only rides commits bounded by the
start watermark; the fence still gates admission and unfenced/late
results are discarded.
New regression tests (tests/gateway/test_session_hygiene_turnhold_adoption.py):
- watermark-fenced worker keeps admission, late summary is committed,
turn still released at the budget, no cooldown while running,
streak reset on adoption;
- kept-admission worker that ends without committing restores the flat
turn-hold retry-after (<=120s, names turn-hold, streak untouched);
- unfenced worker still cancelled and discarded (status quo).
Sabotage-verified: disabling the keep-admission branch fails the two new
adoption tests and leaves the unfenced-cancel test green.
Fixes#97963
The conversation loop has forced stream=True for every turn — subagents
included — since #3120 (always-prefer-streaming for liveness health
checking). Self-hosted OpenAI-compatible backends with broken streaming
tool-call paths (e.g. vLLM --tool-call-parser qwen3_xml + reasoning
parser + MTP) can leak tool-call markup into plain text and return zero
tool_calls, so delegated tasks silently no-op instead of executing.
model.streaming was never a real config key, so users could not opt out.
Seed agent._disable_streaming from model.streaming: false at init; the
loop already routes that flag to the non-streaming path (the same path
used when a provider rejects streaming at runtime). Default stays
streaming-on, preserving #3120's behavior for everyone else. Orthogonal
to display.streaming (token rendering).
Tests: config->flag seeding (patched loader + real config.yaml E2E),
legacy string model section, multi-agent config propagation.
PR re-review caught that cli-config.yaml.example and the setup wizard
still described the OLD day-stamp gate ("period starts on or after the
day you opted in"). The actual gate (CONSENT_GATE_SQL) requires the
entire package period to be contained in one recorded consent window -
stricter, and privacy-significant at opt-in/revocation boundaries: a
package straddling a revocation starts after opt-in yet is correctly
held back. Both surfaces now state the containment rule literally;
docs A.1 already did.
Builds the escalation layer on top of HexLab98's heal-log windowing
(salvaged from PR #96916):
- Per-session heal counters (heal events + messages healed) tracked by the
repair path in agent_runtime_helpers.py, session totals preserved across
10-minute log windows.
- Threshold escalation: after N heals in a session window (default 3,
configurable via agent.sanitizer_heal_escalation_threshold in
config.yaml, 0 = off) log ONE ERROR carrying session id + heal pattern
(events/messages/window/threshold), then stay quiet.
- ONE-TIME out-of-band user notice queued at the threshold and delivered by
the conversation loop through _emit_warning (status callback -> gateway
status message / CLI print). Never injected into conversation context or
the wire copy: prompt caching, role alternation, and durable history are
untouched. Never re-arms on a new window; scoped per session.
- Counters visible in diagnostics: get_sanitizer_heal_stats() rendered in
the /debug share // hermes debug report, and the config key surfaced in
hermes dump overrides. errors.log carries the ERROR line for `hermes logs
errors`.
Salvaged from PR #84199 by @RickyYii. DirectAlias gains api_key/key_env; the direct-alias override re-resolves credentials against the alias endpoint (host-gated, #28660) and reuses the pre-alias key only on an origin match; oneshot -m <alias> passes the alias key as explicit_api_key; direct-alias branch gains the OLLAMA_API_KEY host gate. Fixes#83612.
Router shipped a minimal /v1/chat/completions compatibility surface
(translated onto Responses) after this PR was written, so the
'does not exist and 404s' wording is stale. Responses remains the
native wire — per-model reasoning-effort validation, reasoning
summaries, and prompt caching live there — so the api.router.com
host mandate is unchanged; only the comments and docs are updated.
Ramp Router is an OpenAI Responses-compatible LLM gateway at
https://api.router.com/v1 that routes each request across upstream
providers (OpenAI, Anthropic, xAI, Fireworks, ...) with server-side
fallbacks and spend controls. Nous asked for a PR adding it as a
provider, so:
- plugins/model-providers/router/: RouterProfile plugin —
api_mode=codex_responses, RAMP_ROUTER_API_KEY auth,
RAMP_ROUTER_BASE_URL override, live account-scoped catalog via
GET /v1/models (no hardcoded fallback_models: IDs are key-scoped and
Router's docs mandate runtime catalog reads).
- hermes_cli/providers.host_mandated_api_mode +
runtime_provider._detect_api_mode_for_url: api.router.com ->
codex_responses. The host is Responses-only — POST /v1/chat/completions
does not exist and 404s — so this is a genuine host mandate (exact
hostname match per #32243, mirroring the api.meta.ai precedent).
- providers/base.py: new overrideable supported_reasoning_efforts(model)
hook (tri-state: None=defer, ()=model takes no reasoning params,
tuple=clamp set). Router validates reasoning.effort per model and
returns HTTP 400 invalid-argument on levels outside the model's
published vocabulary, and 400 unsupported_parameter when a
non-reasoning model receives any reasoning field (both verified live).
The profile answers from a cached copy of the catalog's
router.capabilities.reasoning block: cache-only on the hot path,
seeded for free by fetch_models(), disk-mirrored across processes
(/cache/router_catalog.json), background-warmed when cold
— same design as the OpenRouter reasoning-caps clamp on the chat path.
- agent/transports/codex.py: consult the profile-declared vocabulary in
the generic effort-clamp branch (xai/actual/github branches untouched;
profiles that do not override the hook see no behavior change).
- cli-config.yaml.example + adding-providers.md + providers/README.md:
document the provider, the host mandate, and the new hook.
- tests: behavior contracts for the host mandate/URL detection/spoof
rejection, profile registration + auth auto-registry wiring, catalog
parsing, and transport clamp/suppression/fallback paths.
Verified live against api.router.com (Aug 2026): one-shot chat,
streaming SSE, tool calls + parallel_tool_calls, encrypted-reasoning
replay on OpenAI-served models, function_call_output follow-up turns on
OpenAI- and Fireworks-served models; store:false / prompt_cache_key /
include:[reasoning.encrypted_content] / reasoning.summary accepted
across backends; effort clamp confirmed to convert a would-be 400
(xhigh on o3) into a successful request via the disk mirror.
PR review (andrexibiza, post-a69a9c351d) caught the one operator-facing
surface the identity change missed: the example config still promised
the profile-scoped ID is NOT sent and described the 30-day rotating
HMAC. Rewritten to state the stable install_id is transmitted as-is,
matching the sender, wizard, and docs A.2. Swept the repo for further
stale references: none remain (the HMAC text in relay-shared-metrics.md
A.2/A.3 is the intentional decision record).
* refactor(code-execution): retire kernel_mode — session kernels always on for local runs (remote per-call is a tracked gap, not a mode)
* test(code-execution): env-filtering probes use reset=true — kernel env is frozen at spawn, so env rules are only observable on a fresh kernel
* test(code-execution): kernel-aware fixes for mode/pythonpath suites — reset=true on frozen-at-spawn probes, per-test kernel disposal, abort-after-capture fake Popen
* test(code-execution): strict-mode cwd is a behavior contract (staging tmpdir, not session cwd) — kernel stages in hermes_kernel_*, per-call in hermes_sandbox_*
* feat(tools): session-persistent kernels for execute_code (kernel_mode: session)
execute_code spawns a fresh Python process per call, so every multi-step
data task re-loads its inputs: a CSV parsed in call one is gone by call
two, and scripts route state through temp files to survive. Hermes
already rewards programmatic tool calling (execute_code-only turns
refund the iteration budget), which makes the missing half — state that
survives between calls — the bottleneck.
Add opt-in `code_execution.kernel_mode: session`: one persistent kernel
per (task, mode, interpreter, cwd, tool-set). Variables, imports, and
loaded data persist across calls; `reset=true` discards state on demand.
The default `per-call` keeps today's behavior byte-for-byte.
Safety posture is unchanged by design: the child env comes from the same
builder as the per-call path (extracted, not duplicated, so the secret
scrubbing / PYTHONPATH hygiene cannot drift), the RPC server is the same
`_rpc_server_loop` with the same token and a per-cell tool budget, and
output passes the same ANSI strip + secret redaction. A timed-out or
interrupted cell kills the whole kernel tree and the next call respawns
— a wedged kernel can never hang the agent. The kernel env is frozen at
spawn; the schema and config comment say so.
Wire protocol: NDJSON requests on the kernel's stdin; responses framed
on stdout behind a per-kernel random sentinel, with unframed bytes
(fd-level output from user-spawned subprocesses) attributed to the
serialized current cell. The generated RPC client reconnects once when
HERMES_RPC_PERSISTENT=1, because a kernel legitimately outlives the RPC
server's 300s idle window between cells.
Tested on macOS 15 (Apple Silicon), Python 3.11: 13 new tests in
tests/tools/test_code_kernel.py (persistence, reset, error-keeps-kernel,
timeout-kills-kernel, sys.exit ends kernel, subprocess fd passthrough,
schema surface, mode fallback) plus the existing
test_code_execution.py / test_code_execution_modes.py suites (81 passed).
* fix(tools): session kernels get a stable owner, bounded lifetime, and per-cell RPC authority
Addresses the blocking review on the session-kernel design: two
authority/lifecycle boundaries were wrong.
1. Ownership and bounded lifetime. The kernel key's first component is
now the conversation's approval session key (_resolve_owner), not the
per-turn task id run_agent mints per top-level invocation — so state
genuinely survives across user turns of one conversation, and delegated
subagent sessions isolate naturally under their own keys (the task id
remains only the last-resort owner for embeds/tests with no session
context). Lifetime is bounded on four edges: kernels are disposed at the
same session boundary that clears the owner's approval/yolo state
(tools.approval.clear_session -> shutdown_kernels_for_owner), reaped
after code_execution.kernel_idle_timeout seconds idle (default 1800,
swept on every entry), capped process-wide at
code_execution.max_session_kernels live children (default 4, LRU
evicted), and still torn down by reset/death/atexit as before. The
ownership + disposal + idle-reap + cap shape deliberately carries
forward the lifecycle invariants of the earlier session-persistent
implementation in #88637 by @z80dev.
2. Per-cell RPC authority. The serving thread no longer freezes the
spawning cell's context/callbacks for the kernel's life. Each cell
installs a CellAuthority — captured on the calling thread exactly as
propagate_context_to_thread would for a per-call RPC thread — before its
request is written, and retires it on every settle path; _rpc_server_loop
gains a dispatch hook the kernel uses to route each tool call through
the CURRENT cell's context, callbacks, and task id. A call arriving with
no active cell is refused. Interpreter state persists; RPC authority
does not.
Composition with the per-script static guard (see the config note): a
persistent namespace lets cell N+1 invoke objects cell N created, which
a single-cell static scan cannot see — the runtime RPC boundary
(allow-list by name, per-cell budget, per-cell authority) is the
operative cross-cell enforcement in this mode, and the adversarial
alias test pins exactly that.
Tests (9 new): state survives across turns of one conversation;
sessions isolate; clear_session disposes the owner's kernels (and the
next turn starts fresh); the live-kernel cap LRU-evicts with evicted
children proven dead; idle kernels are reaped; a later cell's RPC runs
under that cell's approval callback; a cross-cell alias dispatches under
the CURRENT cell's authority; a settled cell's authority refuses
dispatch; each cell installs a fresh authority. 22/22 kernel tests, 81
code-execution tests, ruff clean. The 7 test-order failures in the
tools/-k-approval selection reproduce identically on the clean branch
base (pre-existing pollution, not this change).
* fix(code-kernel): delegated children get their own kernels — child contexts inherit the parent approval key, so qualify the owner with the delegation session id (live-verified leak, both directions)
---------
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
cli-config.yaml.example said macOS is "always held at FULL regardless",
which reads as "your setting is ignored on this platform" and would talk
an operator out of choosing EXTRA. _apply_synchronous_pragma only refuses
values BELOW FULL on Darwin; EXTRA is applied normally.
The existing doc guard only asserted the key's presence, so it could not
have caught this. Pin the distinction instead.
Reported by @Enough1122 in review.
`apply_database_pragmas()` reads five sizing pragmas from `database:` and no
durability one, and `_enforce_macos_synchronous_full()` returns early when
`sys.platform != "darwin"`. Between them, nothing in the process ever executes
`PRAGMA synchronous` against state.db on Linux or Windows.
The effective level there is therefore `SQLITE_DEFAULT_WAL_SYNCHRONOUS`, a
compile-time constant of whichever SQLite the interpreter links. Debian and
Ubuntu builds commonly ship it as NORMAL; the bundled build and a plain
source build use FULL. So the durability of state.db is decided by which
python3 the installer found, is invisible from config, and cannot be pinned.
#90837 is three weeks of corruption forensics conducted on Ubuntu under the
stated premise `synchronous=FULL`, with every other cause eliminated live.
That premise is not something the reporter could have verified from config,
because there was no config key to set and no log line to read back.
- `resolve_synchronous_level()` maps the spellings operators actually write
(OFF/NORMAL/FULL/EXTRA, any case, or 0-3) to the PRAGMA integer, and
returns None for anything else. Kept out of the sizing loop on purpose: an
unrecognised `cache_size` harmlessly falls back to a default, an
unrecognised durability level must not.
- `_apply_synchronous_pragma()` applies it, and on Darwin refuses to lower
below FULL. `_enforce_macos_synchronous_full()` runs during
`apply_wal_with_fallback()`, which is earlier than `apply_database_pragmas()`,
so without an explicit floor a configured NORMAL would silently undo #64355
by the accident of running last. Raising to EXTRA on macOS is allowed.
- Unset changes nothing, so no existing install moves.
Tests: 34, covering the parser, application, the unset path, the typo path,
a guardrail that #77630's five keys still apply, and the Darwin floor in both
directions. Removing the wiring fails 6; removing the floor alone fails 1.
Related to #90837
Step 1+2 of the shared-metrics exporter.
Config: telemetry.shared_metrics.send (default false) and .endpoint
(default production), resolved by a new shared_metrics_send_config
module. Precedence is HERMES_TELEMETRY_ENDPOINT > config > default; the
env var exists so the live staging E2E never has to mutate a user's
config. send requires enabled and never implies it — that combination
is a misconfiguration the user believes is working, so it logs an ERROR
once per process rather than silently doing nothing. Plaintext
endpoints are refused unless the host is loopback, so a typo cannot
send telemetry in clear text.
Per AGENTS.md, outbound telemetry needs a user-facing opt-in, so
setup_telemetry now prompts for sending as a second, separate question
and force-disables send when collection is turned off.
Storage: six additive nullable columns on package_outbox for send
bookkeeping. The store schema version deliberately does NOT move —
_ensure_schema_in_transaction raises on any version it does not
recognise and has no forward-compatibility branch, so bumping it would
hard-fail an older Hermes, a second profile on an older build, or a
rollback, against the same file. Old readers select named columns and
never SELECT *, so the additions are invisible to them.
Also corrects the two places that promised telemetry is never uploaded
(config_defaults comment and cli-config.yaml.example); leaving them
would make them false privacy statements once sending ships.
Tests: 26 covering config precedence, the enabled/send relationship,
transport safety, fresh-database creation, upgrade from a pre-send
database (rows preserved, version pinned, idempotent), and that the
shipped export query still runs. Mutation-checked: bumping the schema
version fails 5 of them.
Independent review caught a compaction authority the gate missed:
post-turn micro-compaction (turn_finalizer -> _micro_compact) absorbs the
oldest exchanges into a rolling summary with no pre-compress checkpoint
hook in its path, and both compression.checkpoint_required and
compression.micro_compact could be enabled together — assistant evidence
could vanish into a summary the checkpoint filter later excludes, without
ever reaching the durable provider.
- agent_init: checkpoint_required forces micro-compaction off (warned),
mirroring the native-compaction suppression
- turn_finalizer: defense-in-depth guard at the call site (attribute is
plain mutable state a future path could flip on a live agent)
- behavioral regression test with a sabotage control (gate off proves the
harness reaches the call site; gate armed proves zero calls)
- docs + config example mention the suppression; stale v1 test header fixed
Per review: existing providers should not be retroactively re-versioned or
handed a changed payload. Version 1 is now the implicit historical
on_pre_compress() contract (best-effort, raw message list) that every
pre-existing provider is already on; the fail-closed checkpoint contract
becomes version 2. MemoryManager routes the raw transcript to v1 providers
unchanged and hands the host-normalized evidence list only to v2+ checkpoint
providers, so the plugin surface contract for shipped providers is
byte-identical with the gate off.
The fail-closed gate lived only in compress_context(), but two native
lossy owners compact without ever crossing it (review on #93996):
- codex app-server: in "native"/"off" auto-compaction mode (native is the
default) Hermes preflight is skipped and the codex agent compacts its
own thread inside run_turn() — the compress_context() rejection was
unreachable. init_agent now refuses checkpoint_required together with
api_mode=codex_app_server (BLOCKED_MISSING_PREREQUISITE, extracted as a
testable guard), and run_codex_app_server_turn() fails closed as
defense in depth before a turn can reach the codex-owned boundary.
- Responses server-side native compaction:
native_compaction_context_management() now returns None while the gate
is armed, so context_management never goes on the wire and the
checkpoint-aware Hermes compressor stays authoritative. The suppression
is logged once per process, not silently applied.
Regressions: checkpoint_required + app-server raises before run_turn()
(the session is never created); checkpoint_required keeps
context_management off the wire while the plain configuration still
produces it; the init guard refuses exactly the incompatible pair. Docs
and cli-config.yaml.example describe both bindings.
Refs #93986
Context compression is intentionally lossy. Deployments that archive
transcript evidence to an external durable store before compaction had no
way to guarantee the archive actually happened: MemoryManager.on_pre_compress
swallows provider failures by design, so a failed archive silently degraded
into data loss.
This adds an opt-in, provider-agnostic checkpoint contract:
- memory_provider: PRE_COMPRESS_CHECKPOINT_API_VERSION = 1; providers opt in
by advertising pre_compress_checkpoint_api_version. Version 0 keeps the
historical best-effort hook semantics.
- memory_manager: supports_pre_compress_checkpoint() capability probe;
on_pre_compress(require_checkpoint=True) propagates checkpoint-provider
failures and raises when no capable provider completed the checkpoint.
- conversation_compression: new compression.checkpoint_required config key
(default false, documented in cli-config.yaml.example). When enabled,
compaction fails closed with BLOCKED_MISSING_PREREQUISITE (the
uncompressed transcript is preserved) unless a checkpoint-capable provider
confirms the durable checkpoint. Providers receive normalized direct
user/assistant evidence: tool rows, system messages, tool-call wrappers,
and prior compaction summaries are filtered host-side into one stable
contract. codex_app_server compaction is rejected under the gate because
it exposes no truthful pre-compaction transcript boundary.
- hermes_state: persistent _compressed_summary column (declarative schema
migration via _reconcile_columns) so summary provenance survives process
restarts; only the resume model history carries the marker, keeping
get_messages_as_conversation on its existing contract.
- gateway: the lossy hygiene/auto-compact paths load the memory provider
(skip_memory=False) so a required checkpoint also guards those rewrites.
The gate arms only on an explicit boolean True (bare-MagicMock agents in
existing tests have truthy auto-attributes). Default behavior is unchanged:
checkpoint_required=false preserves best-effort semantics for all existing
providers. Contract tests, including a restart round-trip of the summary
marker, in tests/agent/test_pre_compress_checkpoint_contract.py.
Refs #93986
Follow-up to the #65422 salvage:
- startup_orphan_reap joins _RECOVERABLE_END_REASONS (kept distinct from
ws_orphan_reap for forensics): every recovery fence
(find_latest_gateway_session_for_peer, unarchive_recoverable_session,
promote_to_session_reset) now treats a startup-swept row as an
accidental end, so a sweep never makes a session unresumable.
- Config key moves from sessions.orphan_reaper to
dashboard.startup_orphan_sweep in DEFAULT_CONFIG, next to its siblings
ws_ping_interval / ws_ping_timeout / ws_orphan_reap_grace_s; the raw
loader in tui_gateway.server reads the new key (fail-open on missing).
cli-config.yaml.example and website/docs/user-guide/configuration.md
follow the dashboard.* documentation pattern.
- New regression test: a stranded 'active' row (ended_at NULL, no live
runtime) is swept AND still recoverable via peer-keyed lookup and fully
revivable via reopen_session afterward.
Close session rows left ended_at IS NULL when the in-process websocket
orphan timer dies with the process (#65194). Dual-clock staleness
(started_at AND newest message), desktop included, live in-memory
sessions excluded, scheduled once from both entry.main and the WS
sidecar so desktop/dashboard boots also run the sweep.
Keep extension control opt-in and preserve existing browser backends unless an exact server-bound controller is available. Centralize protocol and capability admission across API and dashboard transports, make selected-controller results authoritative, bypass stale availability caches only inside bound requests, and serialize structured results for the existing tool contract.
Add a real browser_snapshot route-table/WebSocket E2E, strict admission and ownership regressions, public configuration and protocol documentation, and tests proving feature-off/no-controller compatibility.
Composio-style MCP servers return un-paginated 22-47K-char payloads that
sail under the generic 100K per-result spillover threshold, bloating
context and ballooning per-turn reasoning time on long conversations.
Competitors cap harder (OpenCode/pi 50KB, Claude Code 30K, Codex ~10K
tokens). Three changes:
- mcp_* tools spill at a tighter 50K default (BudgetConfig.mcp_result_size,
config-overridable via tool_budget.mcp_result_size_chars; pinned and
per-tool overrides still win; capped by the context-scaled default).
- The persisted-output preview now teaches recovery: page the saved file
with read_file or process with execute_code instead of re-requesting the
same data from the remote API.
- Untrusted/MCP string results are scanned (bounded, first 64KB) for
provider-side elision markers ('...N more items', "has_more": true,
'saved to sandbox', data_preview) and get ONE cache-safe incompleteness
notice appended at result-construction time, before untrusted wrapping —
so the model stops treating provider-elided enumerations as complete.
- Hard 2M-char allocation cap in mcp_tool.py (text, error, and
structuredContent paths) so a pathological multi-MB server payload is
bounded before it propagates, while ordinary large results reach
spillover intact. Distilled from #56060/#56072/#56511 (issue #56059);
supersedes their 50K lossy truncation with spillover-friendly semantics.
Docs: configuration.md spillover-budget section + cli-config.yaml.example.
Co-authored-by: Stoltemberg <215755014+Stoltemberg@users.noreply.github.com>
Co-authored-by: AlexFucuson9 <295703459+AlexFucuson9@users.noreply.github.com>
Co-authored-by: Tranquil-Flow <66773372+Tranquil-Flow@users.noreply.github.com>
Reconciles the salvaged Responses-API mandate with the bundled meta-ai
plugin that landed in #88565:
- meta-ai profile api_mode -> codex_responses (prompt caching engages
only on /v1/responses; 0% vs 93-99% measured). Custom endpoints with a
non-api.meta.ai base URL still fall through to chat_completions via
the host-driven mandate design.
- cli-config.yaml.example: point the example at MODEL_API_KEY (Meta's
documented env var) and note the bundled provider covers the default
endpoint
- tests/providers/test_meta_ai_profile.py updated for the new wire
- hermes_cli/providers.host_mandated_api_mode: add exact-hostname clause for
api.meta.ai → codex_responses (measured 0% cache on /chat/completions vs
93-99% on /responses with retention); update docstring.
- hermes_cli/runtime_provider._detect_api_mode_for_url: mirror clause for
api.meta.ai (exact hostname, #32243) to keep runtime resolver in lockstep.
- agent/agent_init: call host_mandated_api_mode early in api_mode cascade
(after explicit api_mode wins, before provider-name specials) via lazy
import; single source of truth, preserves user override.
- agent/transports/codex._default_prompt_cache_retention_for_request: return
24h for api.meta.ai unconditionally; build_kwargs setdefault preserves
override; Bedrock branch untouched.
- cli-config.yaml.example: add commented providers.meta example (api_mode
auto-detected).
- website/docs/developer-guide/adding-providers.md: list Meta alongside
Codex/xAI as codex_responses native provider with retention note.
- tests: add hermetic behavior-contract suites for mandate, retention,
content-addressed prompt_cache_key, reasoning passthrough, AIAgent init,
usage cache reporting, model-switch override, and config roundtrip; extend
test_model_switch_openai_api_mode with meta cases.
Follow-up to #87400: drop the max_iterations and prompt_file knobs from
auxiliary.background_review. The aux model routing (provider/model/
base_url/...) predates #87400 and stays; the enabled switch and the
usage telemetry stay. The fork's iteration budget returns to the
historical hardcoded 16.
Persist fork token usage under session_model_usage task=background_review,
emit a per-fork completion log line, and expose enabled/max_iterations/
prompt_file so operators can see and bound the automatic review cost.
Address review feedback: load auxiliary.background_review once per spawn,
classify completion logs by summarize action prefixes, treat explicit
api_call_count=None as the documented default of 1, and WARNING on the
fail-open enabled-gate path.
Custom providers could only authenticate from a static credential (inline
api_key or a key_env env var). Enterprise gateways -- SSO/OIDC brokers, cloud
IAM, internal auth proxies -- issue short-lived bearers instead, so a value
copied into .env is stale within the hour: long sessions start returning 401s
and the user has to restart or run an external cron that rewrites .env.
The existing `secrets.command` source does not cover this: it runs once per
process at startup (subsequent calls are no-ops by design), so it cannot
re-mint a credential mid-session.
Add providers.<name>.key_cmd: a command that prints a token, wrapped at
resolution in a zero-argument callable. Both wire clients already accept a
callable api_key and invoke it per request (the Entra ID path established
this), so chat_completions, codex_responses and anthropic_messages all work
unchanged and always send a fresh credential. The callable also routes the
Anthropic client through its per-request Authorization hook, which is what
OAuth-gated gateway routes require -- so no per-vendor auth wiring is needed
anywhere in core.
- cached until shortly before the advertised expiry (60s leeway), so the
helper runs about once per token lifetime rather than once per request
- expiry is read from the OAuth 2.0 relative `expires_in` when present, and
otherwise from an absolute ISO 8601 deadline (`expiry`, `expiresOn`), which
is what CLI token helpers commonly print. Reading only `expires_in` treated
those helpers as advertising no TTL at all, cached their token for the life
of the process, and returned 401 on every request once the real deadline
passed. ISO parsing reuses hermes_cli.auth._parse_iso_timestamp rather than
adding another datetime parser.
- no synthetic expiry: when no TTL is advertised, or the advertised one is
unparseable or already past, the token is used and refreshed on 401 instead
of re-minted on an invented schedule
- stdout contract matches OAuth 2.0 token endpoints and existing agent
helpers (bare token or JSON access_token/expires_in); multi-line output is
rejected rather than guessed at, so a misconfigured helper surfaces as a
clear error instead of a corrupt-credential 401
- precedence: explicit --api-key still wins; otherwise key_cmd beats a
static api_key/key_env on the same entry
- failures never include the helper's output (may hold a partial token) or
the command string (may embed a client secret)
Resolution happens on two paths. agent/auxiliary_client.py resolves named
custom providers itself rather than calling _resolve_named_custom_runtime, so
key_cmd is honoured in both: wiring only the runtime resolver leaves the main
agent turn working while every auxiliary call (title generation, compression,
vision, embedding) falls back to the no-key-required placeholder and 401s.
Precedence is identical on both paths, so one config entry cannot yield two
different credentials depending on which resolver the caller reached.
Closes#84162
Signed-off-by: LordMelkor <kray@block.xyz>
delegation.max_concurrent_children caps how many delegated children run in
parallel per batch (and concurrent background delegation units). The old default
of 3 needlessly serialized independent fan-outs (e.g. reviewing/investigating N
PRs or issues at once), so large batches ran in slow chunks of 3.
Raise the shipped default to 10, which sits at/below the existing high-cost
advisory threshold (>10), so the default never trips the warning. Each child
still consumes API tokens independently, so this is a throughput/latency win the
user pays for in parallel token spend — the floor stays 1 and there is no
ceiling, so anyone can tune it down or up.
- config_defaults.py: default 3 -> 10; _config_version 36 -> 37.
- delegate_tool.py: _DEFAULT_MAX_CONCURRENT_CHILDREN 3 -> 10 (+ docstring).
- config_migrations.py: _migrate_to_37 lifts configs pinned at exactly the old
default 3 to 10 (deliberate non-3 overrides preserved; unset inherits 10).
- cli-config.yaml.example: documented default updated.
Verified: default/fallback read 10, version 37, and the migration lifts 3->10,
preserves an explicit 5, and leaves unset untouched.
Co-authored-by: Teknium <teknium1@users.noreply.github.com>
`agent.restart_drain_timeout` defaults to 0 and governed every class of
in-flight work at once. That default is deliberate for chat turns: the
gateway announces the restart to the user and pre-marks the session
resume_pending, so interrupting one is cheap and recoverable.
A cron run has neither property. Nobody is waiting on it, it is written
to jobs.json as a permanent failure, and a recurring job simply skips to
its next schedule. Sharing the chat budget meant `_drain_active_agents()`
short-circuited on `timeout <= 0` before entering the wait loop, so the
drain reported `drain took 0.00s, timed_out=True, cron_at_start=1,
cron_now=1` — it detected the job and killed it anyway.
Cron work now drains on its own deadline, `agent.cron_drain_timeout`
(default 30s, 0 opts out). The floor is clamped to the shutdown-watchdog
leash minus a teardown reserve, so the longer wait can never consume the
post-drain cleanup window: being SIGKILLed mid-cleanup would leave the
job wedged at `last_status=running`, strictly worse than the bug. Being
bounded also means a cron-triggered restart cannot deadlock on itself.
The `timeout <= 0` special case is gone — an expired deadline expresses
the legacy "interrupt immediately" behaviour, so `timed_out` is always
computed from real state instead of asserted up front. The drain-timeout
warning now reports the elapsed wait rather than the configured budget,
which is what made "timed out after 0.0s" so confusing in the report.
Chat-only shutdowns are unchanged: `restart_drain_timeout: 0` still
interrupts chat turns immediately.
Relates to #82161 (complements #82195, which removes the `hermes update`
self-deadlock that triggered the reported instance).
delegation.max_iterations is the per-subagent tool-call budget. The old
default of 50 truncated substantial delegated work: leaf agents spend
~15-20 turns on reconnaissance before producing output, then ran out of
budget mid-task and returned 'completed but unfinished' summaries. 250
gives real delegated work room to finish.
Changes:
- config_defaults.py: delegation.max_iterations 50 -> 250; _config_version 35 -> 36
- tools/delegate_tool.py: DEFAULT_MAX_ITERATIONS fallback 50 -> 250 (kept in
sync with the shipped default to prevent drift)
- config_migrations.py: _migrate_to_36 lifts configs still pinned at exactly
the OLD default 50 -> 250 on update, so existing installs inherit the new
headroom. Any other explicit value (deliberate override) is preserved;
unset inherits 250 at read time.
- cli-config.yaml.example: doc the new default
The cap is per-child and children run concurrently (max_concurrent_children
default 3), so this raises worst-case fan-out cost; delegation.child_timeout_seconds
(default 0 = off) remains available as a wall-clock guardrail, and users can
still pin a lower max_iterations explicitly.
Verified: migration lifts 50->250, preserves a deliberate 120, leaves unset
untouched (3/3); DEFAULT_CONFIG reads version=36, max_iterations=250, fallback=250.
Follow-up on the #84795 salvage: the sequential deadline gets its own
resolver key. Unset, it inherits the concurrent batch deadline (same
value, same HERMES_CONCURRENT_TOOL_TIMEOUT_S bridge) so the two executor
paths cannot drift by default; set, it can be tuned or disabled
independently. Documented in cli-config.yaml.example; 5 contract tests.
Deliberately NOT on run_bounded_sync: the executors extend deadlines
dynamically during human approval waits (authorization-gate excluded
seconds) — the shared primitive is fixed-deadline. Noted in the docstring.
