Adversarial review of the previous commit found a real regression it
introduced, reproduced against the actual code rather than inferred.
Changing _persist_active_ai_config from setdefault("configs", ...) to a
direct assignment made every backend switch write the whole in-memory
AI_CONFIGS over the settings file. Because AI_CONFIGS is now the built-in
defaults merged UNDER the file, that meant:
* an operator's hand edits were destroyed - and hand editing is the only
way to change cheap_model / temperature / max_tokens, since
set_active_model writes latest_model and there is no command for the rest,
* a config deliberately deleted from the file was re-seeded from the
defaults and written back, permanently,
* pinning a model for one provider silently reverted another provider's
entry,
* CONJURER_OLLAMA_MODEL stopped having any effect once the env-derived
block had been persisted once.
The original motivation was still valid (plain setdefault would drop a
pinned model), so the fix is narrower rather than a revert: persist ONLY
the field this process actually changed. _persist_active_ai_config takes
model_for and writes back just that config's latest_model; everything else
in the on-disk block is left exactly as found. The constants.py merge stays
- it is what keeps a newly added provider visible after an upgrade - and is
now in-memory only, so it cannot reach the file.
Tests: the disk-write path had ZERO coverage, which is precisely how this
got in. Added four tests that drive the real _persist_active_ai_config
against a temp settings file: the pin lands while operator edits survive and
a deleted config is not resurrected; a plain switch leaves the configs block
byte-identical; a pin survives a re-read; a corrupt file does not raise.
Verified they have teeth - reintroducing the regression fails two of them.
Also hardened two weak tests the review caught: the pin test asserted on the
object set_active_model returns, which IS the mutated dict (so it passed
regardless), and the unconfigured-endpoint test monkeypatched OLLAMACLIENT
to None when it was already None, passing vacuously.
Suite: 72 unit + 70 integration green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The bot could talk to OpenAI or Anthropic; this adds Ollama as a third
provider so it can run against models hosted on our own box, and extends
the switch command to pick WHICH model - not just which backend.
Provider: Ollama exposes an OpenAI-compatible /v1 surface, so the client is
just openai.AsyncOpenAI(base_url=OLLAMA_URL + "/v1"). That reuses the
existing message format and the whole _map_openai_error mapping instead of
forking a second error taxonomy. There is no API key - the endpoint IS the
configuration, so the backend stays dormant (and refuses to be selected,
with a message naming the variable) until CONJURER_OLLAMA_URL is set, the
same way the Conan bridge behaves.
Model selection:
* list_provider_models() asks the SERVER for Ollama (/v1/models), so the
picker shows what is actually pulled on the box rather than a hardcoded
list. Hosted providers just report what they are wired to.
* set_active_model() pins the config's latest_model and persists it;
cheap_model is left alone so the MUSIC path keeps its cheaper backend.
* $gadaj_teraz now takes "<config> [model]", and a new read-only $modele_ai
lists what is available. Pinning an id Ollama does not have is rejected up
front with the real list - otherwise the typo only surfaces later as a
failed reply.
Two fixes this exposed:
* AI_CONFIGS now merges built-in defaults with the settings-file block
instead of letting the file win outright. Every provider switch persists a
"configs" block, so a file written by an older build would have
permanently hidden ollama from the picker after an upgrade.
* _persist_active_ai_config assigns "configs" instead of setdefault, so a
pinned model actually survives a restart.
* the hardcoded 120s response timeout is now CONJURER_AI_TIMEOUT_SECONDS - a
self-hosted model on a modest GPU can legitimately need longer.
Tests cover: ollama appears in the picker, select_model maps the legacy
gpt-4o default instead of leaking it, model listing (server-queried, sorted,
de-duplicated, failure -> AIError, unconfigured -> auth), pinning (latest
only, blank/unknown rejected), and that provider_generate routes to the new
path. Suite: 68 unit + 70 integration green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
search_bot conflated MAXTHREADS into two jobs at once - how many chunk files to
read (files 0..MAXTHREADS-1) AND how many producer sentinels to wait for - so
the two had to match exactly. Set too low it silently skipped trailing chunks;
set too high (or with any chunk missing/unreadable) a producer crashed before
emitting its sentinel, the consumers' count never reached the threshold, and
search_for_doi hung on join() forever. The idle-timeout failsafe that was meant
to break a starved consumer was dead code: `if empty_counter > 5: ... elif
empty_counter > 10: break` - >10 implies >5, so the elif never ran.
Fix, three layers:
* auto-discover the chunk files present (discover_chunk_files: <n>_chunk.txt in
numeric order) instead of range(0, MAXTHREADS). All files are read regardless
of count, and no producer is ever pointed at a missing file;
* the sentinel threshold is now the number of producers actually started, so it
can't drift from what's emitted;
* producers emit their sentinel in a finally, so even a crash (missing/unreadable
chunk) can't starve the count; and the idle backstop is reordered so it can
actually fire (>EMPTY_LIMIT seconds) as a last resort.
MAXTHREADS is deprecated and unused (kept only so old env files don't break);
docs/env updated to say chunk files are auto-discovered.
For the reported case (MAXTHREADS=40, files 0..43): before, files 40-43 were
silently never searched, and any run that referenced a missing chunk hung
forever. After, all 44 are searched and it always terminates.
Verified in a pytest-only venv (tests/unit/test_search_bot.py): DOI in a
trailing chunk is found; an unreadable chunk still terminates; empty dir returns
at once; discovery is numeric-sorted. Full unit job 27 passed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The Python half of the short-lived share links lived in the repo; the Apache
config and the cron entries that make it work were hand-placed on the host, so
the feature could not be rebuilt from a checkout. This adds the missing half.
Scripts (defaults unchanged, so existing bare-metal cron keeps working):
* scan_shares.py / revoke_shares.py take their paths from CONJURER_SHARE_*
instead of hardcoding the Pi layout, and create their parent dirs;
* the revoke TTL is now CONJURER_SHARE_TTL_SECONDS. Its --help claimed "2min"
while the code used a hardcoded 3600 - the help text now reports the real,
configured value.
New share service:
* docker/Dockerfile.share - Apache + the two jobs, reusing the same scripts
rather than forking copies;
* docker/share-vhost.conf.tpl - the previously undocumented Apache half.
Three settings are load-bearing and commented as such: +FollowSymLinks (the
shares ARE symlinks), -Indexes (a listing would expose every live token), and
a deny rule for dotfiles (revoke_shares.py keeps .downloads.json - a map of
every live token - inside the served directory);
* docker/entrypoint.share.sh - renders the vhost, seeds the index on first run,
then runs scanner/revoker in sleep loops beside Apache (no cron, so their
output shows up in docker logs);
* compose + env example, incl. the two volumes that MUST be shared with the
musician (it creates the links and reads the index).
docs/deployment/FILE_SHARING.md documents the mechanism, both deployment routes
(docker and existing host Apache), the Discord command, why each Apache setting
matters, verification commands, and the known limitations - notably that a link
nobody ever downloads is never revoked, since the TTL starts at first download.
Verified: scanner and revoker exercised end-to-end against temp dirs (index
built; token recorded from a combined-format log line and the symlink unlinked).
Compose file not validated - no docker on this machine.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wire the bot's AI chat pipeline (ai_functions.handle_response) to talk to
either OpenAI or the Anthropic Messages API, chosen by one active-config
switch. Behaviour on the default "gpt" config is unchanged.
constants.py:
* guarded `import anthropic` + CLAUDECLIENT (mirrors OPENAICLIENT), netrc
machine 'anthropic' / ANTHROPIC_API_KEY;
* CLAUDE_LATEST_MODEL / CLAUDE_CHEAP_MODEL (opus-4-8 / haiku-4-5);
* AI_CONFIGS + DEFAULT_AI_CONFIG loaded from an optional 3rd element of
system_gpt_settings.json (backward compatible - a 2-element file falls
back to built-in defaults, active "gpt"). Single switch: CONJURER_AI_CONFIG
env > settings "active" > "gpt".
ai_functions.py:
* provider_generate() dispatches to OpenAI (unchanged openai_call) or the new
_anthropic_call() (splits system out, alternating messages, max_tokens,
temperature omitted - Opus 4.8 rejects sampling params);
* AIError normalises both SDKs' exceptions into one category set so
handle_response keeps its single set of in-character error replies;
* select_model() reads the active config; legacy "gpt-4o" default auto-maps
to the active provider's model so the switch actually changes the backend;
* set_active_ai_config()/list_ai_configs() with best-effort persistence back
into system_gpt_settings.json index 2.
ai_commands.py:
* $gadaj_teraz <config> hybrid command (Vykidailo-gated) switches backend at
runtime;
* graceful guards when OPENAICLIENT is None: personal assistants (OpenAI
Assistants API) and DALL-E image gen degrade instead of crashing, so a
Claude-only deployment boots.
system_gpt_settings.json: add the configs block (gpt/claude/_template) as the
collection point for future backends. requirements_bot.txt: add anthropic.
bot.env.example: ANTHROPIC_API_KEY + CONJURER_AI_CONFIG. Unit tests cover the
message splitter, model selection, config listing, and error mapping.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
(Re-applied cleanly on top of main: PR #18 was rebase-merged, so the branch
that became #19 conflicted on the already-landed commits. This carries ONLY
the librarian state fix - the sole content difference between that branch
and main - so nothing else is touched or lost.)
The worker threads open cr_results/rr_results/not_in_db/s_results.json in
place ('r+'), crashing with FileNotFoundError in a fresh container. New
conjurer_librarian/lib_paths.py resolves all four under a persistent dir
(CONJURER_LIBRARIAN_STATE_DIR, default /lib_temp_files) and seeds missing
ones with '{}' on import; shared by conjurer_librarian.py and scrape_bot.py
(no circular import). ndb_database/database initialised to {} before load so
a corrupt persisted file degrades to empty instead of NameError. search_bot
/search_bot2 open the DOI DB 'r' not 'r+' so /doi can stay read-only. Docker:
STATE_DIR env + VOLUME, compose mounts /srv/librarian/state:/lib_temp_files.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Permissions post-mortem that motivated this: the musician wrote radio
playlists AS ROOT onto a ROOT-OWNED network share which liquidsoap then
read AS USER 'radio' - chown fails on such shares by design (root squash /
uid mapping), so the radio came up and died on the playlists. The fix is
structural: the playlist WRITER now lives in the same container as the
READER, as the same user, on a local volume. No shared partition, no
chown, no uid mapping.
New: conjurer_betoniarka/betoniarka.py - runs inside the radio container
(started by the entrypoint as user 'radio', port 5005):
- library scan -> all_playlist/hit playlists with LOCAL container paths
(start + every 24h + authenticated GET /rescan)
- bot-facing radio API moved from the musician: /add_to_priority,
/create_priority_playlist, /request_radio_file, /clear_pr_pls,
plus GET /ping (health) and /stream (web page)
- radio_log/persistence tailer forwarding play events to the bot's
/prepped_tracks with the shared API key (bot-unreachable = logged, not fatal)
Musician: pure Discord music player now - keeps /mp3, /update_mp3,
/get_music and the file-share endpoints; all radio playlist writing, radio
paths/env and the tailer removed.
Bot: new CONJURER_RADIO_SERVICE (defaults to CONJURER_FILE_SERVICE so
un-split deployments keep working); radio_commands targets it; separate
'radio' health-gate group on betoniarka /ping (musician group now covers
music_commands + file_search_commands only).
Docker: betoniarka baked into the radio image (python3 + flask/waitress/
requests from Debian debs), port 5005 exposed, entrypoint starts it via
setpriv as 'radio'; data-volume chown is now best-effort with a loud
warning (keep the volume local); docs get the post-mortem + wiring.
Verified: py_compile everything; functional stub tests - rescan writes
local-path playlists, wyszukaj scores and appends to priority, auth
401/ok, tailer forward carries the API key.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The cog did its own netrc read from a hardcoded /home/pi/.netrc at import
time, crashing on any other host. Now:
- constants.py: ASSEMBLYAI_API_KEY resolved like every other token
(env ASSEMBLYAI_API_KEY -> netrc machine 'assemblyai' at
CONJURER_NETRC_FILE); new TRANSCRIPTS_PATH (env
CONJURER_TRANSCRIPTS_PATH, defaults next to the log file, created by the
runtime layout)
- voice_recognition_commands.py: drop the hardcoded netrc read and
transcript dir; when the key is missing raise a clear RuntimeError so
the guarded loader disables ONLY this cog with a readable reason
- bot.env.example: document ASSEMBLYAI_API_KEY
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Containerises the three services (each intended for its own Proxmox VM)
and adds the code changes needed to run cleanly on Linux/Docker.
Code fixes:
- constants.py: CONJURER_DATA_DIR roots all writable bot state under one
mounted volume (per-variable overrides still win; native Pi unaffected)
- conjurer_librarian/search_bot.py + scrape_bot.py: the hardcoded Windows
DOI database path (C:\Database\chunks\) is now CONJURER_LIBRARIAN_DB_PATH,
with CONJURER_LIBRARIAN_MAXTHREADS / _CHUNK also env-overridable
Docker:
- docker/Dockerfile.{bot,librarian,musician} + compose.{bot,librarian,musician}.yaml
- docker/env/*.env.example (force-added; real *.env stays gitignored)
- docker/entrypoint.bot.sh seeds default JSON state into /data only when
absent, so preserved history is never overwritten
- .dockerignore
- docs/deployment/DOCKER_PROXMOX.md: step-by-step runbook incl. preserving
the existing command/conversation history and cross-VM auth
The bot image uses the vendored yt_dlp/spotify_dl forks (they win on
sys.path over the pip packages), dropping the old sed patching.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
gitea
Michal Tuszowski