Tokens saved is the wrong headline for this feature. Micro-compaction is
not an efficiency optimisation — the same summarization work happens either
way. What it buys is (a) that work amortized across turns instead of one
stall, and (b) a window kept low enough that a session runs much further
before needing a hard compaction at all.
Neither shows up in "net tokens saved". A session can save nothing on paper
and still be a clear win on both counts.
So the telemetry now carries occupancy: tokens_after as a share of the
compaction threshold, plus the threshold and resolved window it was
computed from. That is the number that says whether a session has headroom
left. The report leads with it, and cross-references the batch
`compression_attempt` lines already in the log so it can show how often the
long pause actually fired — ideally never.
Occupancy is read from the cached threshold only. The public
`threshold_tokens` property resolves lazily and can issue a synchronous
/models probe (#32221); telemetry must never be the thing that blocks a
turn, so an unresolved window reports null. In practice a pass has already
resolved it via the tail calculation, so the field is populated. A test
pins the no-forcing behaviour directly against the emitter.
The report is pure ASCII: `scripts/check_subprocess_stdin.py` currently
dies on a cp1252 console before printing its results, and a diagnostic tool
that crashes on the platform it is diagnosing is worse than no tool.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The existing log line reports message counts, which is the least
informative number available here: absorbing one tool-heavy exchange can
drop hundreds of tokens while moving the count by one. There was no way to
answer "is this actually helping?" from a real session.
Emit one content-free JSON line per pass, in the same shape as the batch
compaction telemetry: before/after tokens, the delta, the size of the
absorbed exchange, the rolling summary size, duration, and running
per-session totals so a whole run can be read off the last line. No
transcript content rides along.
Add scripts/micro_compaction_report.py to aggregate those lines into
passes, outcome mix, net tokens saved, mean exchange size and durations,
with an optional per-session breakdown.
Measuring it immediately surfaced something worth documenting: the first
pass in a session normally *costs* tokens. The summary marker carries a
fixed ~400 tokens of scaffolding, paid on pass one against a single
absorbed exchange. From pass two the marker is replaced rather than added,
so the overhead is already paid and each exchange is close to pure saving.
Break-even is typically the second or third pass. Tests cover the
telemetry contract, the cumulative totals, and that first-pass/later-pass
shape so nobody reads a single turn and concludes it made things worse.
The estimator costs ~5 ms at 600 messages and ~20 ms at 1200, taken twice
per pass, post-turn — and only once an exchange is actually in hand, so
turns that no-op early pay nothing.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
`_find_one_exchange`'s docstring described an exchange as "(optional) user
message + assistant message + its tool results", but the walk skips past
user messages and starts at the assistant, so user turns are never absorbed
into the rolling summary.
The code is right and the docstring was wrong. Assistant output is largely
an account of what was done and survives summarising with little loss. The
user's messages are the intent everything else is derived from and cannot be
reconstructed from the work that followed — paraphrasing "use the existing
helper, don't add a new one" into a summary is how an agent ends up doing
the opposite six turns later. They are also cheap: a prompt is normally a
tiny fraction of what one tool result costs.
Correct the docstring, document the property (and its cost — a floor on how
small the middle can get, since user turns accumulate), and add a test so it
stays deliberate.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Covers what it does, the head/tail protection, the cursor and rolling
summary, defrag, how the session DB is kept in step, and the failure
paths. States the tradeoff up front: compression cost is amortized across
turns, at the price of older detail becoming summarized earlier in a
session than batch-only compaction would.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Both relay Slack knobs read their value through bool(), while the native
adapter they mirror uses str(raw).strip().lower() in {"1","true","yes","on"}.
A YAML-quoted string diverges:
dm_top_level_threads_as_sessions: "false" → relay True, native False
Non-empty strings are truthy, so the escape hatch is silently ignored in
exactly the shape an operator writes to switch it OFF. reply_in_thread has the
same defect and gates reply placement, session keying and run.py's progress
resolver, so one quoted "false" misfires three ways.
Route both through a shared _coerce_flag mirroring native's predicate. Real
booleans pass through untouched; None falls back to the default. Contract §8
documents the accepted spellings.
Tests: both knobs parametrized over the true/false spellings native accepts,
plus the absent-key default.
Salvaged from PR #47588 and rebased onto the post-campaign streaming core:
the StreamingTTSProvider ABC/registry and the ElevenLabs/OpenAI streamers
already live on main (tools/tts_streaming.py), so this ports the pieces
main lacked:
- GeminiStreamer: streamGenerateContent?alt=sse -> base64 PCM chunks
(24 kHz mono int16), reusing main's DEFAULT_GEMINI_TTS_* constants.
- XAIStreamer: WebSocket wss://api.x.ai/v1/tts -> binary PCM frames,
async->sync bridged via the _collect_async test seam.
- tts.streaming.provider config knob: pin one streamer, or 'auto' to
walk the priority list elevenlabs -> gemini -> openai -> xai. Unset
keeps the never-swap-the-user's-voice default.
- docs/streaming-tts.md: architecture, capability matrix, how to add
a provider.
- Unit tests for the knob, SSE parsing, and the WS bridge; key-gated
E2E tests (skipped without credentials).
Refs: #47588
Review finding: native gates per-message DM sessions behind
platforms.slack.extra.dm_top_level_threads_as_sessions; the relay lane
coupled session keying to reply_in_thread alone, so 'threaded replies +
one rolling session' was expressible on native but not here.
Adds the same knob to the relay subset (platforms.relay.extra.slack.
dm_top_level_threads_as_sessions, default true = per-message sessions,
unchanged behavior). false keeps thread-per-message reply placement but
skips the session stamp — one rolling DM session, legacy steer posture.
TDD: opt-out + default-unchanged tests written first.
Relocate the platforms.relay.extra.<platform> documentation from a new
user-guide page into docs/relay-connector-contract.md (the existing
canonical relay doc, already linked from gateway-internals) as §8. The
relay lane is an enterprise-only component: it gets minor coverage in
the developer-facing contract doc, not a prominent user-guide page, and
no links to private components.
- RelayAdapter.create_handoff_thread → one op-gated thread_create op
(Discord channel thread / Telegram forum topic / Slack named seed root);
None fallback contract preserved for the handoff watcher.
- RelayAdapter.rename_thread → thread_rename with only_if_current_name
no-clobber guard on the wire (connector enforces; Telegram guarded
renames fail safe). The native semantic-rename lane
(_is_discord_auto_thread_lane) lights over the relay via the
connector-stamped auto_thread_created/auto_thread_initial_name markers
parsed onto SessionSource in _event_from_wire.
- reply_to {text, author, is_own} wire parse onto the SAME MessageEvent
reply-context fields native adapters populate.
- gateway/relay/command_manifest.py: the gateway-declared slash-command
manifest (native Discord tree mirror) sent on the DISCORD hello; the
connector reconciles Discord's global registration (additive field,
older connectors ignore).
- Contract doc §OutboundAction ops + Phase 4 semantics sections.
- 12 new tests (tests/gateway/relay/test_relay_threads.py); relay suite
266 passed.
- RelayAdapter.send_exec_approval / send_slash_confirm / send_clarify:
override the base text fallbacks with ONE platform-abstract `prompt` op
(connector renders Discord components / Telegram inline keyboards /
Slack Block Kit / WhatsApp buttons+lists). Option sets mirror the native
adapters exactly (once/session/always/deny with the same
allow_session/allow_permanent/smart_denied gating; once/always/cancel;
choices + Other). Clarify option ids are positional (c0..cN/other) —
choice text is arbitrary UTF-8, callback budgets are 64 bytes.
- Pending-prompt registry: gateway-minted 8-hex prompt ids →
{kind, session_key, extras}; one answer wins, lazy expiry, unanswered
prompts swept opportunistically. Wire timeout_s stays advisory.
- _consume_prompt_response (wired into _on_inbound AND the Discord
passthrough lane): routes answers to the SAME primitives the native
button handlers call — tools.approval.resolve_gateway_approval,
tools.slash_confirm.resolve, tools.clarify_gateway
resolve/mark_awaiting_text — then acks in-channel. Unknown/expired ids
fall through as command-shaped text (typed-reply degradation, the
relay's analog of the native 'approval expired' edit).
- Discord type-3 stub replaced: an hp1:<prompt>:<option> custom_id decodes
to a structured prompt_response (codec mirrored from the connector's
promptCodec); foreign custom_ids keep the legacy best-effort text shape.
- MessageEvent.prompt_response field + ws_transport wire parsing (additive).
- react ack lifecycle: on_processing_start/complete → `react` ops
(👀 → ✅/❌, remove-then-add), op-gated on supported_ops, best-effort by
contract (a react failure never touches the turn).
- Op gating throughout: a connector not advertising `prompt` gets
success=False from send_exec_approval/send_slash_confirm (run.py's text
fallback takes over — same contract as a failed native button send) and
the base numbered-text clarify; `react` silently no-ops.
- docs/relay-connector-contract.md §4: prompt / prompt_response / react
semantics (callback token, budgets, authorization-parity, foreign-id
behavior, per-platform react mappings).
- tests: tests/gateway/relay/test_relay_interactive.py (19) — option-set
rendering + gating matrices, registry consume-once/expiry, resolver
routing for all three kinds (monkeypatched primitives), fall-through
cases, Discord hp1 decode + foreign-id shape, react lifecycle
(success/failure/cancelled), op-gated/best-effort react.
Cross-repo pair: gateway-gateway 'Phase 3 interactive' PR (prompt/react
senders on all four lanes + interaction ingest).
- gateway/relay/media.py: RelayMediaClient for the connector's /relay/media
plane (upload local files → re-host reference for send_media; download
re-hosted inbound attachments → local temp paths). Same connector base URL
the WS dials, same per-gateway signed bearer as the upgrade (auth.py) —
no new configuration. stdlib urllib in a thread executor (no new deps);
25MB cap mirroring the connector's MEDIA_MAX_BYTES.
- RelayAdapter: send_image / send_image_file / send_voice / send_video /
send_document overrides route through ONE send_media op (media by
reference: local paths upload first, public URLs pass through). Gated on
supported_ops advertising send_media — legacy connectors keep today's
text fallbacks; connector declines/failed uploads degrade the same way.
Scope/user egress discriminators ride metadata exactly like send.
- Inbound: _localize_inbound_media downloads each media_urls entry to a
local temp path (native-adapter parity — vision/file tools consume
paths); dead re-host refs are dropped, public URLs survive a missing
client. Best-effort, never blocks handle_message.
- docs/relay-connector-contract.md §4: send_media op row + media
ingress/egress semantics (replaces the 'deferred to a later revision'
note). Additive within contract_version 1.
- tests: tests/gateway/relay/test_relay_media.py (15) — kind mapping,
upload-first path handling, op gating (explicit + legacy-empty),
decline/upload-failure fallbacks, scope metadata, inbound localization
matrix, client URL derivation/credential gating. Stub connector grew a
canned send_media result.
Cross-repo pair: gateway-gateway 'Phase 2 media parity' PR (re-host plane +
four ingress lanes + four platform send_media senders).
Complements the task-granular background_work with the async-delegation
UNIT count (each dispatch/batch = 1), recovering the pool-slot semantics
active_count() gives. Together: background_work = real concurrent subagent
load (batch expanded), background_delegations = slot pressure to alert
against delegation.max_concurrent_children. Registered in metric_names,
documented, and covered by a task-vs-unit contract test.
A delegate_task fan-out batch occupies ONE async-pool slot by design, so
active_count() (unit/slot count) reports a 3-task batch as 1 — which
undercounts real concurrent subagent load on the background_work metric.
Add active_task_count() that expands a running batch to its child count
(N-task batch -> N, single -> 1) and switch the background_work reader to
it. active_count() is unchanged (capacity semantics preserved). Adds a
contract test for the unit-vs-task distinction and documents both counts.
Document hermes.gateway.background_work in the export table, and add a
'Maintaining and extending this plane' section: the content-free
invariant, and per-change checklists for adding a metric, a new
subsystem, extending the error-class/status/source/state enums, and
adding a content-free span attribute. Each calls out the layers that
silently drop an undeclared signal (observable metric_names registration,
the emitter keep_by_kind allowlist, the closed enums, and any collector
name/keep_keys allowlist) plus whole-chain verification.
Salvages the event-spine foundation from feat/telemetry-observability
(emitter, typed events, OTLP streaming, redaction — authorship preserved in
the preceding commits) and scopes it to the plane enterprise operators need
today: gateway Service Health Monitoring plus redacted Operational
Diagnostics, exported over OTLP.
Dropped from the salvaged branch, deliberately:
- run/model/tool trajectory capture (plugins/telemetry hooks, tel_spans)
- the local JSONL + state.db tel_* store (monitoring is egress, not storage)
- usage rollups/metrics, /insights integration, bulk export
- hermes telemetry CLI (replaced by hermes monitoring status)
Those planes — shared client usage metrics and enterprise trace telemetry —
are being designed on the NeMo Relay integration with distinct consent,
policy, and export boundaries; this keeps the monitoring plane content-free
and independently enableable.
Renames agent/telemetry -> agent/monitoring, config telemetry.* ->
monitoring.*, and pins the otlp extra at OpenTelemetry 1.39.1 (matching
uv.lock; 1.30.0 conflicts with mistralai>=2.4 on opentelemetry-api).
Match the docs to the code after the dead-schema cut and span layer:
- List the actual tel_* tables (runs, spans, model_calls, tool_calls,
error_events) instead of a vague "indexed tel_* tables".
- Add a "Traces and spans" section: a run = one session, each call is a child
span under the run root in tel_spans keyed by span_id, reconstructable as a
connected run -> calls tree. Note subagent cross-run lineage isn't recorded.
- Fix stale "tool failure rates by category" -> "by tool" (categories were
removed; insights groups by raw tool name).
- OTLP: state plainly that events export as per-event spans and the tel_spans
parent/timing linkage isn't reconstructed into connected SpanContexts yet,
matching the exporter's own docstring.
- README: "telemetry plane" -> "telemetry system" (stale rename miss); mention
spans.
Config reference verified to match DEFAULT_CONFIG exactly (9 keys).
Rename the telemetry tiers away from the borrowed control-plane/data-plane
jargon to plain language, across code, CLI output, config, and docs:
- "local plane" -> "local telemetry"
- "aggregate plane" -> "aggregate metrics"
- "trajectories plane" -> "trajectories" / "telemetry.trajectories"
- "three planes with a hard wall" -> "three settings, isolated from each other"
User-facing `hermes telemetry status` now reads "Local telemetry: on" /
"Aggregate metrics: off" / "Content export: off (trajectories disabled)".
The OTLP resource attribute key telemetry.plane is renamed to telemetry.scope
(wire-level identifier; nothing consumes it yet).
No behavior change — wording only. Status renders identically apart from the
labels; tests updated to match the new strings.
Add a built-in telemetry system that records what the agent does — workflows,
model calls, tool calls, errors — to the local machine, powers `/insights`, and
can export to an operator-chosen destination. Default-on locally; nothing leaves
the machine unless the user exports it or opts into the aggregate plane.
Three planes with a hard wall between them:
- local: full-fidelity observability (real model/provider/tool names), on by
default, never leaves the machine.
- aggregate: opt-in metadata, default off. No uploader ships — consent is
recorded via telemetry.consent_state, and `preview` shows what would be
produced, computed locally.
- trajectories: full message content, opt-in, exported only to the operator's
own destination.
Mechanism:
- Bundled `telemetry` plugin registers observational lifecycle hooks
(on_session_start / post_api_request / post_tool_call / on_session_finalize).
No core call sites are edited; hooks already carry the data.
- Fire-and-forget emitter: emit() returns in microseconds, never blocks or
raises into a model/tool call. A daemon thread writes events to an
append-only JSONL log and the tel_* tables in state.db (its own sqlite
connection, separate from SessionDB).
- tel_runs / tel_model_calls / tel_tool_calls live in the declarative
SCHEMA_SQL and are reconciled automatically; SCHEMA_VERSION 16 -> 17.
- metrics derives rollups for /usage and /insights; rollup builds per-run
summaries for `hermes telemetry preview`.
Consent is config, not a parallel command surface. The config file is the root
of trust: set telemetry.consent_state with `hermes config set`, or pin any
telemetry.* key (including allow_aggregate) via managed scope, which overrides
the user's value per key. `hermes telemetry` exposes only what config cannot:
status (report), preview (query), and export.
Export:
- exporter_bulk writes telemetry (and, when the trajectories plane is enabled,
session content) to ndjson/json.
- otlp_exporter streams spans to a configured OpenTelemetry Collector over
OTLP/HTTP. The SDK is an optional extra (hermes-agent[otlp]), lazily
installed via tools.lazy_deps on first use.
- Secrets are always redacted on every export path
(redact_sensitive_text(force=True)); content export is gated by the
trajectories plane, and PII scrubbing follows telemetry.content_redaction.
OTLP auth headers reference environment variable names, never inline values.
No outbound emission to Nous. The aggregate uploader is intentionally not built.
The base class spawns _keep_typing for every adapter — a 2s refresh loop
that runs for the whole turn, including while the stream consumer sends
the response — but RelayAdapter inherited BasePlatformAdapter's no-op
send_typing. The loop ran every turn and emitted nothing, so relay-fronted
chats (hosted Discord/Telegram/Signal/Slack) never showed 'is typing…'.
The rest of the pipe already existed on both sides: OutboundOp "typing"
is in the wire contract (contract_version 1), and every connector-side
sender implements it (Discord POST /channels/{id}/typing, Telegram
sendChatAction, Signal sendTyping, Slack assistant status).
This bridges the tick onto the existing outbound frame, mirroring send():
- _with_scope re-attaches the tenant discriminator (metadata.scope_id, or
user_id for DMs) — the connector's routedEgressGuard wraps ALL ops, so
an undiscriminated typing frame is declined like a bare send would be.
- the Phase 1.5 per-frame platform tag routes typing through the platform
the chat lives on for multi-platform gateways.
Best-effort by design: transport errors are swallowed (typing is cosmetic;
the next tick retries), no transport is a silent no-op, and stop_typing
stays the base no-op (platform indicators self-expire). Additive within
contract_version 1 — an older connector returns an unsupported-op result
we ignore. Contract doc §4 updated (typing now carries metadata?).
* feat(cli): plan catalog on Free + plan= deep link + top-up/auto-refill copy split
Bring the plain (non-TUI) CLI billing surface to parity with the desktop/TUI
billing changes:
- /subscription on Free (admin/owner, interactive) prints the plan catalog
(name · $/mo · $credits/mo, from the same tiers[] data the TUI uses; monthly
credits render as dollars). A numbered pick opens the manage-subscription
deep-link directly with plan=<tier_id> appended.
- subscription_manage_url(state, tier_id=...) appends plan=<tier_id> (the stable
tiers[] id) when a tier was picked, org_id first — mirrors the TUI's ?plan=.
The paid change flow's blocked/unknown-preview portal fallback carries plan=
for upgrades only; downgrades stay generic/native.
- /topup overview splits one-time top-up from automatic refill, the distinction
stated in each first sentence ("Add funds now — a single charge…" vs "Refill
when low — charges … automatically …"), keeping "credits" out of the
dollars-only surface.
- Downgrades remain native (chargeless scheduled change), unchanged.
Updates the CLI-parity section of docs/billing-lifecycle.md and tests under
tests/hermes_cli + tests/agent.
* refactor(billing): share plan-catalog helpers + harden manage-url builder
- subscription_manage_url now preserves unrelated portal query params (parse_qsl,
popping only the contract-owned org_id/plan) and restricts to http/https schemes,
matching the desktop URL builder — the function owns the contract.
- Lift the plan-catalog derivation into agent/subscription_view.py so the CLI Free
catalog and the paid picker/blocked-preview branch share one implementation:
selectable_tiers (enabled paid, not current, sorted), format_tier_row (name · $/mo
· $credits/mo — thousands-grouped like the TUI's toLocaleString, credits suffix
hidden when absent/zero), and is_upgrade(state, tier_id).
* fix(cli): numbered pick, canonical guarded browser opener, partial auto-refill copy
- Free catalog: accept a bare digit as a pick (the shared normalizer only knows the
confirm-dialog digit aliases, so `1` used to resolve to None → "Cancelled"). The
Nth digit maps to the Nth printed row.
- Extract one _open_url_in_browser used by every "open the portal" path, applying the
device-code flows' console-browser / remote-session guard (webbrowser.open returns
True even for lynx/w3m over SSH) and returning whether a real browser opened.
- Consume the shared selectable_tiers / format_tier_row / is_upgrade helpers from the
Free catalog, the paid picker, and the blocked-preview branch.
- /topup auto-refill copy: the concrete "charges $X … below $Y." sentence only when
both amounts are present and finite; otherwise the generic sentence.
* docs(billing): correct CLI-parity rows (drop cross-repo ref, downgrade invariant)
Remove the other-repo PR reference from the manage-URL row, and state the real
downgrade invariant: a blocked downgrade may print the generic manage URL but never
carries plan=<tier_id> — selected-tier deep-links are reserved for new subscriptions
and upgrades.
* fix(billing): rename user-facing "terminal billing" copy to Remote Spending
The capability was renamed Remote Spending on the portal (consent CTA:
"Allow Remote Spending"; per-terminal states Granted/Stopped), but the
terminal, desktop, and docs still said "terminal billing" everywhere.
- Feature name: Remote Spending in titles/labels, lowercase mid-sentence.
- Step-up action verb is now "allow", matching the portal consent CTA.
- Kill-switch-off recovery copy points at the actual control ("a billing
admin can turn it on from the portal's Hermes Agent page") instead of
the dead-end "manage it on the portal".
- Per-terminal revoke copy uses the portal vocabulary ("stopped").
- Wire identifiers (cli_billing_enabled, cli_billing_disabled, ...) are
unchanged; copy, comments, docs, and test expectations only.
* fix(billing): correct the post-step-up denial diagnosis + finish the desktop rename
Adversarial review findings: (1) a repeated insufficient_scope after a
successful step-up is a per-terminal authorization failure, but the copy
blamed the org kill-switch and pointed at the wrong recovery control —
now: "Remote Spending still isn't active for this terminal — the
authorization didn't take. Retry, or make this change on the portal."
(2) the desktop step-up flow started in Remote Spending vocabulary but
finished in "billing management access" — renamed both end states.
(3) prettier formatting on the touched files (matches the post-merge
fmt bot).
#60194 flipped SessionResetPolicy's default to mode: none, but
cli-config.yaml.example still shipped session_reset.mode: both. Every
install path (install.sh, install.ps1, docker stage2-hook, hermes
doctor) copies the template verbatim to ~/.hermes/config.yaml, so fresh
installs got an EXPLICIT mode: both that overrides the code default —
users hit 24h-idle resets with 'nothing' in their config enabling it.
- cli-config.yaml.example: session_reset.mode both -> none, comments
rewritten to describe auto-reset as opt-in
- docs/session-lifecycle.md: appendix example updated to match
- tests/gateway/test_config.py: invariant tests — template seed, absent
config, and mode-less session_reset block all resolve to mode none;
explicit opt-in still honored
