Apply the existing truncation and checkpoint-order eligibility to marked
state.db image rows before insertion. Keep removed turns out of full,
limited, and model-context reads without changing no-watermark replay.
Preserve conflicting provider payloads for a uniquely proven retained
image row across Undo without restoring distinct removed rows.
Assisted-by: Hermes Agent:gpt-6-sol
Assisted-by: Codex:gpt-6-luna
Review follow-up on #7720 (Greptile P2): the external Notes drawer reads the
same profile-bound MCP inventory as the MCP panel but dropped the
``runtime_scope`` label, so a profile whose runtime scope could not be
confirmed rendered its note sources as inactive/configured with no
explanation. ``/api/notes/sources`` now returns ``runtime_scope`` and the
drawer shows the existing ``mcp_runtime_scope_unavailable`` notice (same key,
no new locale strings) when it is ``unavailable``.
Tests: the skewed-routing unit test now also asserts the notes response
carries ``runtime_scope: "unavailable"`` with its sources inactive.
docs/troubleshooting.md mentions the drawer next to the panel.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Two profiles configuring a same-named MCP server shared one connection and
the MCP settings panel showed another profile's runtime ("Active, N tools"
next to an empty inventory); /reload-mcp stopped every profile's servers and
rediscovered from the process-default config.
- api.profiles._set_hermes_home() is the single writer of the process-profile
home: it records get_process_profile_home() and hands it to Hermes Agent's
hermes_constants.pin_process_hermes_home when available, at startup and on
switch_profile(process_wide=True), so the per-turn HERMES_HOME mirror no
longer makes every turn look like the process profile (bare-name,
cross-profile MCP keys) and the anchor cannot drift from HERMES_HOME.
- Run get_mcp_status/registry reads and /reload-mcp inside
api.mcp_runtime.mcp_runtime_scope(): request profile's Hermes-home override
and secret scope (root included), no os.environ mutation, restored on exit.
- One ledger predicate, ledger_key_serves_view() (owned via
_server_scope_keys/key scope, or adopted via _server_tool_scopes), is shared
by status, inventory and the reload summary. The Agent's launch-profile view
is process-wide and name-indexed, so filter_runtime_status_to_view()
rebuilds connected/tools/status/error from the entries serving the profile:
the root profile never shows a routed profile's connection (nor lets its own
parked failed-spawn task borrow a routed profile's live same-named one).
- Inventory lists only tools in the profile's own registry slot for servers it
configures; responses carry runtime_scope.
- Fail closed when the agent's routing does not match the resolved profile:
hide runtime data (runtime_scope "unavailable", shown as a notice in the MCP
panel, 14 locales) and refuse /reload-mcp.
- /reload-mcp shuts down only the profile's own ledger names (parked
included), drops its own connect cooldown/error entries so a failed spawn is
retried (the wildcard cleared every cooldown; a scoped shutdown only clears
the live keys it tears down), rediscovers under the profile's home and
counts live connections only. The bare wildcard remains for agents without
profile-scoped MCP.
- Signature introspection is centralized (accepts_keywords) and falls back to
the bare call instead of blanking every status; ledger key helpers resolve
to the Agent's tools.mcp_tool_scope when present; tools.mcp_tool is
resolved by full name so stubbed agents still work.
- ARCHITECTURE.md §4.10 and docs/troubleshooting.md document the boundary.
- Tests: agent-free contract (models adoption, parked tasks, cooldowns and the
process-wide root view) and real-Agent integration (fake stdio MCP server,
skips without hermes-agent + mcp SDK).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Keep image-turn context tagging and upstream's typed steer-wrapper cleanup
in the same settlement path. Verify the combined recovery and streaming
behavior against current master.
Assisted-by: Hermes Agent:gpt-6-sol
Count a proved WebUI-owned pending row in the display baseline before
accepting a state.db self-heal. Without assistant output past that turn,
leave pending state for the run journal to restore partial text and the
interruption marker instead of clearing it prematurely.
Assisted-by: Hermes Agent:gpt-6-sol
Assisted-by: Codex:gpt-6-luna
Assisted-by: Claude Code:claude-opus-5-5
When a dead stream is reconciled from state.db, retain the submitted
prompt and attachment in the sidecar while keeping the Agent-enriched
row in model context. Use one parent snapshot for full-session conflict
projection so the sidecar owner is stable across the display merge.
Assisted-by: Hermes Agent:gpt-6-sol
Assisted-by: Codex:gpt-6-luna
Assisted-by: Claude Code:claude-opus-5-5
Record pending-turn proof under caller-owned session locks during normal
runs and credential recovery. Preserve both conflicting provider payloads
for replay, but display one sidecar-owned bubble when row identity and
visible content are unambiguous.
Assisted-by: Hermes Agent:gpt-6-sol
Assisted-by: Codex:gpt-6-luna
Persist trusted pending Agent timestamp evidence before the model call so
session reads, including metadata polls and cold reloads, keep only the
submitted prompt and attachment visible. Preserve conflicting provider
payloads without guessing which copy is newer.
Assisted-by: Hermes Agent:gpt-6-sol
Assisted-by: Codex:gpt-6-luna
Re-review #7165 (nesquena-hermes 2026-09-23T06:21:57Z, CHANGES_REQUESTED).
CORE: a dict-shaped custom_providers[].models mapping (what Hermes Agent's
setup flow writes, e.g. {chat-a: {context_length: 128000}}) was treated as an
allowlist by iterating its keys, collapsing the live /v1/models catalog to a
single saved default while the CLI live-probed the full list. The Agent defines
exactly this contract in hermes_cli/model_switch.py::_models_config_is_allowlist:
a mapping is per-model metadata, NOT a catalog narrow.
Fix (all 3 spec points):
1. api/routes.py::_custom_provider_allowlist_ids: added
_custom_provider_models_discover_is_false(_cp) (mirrors
api.config._provider_discover_allowed / Agent
model_switch_providers.py:557: bool False or string false/no/0,
case-insensitive). In the dict branch, when discovery is NOT explicitly
false, return no allowlist so the live probe returns the full catalog.
Only discover_models: false opts into treating dict keys as a pinned
allowlist. List / JSON-array-string / Python-literal shapes stay plain
allowlists.
2. tests/test_issue3718_live_models_custom_probe.py: removed the
mapping-metadata param that asserted the regression; added two
real-handler tests: test_dict_models_without_discover_false_does_not_gate
(dict -> full _LIVE_CATALOG) and test_dict_models_with_discover_false_pins_to_keys
(bool False / "false" / "no" / "0" -> pinned to keys).
3. docs/architecture/live-models-allowlist.md: documented that list and
string shapes filter, and a dict filters only with discover_models: false.
Companion test update (blocker reported by the fix itself):
tests/test_byok_model_dropdown.py rightcode-codex entry encoded the removed
dict-as-allowlist behavior (models: {"gpt-5.5-mini": {}} asserting the response
collapsed to just that key). Added discover_models: False to preserve the
provider-scoping intent (no sibling leak) under the new contract.
Red/green verified: removing the dict-branch guard turns
test_dict_models_without_discover_false_does_not_gate red (collapsed catalog);
restoring it turns it green.
Verification: 3718 18 passed; byok 24 passed; neighbour sweep (46 files)
520 passed (2 pre-existing order-dependent flakes reproduce identically on
clean HEAD, verified via git stash); ruff curated gate OK.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Addresses the standing documentation finding: records the four evaluation
signals (discovered catalog defers, plural allowlist filters, singular model
never gates, no allowlist shows full catalog), serialized-list shapes, the
empty-allowlist-is-not-configured rule, and the probe-failure fallback.
Registered in docs/CONTRACTS.md per the #7556 precedent.
A unique durable row remains one visible row when its sidecar provider payload is stale. Use the state.db payload for replay, cover repeated recovery, and document the image-turn ownership exception.
Assisted-by: Hermes Agent:gpt-6-sol
Assisted-by: Codex:gpt-6-luna
Greptile's P2 was right: 'upgrade past the sync' had no installable
target. Version audit across core tags: every RELEASED Agent (0.20.5 ->
0.21.1, tag v2026.9.7) still carries ox-alpha-free in the curated floor;
the removal exists only on core main, which self-reports the same
0.21.1 version string as the stale tag — a version number alone cannot
distinguish fixed from unfixed. State that plainly and present the
config allowlist as the only verified workaround until a release notes
the 2026-09-09 catalog sync.
Verified against a real install (core v0.21.0 + live key + endpoint):
- on Agent releases between v0.20.5 and the 2026-09-09 catalog sync,
the delisted ox-alpha-free can STILL be offered — via core's own
live/curated merge AND via _seed_provider_models_from_core() injecting
the installed core's stale curated ids into WebUI's static list.
'Upgrade the Agent past the sync' is the correct guidance, not
'upgrade the WebUI'.
- allowlist precedence re-verified with a real config.yaml on disk
(group == exactly the allowlisted ids).
- note the 4s foreground rebuild budget: first picker open after a cold
start can serve last-known catalog while the live rebuild finishes
out-of-band.
User-visible runtime behavior changed in this PR (live catalog first for
Agent >= 0.20.5, resynced static fallback): document both failure
directions users can now hit — listed-but-failing ids (tier/region gates
on the live endpoint, the #7507 follow-up) and missing new ids on
older-AGENT installs — with the diagnostic (hermes --version + authed
curl of /zen/go/v1/models) and fixes (allowlist precedence, Agent
upgrade). Follows the file's Symptom/Why/Diagnostic/Fix/File-a-bug
format.
AGENTS.md asks for the documentation to move with a runtime-behaviour change, and docs/CONTRACTS.md points at the stable-assistant-turn-anchors RFC for anything that reconciles a live turn with the settled transcript. That is what this change adds, so the rule belongs there.
A new part of the Settlement section says why a preserved live node is not evidence of a running turn, the four facts that have to hold before one is dropped, that ownership is proved from state rather than by comparing two rendered trees, and that only the branches which ADD a turn are gated. It also records the settled-scene half: a prose row that duplicates the final answer, exactly or as a prefix within ten percent of its length, is dropped where both settled renderers take their rows, and live rendering is untouched.
Review follow-up for #7569: change 4 of the live-snapshot perf PR replaced
one quadratic with another. The window-free backward walk is correct, but it
re-walks the raw reasoning transcript's whitespace once per interim event —
on a whitespace-heavy transcript that span is megabytes, and the replay went
~55x slower than master on the production shape the gate measured
(1MB / 20-interim journal: 0.035s master → 1.922s branch).
## Thinking Path
The gate's finding was that the cost is structural, not a tweak: the matcher
consults the *whole* accumulated transcript on every interim event, so any
raw-text rescan of it is O(interim_count x whitespace_span). The fix is the
data-structure change the review asked for — maintain the folded view and the
raw cut offsets incrementally, and match/strip from that indexed state
instead of rescanning the raw buffer.
## What Changed
- `api/streaming.py`: new `_CompactEchoIndex` — an append-only folded index
that records, per non-whitespace character, its raw index. `append` folds a
chunk once (cost proportional to the chunk, never the buffer),
`matches_tail`/`cut_to` compare only the candidate against the folded tail
(O(len(candidate)), no raw walk), `reset` drops the state after the raw
text is truncated. The old raw helpers (`_find_compact_echo_suffix_start`,
`_strip_compact_echo_suffix`) stay as the equivalence oracle.
- `api/routes.py::_run_journal_live_snapshot`: reasoning chunks feed the
index as they are appended; `reasoning_echo_tail_matches` and
`strip_reasoning_echo_tail` consult the index. The strip re-indexes the
truncated transcript so later probes match against it.
- `api/streaming.py` live path: the same swap for the live-stream echo strip.
The three live reasoning buffers (STREAM_REASONING_TEXT, the coalescing
buffer, the per-message segments) each carry a mirrored index, fed on every
append and re-indexed after a strip. The buffer flush resets the buffer's
index with the text it drops, so the index never describes text that is no
longer there.
- `docs/rfcs/webui-run-state-consistency-contract.md`: the echo-match clause
now names the indexed representation and the scaling regression that pins
it.
## Why It Matters
Removing one quadratic by introducing another in the same hot path is the
exact risk the gate flagged — the headline benchmark used a journal shape
where the window-free walk's cost does not dominate, so the aggregate number
still looked like a win. The index keeps the original 8.9x and adds the
scaling guarantee on the shape that was regressing.
## Verification
- Measured on the reproduced shape (1MB whitespace span, 20 interim events):
0.972s → 0.049s. Doubling both span and interim count scales ~2x per step
(x1 0.041s / x2 0.090s / x4 0.175s) — linear, not quadratic.
- Behaviour equivalence: 300 randomized journals (whitespace-heavy,
Unicode, chunked, flagged/unflagged interims) rebuilt with the indexed
implementation and with the raw walk swapped in — sha256 of the canonical
snapshot JSON matched on all 300.
- `tests/test_compact_echo_index.py` (new, 6 tests): oracle equivalence over
2000+ randomized cases, chunked-append equivalence, matches_tail/cut_to
agreement, reset-after-truncation, and two cost probes that fail the raw
walk.
- `tests/test_live_snapshot_echo_scan_scaling.py` (new, 4 tests): the
proportional-scaling regression the review asked for — verified to FAIL on
the pre-fix matcher (14.6x time for 4x rows, the quadratic signature) and
pass on the indexed one.
- Existing echo/journal suites unchanged and green: 19 items across
`test_compact_echo_suffix_linear_scan` / `test_live_snapshot_echo_dedup` /
`test_live_snapshot_single_parse`, plus 66 neighbouring items
(`test_issue1361_cancel_data_loss`, `test_issue2565_reasoning_accumulation`,
`test_issue2713_streaming_segment_flush`, `test_cancel_interrupt`,
`test_run_journal`).
## Contract Change
None. The matcher's observable behaviour is unchanged (same cut points, same
whitespace-insensitive semantics); only its cost profile changes. No config
knobs, no API surface.
## Risks
- Index drift: if a future writer mutates one of the reasoning buffers
without feeding (or resetting) its index, the matcher would silently miss
echoes. Mitigated by keeping the index feed adjacent to every existing
write site and by the reset-on-flush/reset-on-strip symmetry; the
equivalence test would catch a dropped feed as a missed echo.
- Memory: the index stores one char plus one int per non-whitespace
character. On a whitespace-heavy transcript this is bounded by the folded
length, which is what the transcript would cost folded anyway; the raw
text is still the larger object.
## Model Used
Hermes Agent (step-5-preview) with direct file edits and pytest verification.
Cost properties were measured with a purpose-built scaling probe (proportional
span x interim count), not a fixed-size fixture; the probe is kept as a
regression test rather than a script.
## Related
#7569 (this PR), #7310 (slow /api/session under load), #7534 (incremental
journal read cache — complementary), #7273/#7291 (metering write-side skip).
nesquena-hermes