Commit Graph

19 Commits

Author SHA1 Message Date
Teknium b167e81750 fix: legacy Bot Mode section in SOUL.md no longer taxes every session or shadows the live roster
Older desktop builds appended a frozen "## Messaging other agents" section (roster
included) to SOUL.md. Since the server started injecting the live section into Bot Chat
sessions, that copy did two wrong things: every CLI/TUI/messenger session paid ~600 tok
for a bot-only protocol, and in Bot Chat itself the probe went silent when SOUL carried
the heading, so bots saw the stale roster instead of the live one.

- load_soul_md strips the legacy section at read time (covers un-migrated profiles and
  the ambient-home edge cases the same way the SOUL isolation fix does)
- bot_mode_probe drops the SOUL-carries-heading suppression; a SOUL-era stored Bot Chat
  prompt now counts as legacy and is upgraded once (stamped, so it cannot loop)
- config migration v41 rewrites SOUL.md across the default + every profile once
2026-09-06 13:08:31 -07:00
Teknium 7a33369e81 simplify(compat): interrupt — drop _ThreadAwareEventProxy/_interrupt_event legacy alias, repoint 2 test files
No runtime consumer read the proxy (terminal_tool/environments call is_interrupted()/set_interrupt()
directly); its only users were tests patching tools.interrupt._interrupt_event, which had no effect on
the code under test. tools/terminal_tool.py's own re-export of the name is owned by another worker.
2026-09-03 14:00:59 -07:00
Teknium c93ace77c2 simplify(compat): config/runtime_provider/plugins/commands/secrets_cli/kanban — drop 96 re-exports (incl. PEP 562 facades) + 3 aliases (get_pre_tool_call_directive/_block_message, get_telegram_handler_factories), repoint 56 callers + 50 test files 2026-09-03 14:00:17 -07:00
Teknium 8b74aa07a4 refactor(hermes_cli): group B — docstring compaction, provider scalar-field table, config mirror _items helper, regex kebab collapse 2026-09-02 21:03:13 -07:00
Teknium 6121fefb78 refactor(hermes_cli): config_migrations — declare default-flip steps inline in MIGRATIONS via _rewrite_stale_default/_rewrite_key partials 2026-09-02 20:57:06 -07:00
Teknium e4a149a64f refactor(hermes_cli): group B — _rewrite_key generalization (v31/v35 fold), _put in provider normalizer, dedup loop flatten, gateway configured-dict; AST-neutral layout hug/pack 2026-09-02 20:47:14 -07:00
Teknium e3d78021f3 refactor(hermes_cli): codex_runtime_switch synonym table + _migration_lines; context_switch_guard/credential_lifecycle defensive collapse + doc compaction; config_defaults drop key-restating section comments (values byte-identical) 2026-09-02 20:31:42 -07:00
Teknium 251afce10c refactor(hermes_cli): config_migrations — shared _commit/_dict_at helpers, early returns, extracted plugin scan; compact step comments 2026-09-02 20:14:02 -07:00
Teknium 5d4b97939e refactor(hclib): config — config/config_migrations/tools_config/toolset_* dispatch tables and dedupe 2026-09-02 14:42:18 -07:00
Teknium c2954c8934 feat(model-catalog): picker catalogs refresh every 20 minutes, gateway keeps them warm
The /model picker's remote catalogs (curated manifest, OpenRouter live
filter, Nous Portal recommendations) only refreshed when someone opened
the picker on a stale cache, with a 1h TTL. A delisted model (tencent/hy3:free
after the free promo ended) or a newly published one could sit stale for
an hour after the manifest deploy, and indefinitely in a gateway nobody
opened /model in.

- model_catalog.ttl_minutes: 20 replaces ttl_hours: 1 as the default;
  an explicitly set legacy ttl_hours is still honoured.
- model_catalog.refresh_catalogs() force-refreshes all three sources to
  disk; refresh_interval_seconds() exposes the cadence.
- Gateway spawns a supervised _model_catalog_refresh_watcher that calls
  it off-thread every TTL window, so every surface on the machine reads
  a cache no older than 20 minutes.
- Config migration v39→v40 drops the old ttl_hours: 1 default only.
- Docs: reference/model-catalog.md updated.
2026-09-02 06:16:54 -07:00
Teknium 76e306c458 refactor(tools): remove expired BFL FLUX 3 promo core tools (migration v39); FLUX 3 stays via video_gen/FAL for subscribers (#94599)
* refactor(tools): remove expired bfl_flux3_* promo tools; FLUX 3 rides the video_gen provider surface

* test: relay-cutover migration asserts >= v38, not the version literal
2026-08-25 02:45:10 -07:00
fangliquanflq 3963fc6f21 fix(config): stop reporting stripped v15 defaults
(cherry picked from commit 4c6b67ec371b16c15e9ffbb91bfb47a504e913fe)
2026-08-24 03:20:28 -07:00
Bryan Bednarski 3fad83df31 fix(relay): guard native plugin ownership cutover
Signed-off-by: Bryan Bednarski <bbednarski@nvidia.com>
2026-08-19 08:52:03 -07:00
Teknium ce996d4057 feat(delegation): raise max_concurrent_children default 3 -> 10 (+migration) (#86745)
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>
2026-08-15 00:20:32 -07:00
Teknium 50d98fc1f3 feat(delegation): raise subagent iteration cap default 50 -> 250 (+migration) (#86506)
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.
2026-08-14 16:50:30 -07:00
Teknium 1c971769ec feat(gateway): concise background process notifications by default
Background process completions on messaging platforms now default to a
one-line status message (✅/❌ + command + duration; failures append a
short output tail) instead of dumping the raw output buffer into the
chat. New display.background_process_notifications mode 'concise' is
the default; 'all' keeps the old raw-dump behavior for anyone who wants
it. Config migration v35 moves users still on the old implicit default
'all' to 'concise' on their next update; explicit result/error/off
choices are preserved.
2026-08-14 00:26:11 -07:00
Teknium 244d296646 fix(personality): single-owner personality state + one-time reset migration
Personality persistence used to be split per surface: the TUI/desktop wrote
the NAME to display.personality while the CLI/gateway wrote rendered TEXT
into agent.system_prompt (and their /personality none only blanked the
text, leaving the name behind). When #81946 made display.personality
authoritative everywhere, stale names written long ago resurrected
personalities users had turned off - kawaii defaulting on after updating.

- hermes_cli/personality.py: new single owner of personality state.
  Built-in personality definitions, neutral-name normalization, rendering,
  availability (built-ins overlaid by agent.personalities), overlay
  resolution, and the ONLY sanctioned persistence path
  (persist_personality -> display.personality; never agent.system_prompt).
- v34 config migration: one-time reset of display.personality to none
  (announcing which personality was cleared and how to re-enable), plus a
  scrub of agent.system_prompt when it verbatim-equals a known personality
  render (machine-written by the old CLI/gateway). Hand-written manual
  prompts are never touched.
- All surfaces rewired through the module: CLI /personality (incl. active
  marker in the list), gateway /personality, TUI config.set + slash path
  (which previously applied without persisting), TUI config.get (reports
  the EFFECTIVE personality), completer, hermes config display, and the
  tui_gateway health probe.
- cli.py/config duplicates removed: built-ins now defined once; the
  desktop mirrors them from one lib module (src/lib/personalities.ts).
- Docs updated: selection lives in display.personality, built-ins always
  available, one-time reset note.
2026-08-09 10:33:58 -07:00
teknium1 4b33e5663b refactor: config auto-migration support floor at v12 + deprecated shim retirement 2026-07-29 16:44:31 -07:00
teknium1 326764e255 refactor: table-driven config migration registry (17 if-blocks → (version, fn) table, byte-identical semantics) 2026-07-29 10:14:32 -07:00