Three state-loss bugs at the compression rotation boundary, fixed together
because they all live in the same ~80-line rotation block:
- #33618: a persistent /goal did not follow the rotation. load_goal does a
flat per-session lookup with no lineage walk, so a goal silently died when
compression minted a fresh child id. Added migrate_goal_to_session() and
call it after the child session is created (move-not-copy: the parent row
is archived as cleared so exactly one active goal row exists).
- #33906/#33907: if the child create_session raised (FK constraint,
contended write), the outer handler only warned and let the agent continue
on the NEW id — which has no row in state.db — producing an orphan session.
Now the rotation rolls agent.session_id back to the still-indexed parent
(reopening it) instead of stranding the conversation on a phantom id.
- #27633: the compaction-boundary on_session_start notification omitted the
platform kwarg, so context-engine plugins saw source=unknown for every
message after the boundary. Forward platform (matching the initial
session-start call in agent_init.py).
Co-authored-by: denisqq <21260182+denisqq@users.noreply.github.com>
Co-authored-by: zccyman <16263913+zccyman@users.noreply.github.com>
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
The subagent-demotion busy-handler test asserted the internal
merge_pending_message_event call, which the FIFO refactor replaced with
_queue_or_replace_pending_event. Assert the behavioral outcome (the
follow-up lands in the pending slot for the next turn) instead — same
fix already applied to the two steer-fallback tests.
When the agent is busy and the user sends multiple text follow-ups, the
interrupt-mode and steer-fallback path stored them via
merge_pending_message_event(merge_text=True), which newline-joins
consecutive TEXT messages into a SINGLE pending turn — collapsing two
separate user messages into one mashed-together turn and destroying the
message boundaries the user sees (#43066 sub-bug 2).
Route that storage through _queue_or_replace_pending_event (the same FIFO
infrastructure used by busy queue-mode and /queue) so each follow-up gets
its own next-turn slot in arrival order, while still preserving
photo-burst / album merge semantics for media. Pure queue-mode already
used FIFO; this brings the interrupt/steer-fallback path in line.
The sibling defect in #43066 (assistant messages lost after compaction)
was already fixed on main by the identity-tracking flush rewrite (#46053)
plus the pre-rotation flush (#47202), so this only addresses the
remaining busy-message-merge half.
Co-authored-by: KiruyaMomochi <65301509+KiruyaMomochi@users.noreply.github.com>
On Windows, hermes writes writer.bat (@echo off / hermes -p writer %*)
with CRLF endings instead of the POSIX writer shell script. The test
hardcoded the POSIX path and exact bytes, so it failed on Windows hosts.
Assert on stripped non-empty lines per platform, making it line-ending-
and OS-independent.
Follow-up to the salvaged worktree-materialization fix. When a worktree
task has no explicit workspace_path, resolve the anchor from the board's
default_workdir (a git repo) and materialize <repo>/.worktrees/<id> per
task, instead of silently rooting under the dispatcher's CWD (whatever
directory launched the gateway, e.g. the Hermes checkout). If no
default_workdir is configured, raise with a clear message rather than
guessing from CWD.
Adds AUTHOR_MAP entry for the salvaged commit.
The dispatcher treated workspace_kind=worktree as metadata only and never
ran 'git worktree add', so every worktree task ran in the main repo checkout
instead of an isolated worktree — concurrent tasks silently shared one tree
and contaminated each other.
This materializes a real linked worktree at <repo>/.worktrees/<task_id> on
branch wt/<task_id> when resolve_workspace() handles a worktree task, treats a
repo-root workspace_path as shorthand for that location, persists the derived
workspace/branch back onto the task row, and — on rerun/redispatch — detects an
already-materialized linked worktree (via git-common-dir) and reuses it instead
of nesting a second .worktrees/<id> inside it.
Follow-up for salvaged #49654: unit tests for resolve_whatsapp_bridge_dir()
(writable passthrough, read-only mirror, existing-mirror reuse) and the
AUTHOR_MAP entry for the contributor.
Add a regression test for #47868 asserting convert_messages strips the
internal per-message timestamp field, plus the identity-return path for
timestamp-free message lists. Map x7peeps for the release attribution gate.
When the auxiliary summary call fails with an authentication/permission
error (HTTP 401/403), context compression now ABORTS and preserves the
session unchanged instead of rotating into a child session with a
placeholder summary.
Before: a 401 (invalid/blocked key, or a token pointed at the wrong
inference host) fell through every transient-error check to 'return
None', and because compression.abort_on_summary_failure defaults False,
compress() took the static-fallback path and rotated the session anyway
(messages N->N). The user landed on a fresh-but-broken session that kept
failing the same way — paying for a full-context API call each turn with
no useful compression.
After: _generate_summary classifies 401/403 as a non-recoverable auth
failure (_last_summary_auth_failure) and compress() aborts on it
regardless of abort_on_summary_failure. A distinct auxiliary summary_model
that 401s still retries once on the main model first (its dedicated creds
may be the only broken thing); the abort only sticks when the main model
itself auth-fails or the fallback also auth-fails. The existing
_last_compress_aborted handling in conversation_compression.py already
skips rotation and emits a warning, so no session rotation occurs.
Tests: TestAuthFailureAborts — 401/403 flagging, compress() aborts despite
flag=False, non-auth failures keep the historical fallback path, and
aux-model auth failure recovers on main without aborting.
When the active provider returns a 401/403 that survives its per-provider
credential-refresh attempt (revoked OAuth, blocked/expired key, or an
account pinned to a dead/staging inference endpoint), the conversation
loop now escalates to the configured fallback chain instead of dead-ending.
Before: the generic failover dispatch fired only for {rate_limit, billing};
auth/auth_permanent fell through to 'switch providers manually' advice and
never called _try_activate_fallback(). A user whose primary credential was
broken kept thrashing on the same dead credential every turn — the main
agent appeared 'stuck in fallback mode' while never actually failing over.
This also affected auxiliary tasks (compression, vision, title-gen), since
auto-resolved aux follows the main provider.
After: a persistent auth failure with a configured fallback chain switches
to the next provider (mirroring the rate-limit/billing failover path),
guarded one-shot per attempt by TurnRetryState.auth_failover_attempted.
When no fallback is configured the behavior is unchanged — it falls through
to the existing terminal handling and provider-specific troubleshooting
guidance.
Tests: test_auth_provider_failover.py — 401/403 classify as auth, the
gating condition fires only with a chain present + guard unset, the guard
blocks repeats, and non-auth (500) errors do not trigger auth failover.
* feat(delegation): single-task delegate_task always runs in the background
The model no longer decides whether a subagent runs in the background — a
single-task delegate_task from the top-level agent is now always dispatched
async, so the parent turn returns immediately and the subagent's result
re-enters the conversation when it finishes.
- run_agent._dispatch_delegate_task (the live model path) forces
background=True for top-level single-task calls; the schema-level
`background` param is ignored.
- A batch (tasks with >1 item) stays synchronous (fan-out can't go async).
- A delegation from an orchestrator subagent (depth > 0) stays synchronous —
it needs its workers' results within its own turn.
- The function-level default is unchanged, so direct Python callers/tests keep
the historical synchronous behavior.
- On async-pool capacity rejection, single-task now falls through to a
synchronous run instead of erroring (the child stays attached for interrupt
propagation; detach happens only on a successful dispatch).
- Schema `background` param marked deprecated/ignored; tool description
updated to state the always-background single-task rule.
* feat(delegation): all delegate_task fan-out runs in the background
Extend the always-background behavior to the full fan-out. A batch is now
dispatched as N independent async subagents (one handle each), instead of
running synchronously. Single task and batch both return immediately; each
subagent's result re-enters the conversation as its own message when it
finishes.
- delegate_task: when background is set, loop over ALL built children and
dispatch each via dispatch_async_delegation; return a combined handle block
(count + per-task delegation_ids). Children the async pool rejects (at
capacity) run synchronously inline and are reported alongside the dispatched
handles, so nothing is silently dropped.
- run_agent._dispatch_delegate_task + registry handler: force background for
any top-level model delegation (single OR batch); orchestrator subagents
(depth > 0) still run synchronously since they need workers' results within
their own turn.
- Removed the v1 'batch async not supported' rejection.
- Tool description updated: BOTH MODES RUN IN THE BACKGROUND.
- Tests updated to assert batch fan-out dispatches each task async (verified
E2E: 3-task batch -> 3 independent completion-queue events).
* fix(delegation): background fan-out joins and returns one consolidated block
Correct the fan-out semantics: a backgrounded batch is dispatched as ONE
async unit (one handle, one async-pool slot), not N independent dispatches.
The unit runs all children in parallel, waits on every one, and emits a
SINGLE completion event carrying the consolidated per-task results. The chat
is never blocked; when all subagents finish, their full summaries re-enter
the conversation together as one message.
- async_delegation.dispatch_async_delegation_batch + _finalize_batch: a batch
occupies one slot; its runner returns the combined {results:[...]} dict and
one event with the full results list is pushed to the completion queue.
- delegate_tool: extract the sync execution+aggregation into
_execute_and_aggregate(); background dispatches it via the batch unit and
returns one handle; on pool-capacity rejection it runs the batch inline.
- process_registry._format_async_delegation: render a consolidated multi-task
block (TASK i/N + per-task summary) when the event carries is_batch/results.
- Tests updated; E2E verified: 3-task batch -> immediate return -> one combined
completion block with all three summaries.
Async-delegation completions (delegate_task(background=true)) and
background-process completions (terminal notify_on_complete) re-enter the
originating session as internal MessageEvents. When the session was busy,
_handle_active_session_busy_message treated them like a user TEXT message and
the default busy_input_mode='interrupt' aborted the active turn (and sent a
'Interrupting current task' ack) — the opposite of the design invariant that a
completion surfaces as a new turn only when idle.
Short-circuit internal events to return False so the base adapter queues them
silently (it already excludes internal events from debounce), cascading them as
the next turn after the current one finishes.
Follow-up to the soft-archive durability fix. Reusing the rewind/undo active=0
flag for compaction-archived turns inherited the wrong search semantics: undo
rows are intentionally HIDDEN from session_search (the user took them back), but
compaction-archived turns must stay DISCOVERABLE — that is the whole point of
Teknium's "searchable / recoverable" requirement. As built, search_messages
defaulted to WHERE active=1, so after in-place compaction the pre-compaction
turns were in the FTS index but filtered out of the default search. (The earlier
"searchable" claim only held for a raw FTS query / include_inactive=True, not
the actual session_search tool.)
Empirically confirmed the gap: search 'HMAC' returned 2 hits before compaction,
1 after (only the summary's mention) — the originals were hidden.
Fix — a `compacted` flag distinct from `active`, giving a 3-way state:
- active=1, compacted=0 → live context (normal)
- active=0, compacted=1 → compaction-archived: OUT of live context, IN search
- active=0, compacted=0 → rewind/undo: OUT of live context, OUT of search
Changes:
- messages.compacted INTEGER NOT NULL DEFAULT 0 added to SCHEMA_SQL. Declarative
_reconcile_columns adds it on existing DBs — no version bump (plain column add).
- archive_and_compact: UPDATE … SET active=0, compacted=1 (was active=0 only).
- search_messages: default WHERE active=1 → (active=1 OR compacted=1), on BOTH
the main FTS5 path and the trigram CJK path. include_inactive=True still
returns everything. The short-CJK LIKE fallback already returns all rows
(no active filter) — unchanged.
- Docstrings on archive_and_compact + search_messages document the 3-way state.
Verified: after compaction, session_search default finds the archived originals
(ids 1 & 4); rewind/undo rows stay hidden by default (recoverable via
include_inactive); live context still excludes both. 322 in-place + hermes_state
tests and 46 session_search tests green; ruff clean. Mutation check: reverting
the search WHERE to active-only fails the new searchable test.
(Surfaced by the question "is search semantic or only FTS?" — answer: session
search is FTS5 keyword/BM25 only, no embeddings over the transcript; semantic
retrieval lives in the optional memory-provider layer. Tracing that confirmed
the active-only filter gap above.)
Teknium review: keeping one durable session id must NOT come at the cost of
destroying history. The prior in-place implementation used replace_messages,
which hard-DELETEs the pre-compaction turns (they also drop out of the FTS
index) — same id, but the original conversation is gone with no recovery path
and the summary becomes the only record. Rotation today is non-destructive
(the old session's full transcript survives under the old id); in-place must
match that durability contract, not weaken it.
Fix: compact in place by SOFT-ARCHIVING, reusing the existing messages.active
flag (the /undo soft-delete mechanic), instead of deleting:
- New SessionDB.archive_and_compact(session_id, compacted): in one atomic
write, UPDATE messages SET active=0 on the live turns, then insert the
compacted set as fresh active=1 rows. Nothing is deleted.
- The insert loop is extracted into a shared _insert_message_rows() helper so
archive_and_compact and replace_messages don't duplicate the 60-line
column/encoding block (extend-don't-duplicate).
- Agent in-place branch calls archive_and_compact instead of replace_messages.
Durability outcome (proven by test + E2E across repeated compactions):
- Live context load (get_messages_as_conversation / get_messages) filters
active=1, so a resume reloads ONLY the compacted set — compaction still
shrinks the live session.
- The pre-compaction turns stay on disk at active=0, recoverable via
get_messages(include_inactive=True) / restore_rewound.
- They remain FTS-searchable: the messages_fts* triggers index on INSERT and
remove on DELETE only — they do NOT key on active, and active=0 is a
content-preserving UPDATE. session_search still finds them.
- Verified across TWO successive compactions: the 1st compaction's originals
are still recoverable + searchable after the 2nd (answers the "no recovery
path after the next compaction" concern directly).
message_count now reflects the LIVE (active/compacted) count, matching the
live load. replace_messages keeps its DELETE semantics (still correct for
/retry, /undo) and gains a docstring note pointing compaction at the
non-destructive method.
Tests: test_in_place_keeps_same_session_id strengthened to assert the 8
seeded originals survive at active=0 alongside the 2 compacted rows AND stay
FTS-searchable. Mutation check: swapping archive_and_compact back to a hard
DELETE fails the test, so the non-destructive contract is bound. 285
hermes_state + in-place tests green; rotation/persistence/compress-command/cli
suites green; ruff clean.
Parallel 3-reviewer cleanup of the in-place compaction code. Findings applied:
- perf: in-place mode no longer pre-flushes current-turn messages. The flush
ran INSERTs that the immediately-following replace_messages(compressed)
DELETE+reinsert discarded -- pure wasted writes per compaction. The
current-turn tail survives via the compressor's compressed output
(protect_last_n), not the flush. Verified no data loss; rotation still
pre-flushes (its old session row is preserved, so the flush is real there).
- quality: hoist the two shared post-write steps (update_system_prompt +
_last_flushed_db_idx = 0) below the if/else -- they ran in both branches
against agent.session_id. Removes the easiest divergence bug.
- quality: compute the compaction-boundary locals (_old_sid, _is_boundary,
_boundary_parent) ONCE instead of recomputing locals().get('old_session_id')
and the "_old_sid or agent.session_id or ''" chain three times.
- quality: initialize compacted_in_place up front and assign
agent._last_compaction_in_place directly, dropping the fragile
locals().get('compacted_in_place') reflection.
- reuse: parse the in_place config flag with utils.is_truthy_value (the
project's canonical truthy coerce) instead of a hand-rolled
str().lower() in {...} (agent_init already imports from utils).
Dropped as false positives / out of scope: gateway getattr of agent internals
(established session_id pattern), dual result-dict carry (mirrors history_offset
etc.), stringly-typed "compression" (codebase-wide convention, no constant).
Behavior-preserving: 7 in-place tests (incl. 2 new flush-guard tests) + 26
rotation/boundary/persistence/command tests green; mutation check confirms the
durable-replace guard still binds (removing replace_messages fails the test);
ruff clean. Added test_in_place_skips_redundant_preflush /
test_rotation_still_preflushes to guard the perf change.
Review (Codex + 3-agent parallel) found the first cut of in-place mode was
incomplete: it only updated the system prompt, so the persisted transcript
stayed 'full history + summary' and the next turn/resume reloaded the full
history and immediately re-compacted (a loop), and every downstream layer
that keyed off session-id rotation silently no-op'd. The session_id was
doing double duty as the 'compaction happened' signal. This wires the whole
path so removing rotation is actually complete:
Agent (agent/conversation_compression.py):
- In-place now DURABLY replaces the transcript: replace_messages(session_id,
compressed) on the same row (the canonical store the gateway reloads from),
not just update_system_prompt. Resume reloads the compacted set; no loop.
- Reset flush identity/cursor (_last_flushed_db_idx=0, _flushed_db_message_ids
cleared) so next-turn appends diff against the compacted transcript.
- Expose a rotation-independent signal: agent._last_compaction_in_place, and
in_place=True on the session:compress event.
- Fire the compaction-boundary hooks (context-engine on_session_start, memory
manager on_session_switch, reason='compression') in BOTH modes — in-place
passes the same id as parent so DAG/buffer state still checkpoints. Without
this, memory/context plugins miss every in-place compaction.
Gateway auto-compress (gateway/run.py):
- Read agent._last_compaction_in_place; set history_offset=0 on rotation OR
in-place (both return the compacted set, so slicing past the pre-compaction
length would drop everything). Carry compacted_in_place in the result dict.
- No extra rewrite needed: the agent shares the gateway's SessionDB, so its
replace_messages already updated the canonical store load_transcript reads.
Manual /compress (gateway/slash_commands.py):
- The throwaway /compress agent has no _session_db, so rewrite_transcript is
the durable write. Previously gated behind 'if rotated:' which treated
'id unchanged' as the #44794 data-loss failure case and SKIPPED the rewrite
— making /compress a silent no-op in in-place mode. Now rewrites on rotated
OR in_place; the data-loss guard still fires only for the genuine
no-rotation-AND-not-in-place failure.
Hygiene auto-compress already writes _compressed to the same id
unconditionally (its agent has no _session_db, can't rotate) — correct for
in-place, no change.
Tests (tests/run_agent/test_in_place_compaction.py):
- Assert the DURABLE transcript IS the compacted set after reload
(get_messages_as_conversation == compacted), message_count==2, flush
identity reset, and the rotation-independent signal set on in-place /
unset on rotation. Rotation regression guard unchanged.
Verified: 64 tests green across in-place + rotation/persistence/boundary/
concurrent/failure-sync/command/cli suites; E2E both modes (durable replace,
gateway offset=0, rotation preserves old transcript); ruff clean. Still
default-off.
Context compression today rewrites the message list AND rotates the
session id — it ends the session, forks a parent_session_id child, and
renumbers the title (name -> name #2). That moving identity key is the
root cause of a whole bug cluster: /goal lost (#33618), pending response
lost at the split (#14238), orphan sessions (#33907), TUI sid desync
(#36777), FTS search gaps + duplicate sidebar entries (#45117), null
continuation cwd (#42228), and title-rename dead-ends (#48989). It also
forced a large defensive apparatus (compression lock, contextvar/env/
logging triple-sync, orphan finalization, gateway SessionEntry
re-propagation, tip projection) whose only job is surviving a
mid-conversation id change.
Add a compression.in_place config flag (default False during rollout).
When True, compaction rewrites the transcript and rebuilds the system
prompt but keeps the SAME session_id: no end_session, no child row, no
title renumber, no contextvar/logging re-sync, no memory/context-engine
session-switch. The conversation keeps one durable id for life, like
Claude Code / Codex. Compaction is lossy by design — the pre-compaction
transcript is summarized away, not archived.
The rotation path is unchanged when the flag is off (moved verbatim into
an else branch). Staged rollout: this PR ships the option behind a
default-off flag for live validation; a follow-up flips the default and
deletes the now-redundant rotation machinery, superseding the 14 open
band-aid PRs in this area.
- hermes_cli/config.py: add compression.in_place (default False), documented
- agent/agent_init.py: resolve the flag -> agent.compression_in_place
- agent/conversation_compression.py: branch compress_context() on the flag
- tests/run_agent/test_in_place_compaction.py: in-place invariants +
rotation regression guard + config default
The pre-flush of current-turn messages (#47202) runs in BOTH modes, so no
boundary data loss. Prompt-cache invariant preserved: the system-prompt
rebuild is the same single sanctioned invalidation that already happens
during compaction — no NEW invalidation. Message alternation preserved.
A nous inference_base_url that fails the host allowlist (e.g. a stale
stg-inference-api.nousresearch.com persisted before the allowlist
existed) was only replaced 'if refreshed_url:' — so when the validator
rejected the URL it left the poisoned value in place. The 'falling back
to default' warning fired but never took effect: every subsequent call,
including the auxiliary compression call, kept hitting the dead staging
endpoint and 401'd.
Reset to DEFAULT_NOUS_INFERENCE_URL when validation returns None at both
refresh sites in resolve_nous_runtime_credentials, so a poisoned
auth.json self-heals on the next refresh. The proxy adapter already did
this correctly; this brings the two auth.py sites in line.
The session-stable system prompt embeds Model:/Provider: identity lines,
but mid-turn failover (try_activate_fallback) swaps the runtime without
touching them, so a fallback model misreports itself as the primary when
asked "what model are you?".
rewrite_prompt_model_identity() rewrites the last occurrence of each line
on _cached_system_prompt when a fallback activates (and back on restore,
byte-identical so the primary's prefix cache still hits). The rewrite is
never persisted to the session DB. _sync_failover_system_message() patches
the in-flight api_messages[0] at all 8 failover sites so the current turn
ships the corrected identity. Cache-safe: the fallback's prefix cache is
cold on a model switch anyway.
Co-authored-by: Hermes Agent <noreply@nousresearch.com>
* feat(setup): Blank Slate setup mode — minimal agent, opt in to everything
Adds a third first-time setup option alongside Quick Setup and Full Setup.
Blank Slate forces ON only what an agent needs to run — provider & model,
the File Operations toolset, and the Terminal toolset — and turns
everything else OFF, then walks the user through opting each capability
back in.
What it does:
- platform_toolsets.cli = [file, terminal] (explicit, authoritative list)
- agent.disabled_toolsets = every other known toolset (web, browser,
code_execution, vision, memory, delegation, cronjob, skills, image_gen,
kanban, …). Applied last in the resolver, so it overrides the
non-configurable platform-toolset recovery that would otherwise re-add
toolsets like kanban — guaranteeing a true blank slate.
- Optional config features off: compression, memory + user-profile capture,
checkpoints, smart model routing, auto session reset.
- Bundled skills default to NONE (reuses the .no-bundled-skills marker);
offers to seed the full catalog.
- Walks through tools / plugins / MCP / messaging, all opt-in.
Proven end-to-end: with the Blank Slate config, model_tools.get_tool_definitions
emits exactly 6 schemas — patch, process, read_file, search_files, terminal,
write_file. Nothing else reaches the model.
Re-enable later via hermes tools / hermes skills opt-in --sync /
hermes setup agent.
Tests: tests/hermes_cli/test_setup_blank_slate.py (8 tests) pin the writers,
the resolver invariant ({file, terminal}), and the 6-schema end-to-end set.
Docs: getting-started/quickstart.md documents all three setup modes.
* feat(setup): Blank Slate fork — finish minimal, or walk through configs
After applying the minimal baseline (provider/model + file + terminal,
everything else off), Blank Slate now presents a choice instead of always
running the full walkthrough:
1. Start with everything disabled — finish now with the minimal agent.
2. Walk through all configurations — opt in to tools, skills, plugins, MCP,
and messaging.
Provider/model and terminal are still configured first either way (the agent
can't run without them). The finish-now path records the bundled-skill opt-out
so future `hermes update` runs don't re-inject skills. The walkthrough body
moved to a separate _blank_slate_walkthrough() helper.
Tests: TestBlankSlateFork covers both branches (finish-now applies baseline +
skill opt-out and skips the walkthrough; walkthrough path invokes it). Docs
updated to describe the fork.
test_telegram_webhook_secret reads telegram adapter source by path; point it
at plugins/platforms/telegram/adapter.py. test_windows_native_support
npm-spawn parametrization referenced gateway/platforms/whatsapp.py; point it at
plugins/platforms/whatsapp/adapter.py.
Salvage of PR #41284 onto current main. Relocates the last 9 inline messaging
adapters (+ satellites: telegram_network, feishu_comment/_rules/meeting_invite,
wecom_crypto, wecom_callback) from gateway/platforms/ into self-contained
bundled plugins under plugins/platforms/<x>/, discovered via the platform
registry. Strips the per-platform core touchpoints from gateway/run.py,
gateway/config.py, hermes_cli/gateway.py, hermes_cli/setup.py, and
tools/send_message_tool.py.
Carries forward the migration fixes (explicit enabled:false honored,
get_connected_platforms forces discovery, plugin is_connected via
gateway.get_env_value, logs --component gateway matches plugins.platforms.*,
matrix hidden on Windows).
Additionally ports config keys main added since the PR base: the matrix
plugin's _apply_yaml_config now also covers allowed_users,
ignore_user_patterns, process_notices, and session_scope (the inline
gateway/config.py matrix block gained these in the 1340 commits the PR sat
open; they would otherwise have been silently dropped on deletion).
`_sent_message_timestamps` (the reply-to-own-message quote cache) used a
`set` evicted with `set.pop()`, which removes an ARBITRARY element — so once
more than the cap (500) outbound timestamps are tracked, a still-recent
timestamp could be dropped while older ones survive, missing a genuine
reply-to-own-message. Convert it to an OrderedDict with FIFO (oldest-first)
eviction, mirroring the recently-hardened echo ring (#31250). This closes the
same bug class on the sibling cache.
Adds a regression test asserting oldest-first eviction + MRU promotion.
The hardened echo ring (#31250) changes _recent_sent_timestamps from a set
to an OrderedDict, so the reply-detection-cache regression test from the quote
salvage can no longer call .discard(); route it through the new
_consume_sent_timestamp() helper, which is the real echo-removal path.
Review follow-up on the salvaged AAC + markdown changes:
- Fix an inaccurate comment claiming the STT layer has a sniff-and-remux
fallback (verified: no such fallback exists; the ffmpeg-absent path caches
raw ADTS and STT may reject it).
- Type the _markdown_to_signal wrapper as tuple[str, list[str]] to match the
shared helper instead of a bare tuple.
- Replace the hardcoded /home/pi/... test fixture with a runtime-generated
ADTS AAC sample so the remux round-trip actually runs in CI (skips only
when ffmpeg is absent) instead of always-skipping.
Android Signal delivers voice notes as raw ADTS AAC frames, which
share the `0xFF 0xFx` sync word with MPEG-1/2 Layer 3 (MP3). The
`_guess_extension` byte-signature test in gateway/platforms/signal.py
was matching both, so ADTS AAC was being misclassified as MP3 — saved
to disk with the wrong extension and rejected by every major STT API
(Groq, OpenAI) because their server-side format sniffers inspect the
actual codec, not the file extension.
Two changes:
1. Tighten the MP3 vs ADTS disambiguator. ADTS packs `ID`,
`layer`, and `protection_absent` into bits 3-0 of byte 1, where
`ID=0` and `layer=00` for AAC. Real MP3 has `ID=1` and
`layer` in {01, 10, 11}. The mask `0xF6` against target `0xF0`
cleanly separates them.
2. Remux raw ADTS AAC to MP4 container at the cache step via
`ffmpeg -c:a copy`. Single demux/remux, no re-encode, no quality
loss, sub-100ms on a Pi 5. The cached file is a normal `.m4a`
that all major STT providers accept. ffmpeg is a transitive
dependency of many other Hermes features (TTS, video skills) so
this isn't a new install requirement; the remux degrades
gracefully to a no-op if ffmpeg is missing.
The new helper `_remux_aac_to_m4a` is unit-tested with a real
Android voice note from the audio cache that originally triggered
the bug, plus synthetic ADTS frames for the byte-level
disambiguator and garbage-input graceful failure.
Closes the gap that broke transcription for any Android Signal user
sending voice messages to Hermes.
Route Signal send paths through shared markdown formatting helpers and render markdown bullets consistently as Unicode bullets. Add coverage for Signal formatting and send_message integration.
The raft platform plugin's check_raft_requirements() logged a WARNING every
time it returned False. Since check_fn is called on every load_gateway_config()
(~every 10s during normal gateway operation), users who don't have the raft
CLI installed get their logs flooded with no way to suppress it — hermes plugins
disable doesn't work for bundled platform plugins, and platforms.raft.enabled:
false doesn't gate the check_fn call.
Fix: make check_raft_requirements() a silent predicate (return True/False
only, no logging), matching the convention documented and used by other
platform adapters (e.g. teams/adapter.py). The caller in
gateway/platform_registry.py create_adapter() already emits its own warning
when requirements aren't met and an adapter is actually requested — that's the
correct place for a user-facing warning (fires once per connect attempt, not
once per config load).
Fixes#49234
When a tool call itself restarts the gateway (docker restart, systemctl
restart, and similar), the process is terminated mid-call — before the
tool result is persisted and before the orderly drain rewind can run. The
transcript tail is left as an assistant(tool_calls) with no matching tool
answer. On resume the model re-issues the unanswered call, taking the
gateway down again — an infinite loop (#49201).
Source fix: _build_gateway_agent_history now strips a trailing
assistant(tool_calls) block that has no tool answers
(_strip_dangling_tool_call_tail), so there is nothing for the model to
re-execute. This complements _strip_interrupted_tool_tails, which only
handles the case where a tool result row exists with an interrupt marker.
Cognitive backstop: the resume-pending system note now states that any
restart command in the history already ran and must not be re-executed or
verified, and the empty-message auto-resume startup turn reports recovery
and asks for instructions instead of the nonsensical "address the user's
NEW message" (there is no new message on that turn).
Reimplements the intent of #49243 by @JoaoMarcos44 at the replay layer.
Fixes#49201
_build_fal_payload and _build_fal_edit_payload assemble the request and then
filter it down to the model's supports / edit_supports whitelist. That filter
also covers prompt (and image_urls for edits), which every FAL endpoint
requires. Today all model configs happen to list those keys, but a single
config that omits one would silently produce a request with no prompt or no
source images — a broken generation with no error.
Always keep the mandatory keys regardless of the whitelist so a missing
whitelist entry can only drop optional knobs, never the prompt or the images.
The god-file Phase 4 refactor (094aa85c37) moved agent construction into
CLIAgentSetupMixin, which set the atexit shutdown reference with a bare
`global _active_agent_ref`. After extraction that global binds the *mixin
module's* namespace, not cli.py's. cli._run_cleanup reads
cli._active_agent_ref to decide whether to fire the memory provider's
on_session_end hook — and it stayed None for the whole session, so the
`if _active_agent_ref:` branch was dead and on_session_end never ran on
/exit. Custom memory providers silently lost end-of-session extraction.
Fix: publish the reference onto the cli module explicitly
(`import cli as _cli; _cli._active_agent_ref = self.agent`), using the
deferred-import pattern already established in the mixin.
Regression test asserts cli._active_agent_ref is populated by the mixin's
publish line and guards against a relapse to the bare `global` form. The
existing shutdown tests passed only because they hand-assigned the ref,
which is exactly what masked this.
Teams overrode send_image/send_image_file but not send_video, send_voice,
or send_document — so when the gateway dispatched a video/voice/document
reply to a Teams chat it fell through to the base-class text fallback and
sent the local file path as plain text (same broken-UX class as the LINE
URL-image gap in #49298).
Extract the existing send_image attachment logic into a shared
_send_media_attachment helper (remote URL by reference, local file as a
base64 data URI, MIME guessed from the path) and route all four media
kinds through it. 5 new tests cover remote-URL, local-file base64,
no-app, and missing-file paths.
Simplify pass on the picker-persist coverage:
- Stub list_picker_providers + resolve_display_context_length so the
tests no longer make real outbound HTTP calls (OpenRouter catalog +
Ollama /api/show) during picker setup and confirmation rendering.
Runtime drops from ~11s to ~0.4s and the tests are now deterministic.
- Collapse the two positive persist cases into one parametrize over the
config seed (nested-dict vs flat-string), asserting the nested-dict
invariant in both.
- Assert the in-memory session override is applied in the --session
case, closing a 'passes for the wrong reason' gap (config untouched
AND the switch still took effect).
- _FakePickerResult -> types.SimpleNamespace.
Mutation re-checked on the final test: both persist cases fail on
pre-fix slash_commands.py; the --session case passes on both.
Add regression coverage for the picker persist fix: drive the real
_handle_model_command with a fake picker-capable adapter that captures
the on_model_selected callback, fire a 'tap', and assert config.yaml is
written (bare /model), left untouched (--session), and that a flat-string
model: is coerced to a nested dict on a tap.
Mutation-checked: the persist and coercion assertions fail on pre-fix
slash_commands.py and pass on the fix.
Auto-generated session titles already rename the Telegram forum topic via
the title_callback path, but the /title command only wrote the session
title to the database. On a Telegram topic lane the visible topic kept its
auto-assigned name, so a user who ran /title to override it saw no change.
Propagate the user-chosen title to the topic by calling the existing
_schedule_telegram_topic_title_rename helper on a successful /title set. It
already no-ops off Telegram topic lanes and when auto-rename is disabled.
MCP Streamable HTTP servers that garbage-collect idle sessions on a short
TTL (e.g. Unreal Engine's editor MCP, ~15s) were unusable: the keepalive
was hardcoded at 180s, so the session was always dead by the time it ran,
and every idle tool call then landed on an expired session and paid the
full reconnect path (observed hangs of 113-143s until interrupt, bounded
only by the 300s tool_timeout).
Two coordinated, backward-compatible changes:
- Add per-server `keepalive_interval` (config.yaml, not an env var per the
contribution rubric). Default 180s — byte-identical to the old hardcoded
value when unset — floored at 5s. Servers with short session TTLs set it
below their TTL so the session stays warm.
- Switch the keepalive probe from `list_tools()` to `ping` (the MCP base
protocol liveness primitive). On large servers `list_tools` pulled ~1 MB
every cycle (830 tools = 1,068,041 bytes); `ping` is ~55 bytes and works
uniformly across tool/prompt/resource servers. Tool-list changes still
arrive out-of-band via notifications/tools/list_changed -> _refresh_tools.
`ping` is an OPTIONAL utility, so to guarantee zero regression for a
tool-capable server that doesn't implement it: the first -32601 latches
`_ping_unsupported` and the probe falls back to the pre-ping `list_tools`
path for that connection (no reconnect loop). The latch resets on each
fresh connection (_discover_tools, all transport paths) so a server that
gains ping support after a reconnect is re-probed with the cheap path.
Non-(-32601) ping errors propagate as genuine liveness failures.
Verified end-to-end against a live Unreal MCP server (idle 22s past the
~15s TTL -> post-idle tool call returns in 0.31s, no teardown) and with a
simulated ping-less tool server driving the real keepalive loop (ping once,
list_tools thereafter, no reconnect). 25/25 unit tests pass.
Note: a separate upstream defect (modelcontextprotocol/python-sdk#2604)
still tears down the whole session when one tool-call POST returns 4xx;
that is not addressed here.
* fix(discord): hydrate channel context when replying to a message
Replying to a message in a free-response (non-mention, threads-off)
channel previously received only the 500-char "[Replying to: ...]"
snippet — the history-backfill gate fired only for mention-gated
channels and threads, so a reply got no surrounding channel context.
Replies now route through the same _fetch_channel_context hydration
that threads use. When the user replied to a specific (often older)
message, a reply-anchored window is scanned ending at that message so
the agent sees the exchange around what was pointed at, even when the
target sits before the self-message partition. The two windows are
merged chronologically and de-duplicated by message id.
Also hardens the recent-window scan to skip non-conversational status
bumps before the self-message partition check, and makes author-name
resolution defensive against partial/deleted authors.
* fix(discord): duck-type reply-target resolution instead of isinstance(discord.Message)
The e2e suite stubs the discord module, so discord.Message is a MagicMock
and isinstance(_resolved, discord.Message) raises 'isinstance() arg 2 must
be a type'. Any object with an int .id works as a scan anchor, so resolve
the reply target by duck-typing on .id and fall back to a _Snowflake from
the reference message_id.
Second review pass (Codex + Hermes subagent). Codex reproduced a real race with
a two-thread harness; both converged on the remaining issues.
- Generation-aware publish (fixes a lost-update race): two refresh callers (the
late-refresh daemon and the between-turns prologue around turn 1) could each
compute a snapshot outside the lock; a SLOWER caller holding an OLDER registry
generation could acquire the publish lock after a newer caller and clobber it,
deleting just-landed tools. refresh_agent_mcp_tools now captures
registry._generation before computing and refuses to publish a stale set;
agent._tool_snapshot_generation tracks the published generation.
- Context-engine routing names (_context_engine_tool_names) are now staged on a
local and published atomically with the snapshot, and only claimed when this
rebuild actually appended the schema — matching agent_init's dedup so a
registry/plugin tool of the same name keeps its own dispatch. (Previously
mutated live, before the publish lock, and on no-change refreshes.)
- CLI /reload-mcp: self.enabled_toolsets is resolved once at startup, so a
server newly ENABLED in config mid-session wasn't picked up (TUI already
re-resolved). Merge now-connected MCP server names into the override (unless
the user pinned all/*), mirroring startup, and keep self.enabled_toolsets in
sync. Closes the CLI/TUI parity hole.
- ACP (acp_adapter/server.py) routed through the shared helper — it was a 5th
sibling rebuild that re-injected memory tools but NOT context-engine tools and
bypassed the atomic/name-diff path (inert today, fragile).
- mcp_startup._resolve_discovery_timeout pulls its default from DEFAULT_CONFIG
(single source of truth) instead of a stale hardcoded 5.0 literal.
- Tests: stale-generation-no-clobber, _skip_mcp_refresh honored, timeout
fallback uses DEFAULT_CONFIG.
Consolidated findings from three independent reviewers (Codex, Claude Code, a
Hermes subagent w/ the hermes-agent-dev skill):
- BLOCKING: refresh_agent_mcp_tools rebuilt only the registry subset, silently
dropping post-build-injected memory-provider (mem0/honcho/…) and context-
engine (lcm_*) tools on every refresh. Now additive-preserving: re-applies
the same injectors agent_init uses, staged on locals and published atomically.
- Re-injection now honors the #5544 enabled_toolsets gate for context-engine
tools, so a restricted-toolset platform can't get lcm_* leaked back in.
- Atomic read-diff-publish under one lock: the returned `added` set and the
(tools, valid_tool_names) pair are consistent even under concurrent callers
(no half-swap, no TOCTOU).
- background_review fork opts out (_skip_mcp_refresh) so its byte-identical
tools[] cache parity with the parent is preserved.
- CLI /reload-mcp routed through the shared helper (was a 4th divergent copy
with the same clobber bug + missing disabled_toolsets).
- Explicit reloads (TUI RPC + CLI) pass enabled_override so a server the user
just enabled in config this session is picked up; automatic paths reuse the
agent's build-time selection.
- mcp_discovery_timeout default 5.0 -> 1.5s: correctness now comes from the
between-turns refresh, so the startup wait is only a small turn-1 UX bump
rather than a heavy dead-server latency penalty.
- has_registered_mcp_tools checks registered TOOLS (not connected servers) so a
zero-tool/prompt-only server doesn't make the per-turn hook fire forever.
- Tests: rewrote the thread-safety test to actually exercise the write path
(alternating tool sets), added the #5544-gate regression, the memory/context
preservation regression, and a "callable next turn via valid_tool_names"
contract; removed a dead monkeypatch line.
A slow MCP server (HTTP/OAuth, 2-6s cold connect) that finishes connecting
after the agent's one-time tool snapshot was uncallable for the rest of the
session. The merged pre-first-turn late-refresh only helps during the dead air
before the user's first keystroke; once a turn starts it bails to protect the
prompt cache, so a user who types before the server connects never gets the
tools without a manual /reload-mcp.
Refresh the snapshot in the per-turn prologue (build_turn_context), before this
turn's first API call assembles tools=. This is cache-safe by construction: the
refresh only ever extends a fresh request prefix at a turn boundary, never
mutates the cached prefix of an in-flight turn. So late tools become callable on
the user's NEXT turn automatically, with no /reload-mcp and no cache cost.
- tools/mcp_tool.py: has_registered_mcp_tools() — cheap guard so sessions with
no MCP servers (the common case) skip the rebuild entirely.
- agent/turn_context.py: call the shared refresh_agent_mcp_tools() helper at the
top of the prologue when MCP servers are registered.
- tests: 3 contract tests through the real build_turn_context (adds late tool;
skipped when no servers; no snapshot churn when unchanged).
.hermes/plans/: SPEC + PLAN documenting the root cause, the cache-safety
constraint, and why the existing fixes (#48403/#41630/#42802) don't close it.
