14 Commits

Include renames

Author	SHA1	Message	Date
dgtlmoonandClaude Opus 5.5	be09f73c3a	Restock: let a plugin do LLM price/stock extraction without litellm (HTML + text hook, reusable helpers) (#4545) ... * LLM restock: parse string prices with price_parser instead of stripping separators If the model returns the price as page text, e.g. "1.299,95 €", stripping everything but digits and dots gave 1.29995. price_parser (already a dependency) handles the locale formats the prompt lists. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * LLM restock: use Restock.parse_currency() like the other price extractors Same parser c8afea1b (#4494) moved the structured-data extractors to, so there's one place price text becomes a number. parse_currency() now lists every caller, and the call sites point back to it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * LLM restock: expose prompt/cache/parsing helpers so other LLM backends can reuse them Split the hook body into build_restock_messages(), restock_cache_key/get/put() and parse_restock_reply(), so a plugin talking to a provider without litellm only has to supply the HTTP call. accumulate_global_tokens() takes an optional cost_usd, since the default estimate imports litellm's pricing (~200MB that's never released). The built-in plugin behaves exactly as before. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * Test: give the no-litellm subprocess check a PYTHONPATH CI runs pytest from inside the package dir without installing it, so the child interpreter couldn't import changedetectionio. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * Restock plugins: pass html_to_text() output to the restock hook, let third-party backends go first get_itemprop_availability_override now also gets `text` (the fetched page through html_to_text()), only computed when an implementation declares it. The hook is firstresult and the built-in litellm plugin is trylast, so a plugin that talks to an LLM with plain requests answers first and the built-in one is never billed as well. Also fixes the built-in plugin never receiving llm_intent: pluggy silently doesn't pass hookimpl arguments that have a default value, and it declared llm_intent=None. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-19 12:32:32 +02:00
dgtlmoonandClaude Opus 5.5	7ec79fc231	LLM restock: fix locale-formatted string prices (1.299,95 read as 1.29995) (#4544) ... * LLM restock: parse string prices with price_parser instead of stripping separators If the model returns the price as page text, e.g. "1.299,95 €", stripping everything but digits and dots gave 1.29995. price_parser (already a dependency) handles the locale formats the prompt lists. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * LLM restock: use Restock.parse_currency() like the other price extractors Same parser c8afea1b (#4494) moved the structured-data extractors to, so there's one place price text becomes a number. parse_currency() now lists every caller, and the call sites point back to it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>	2026-10-13 11:21:06 +02:00
dgtlmoon	a165df2da9	LLM UI - When LLM is disabled, hide it from the groups settings also (#4471)	2026-09-20 15:54:41 +02:00
dgtlmoon	97317398ac	LLM - Per watch/group settings and UI tidyup (#4354) ... * UI - LLM section tidyup * Rebuild translatiosn * UI - Fixing language for prompt adjustement to be more clear * UI - clarify field action * UI - clarify layout for sections * WIP * test tweaks	2026-09-02 10:07:34 +02:00
dgtlmoonandClaude Opus 5	143a0f116f	fix(llm): handle reasoning blocks that aren't a well-formed <think>...</think> pair (#4349) ... Follow-up to #4340. The <think> stripper added there only matches a closed pair, but a reasoning scratchpad routinely contains JSON of its own ("initially I thought {"important": false}, but..."), so any leftover scratchpad lets _extract_json lock onto a discarded intermediate answer. Three shapes slipped through, all of which inverted the verdict to important=false and therefore silently suppressed the notification: - opener stripped by the provider/chat template, only </think> comes back over the wire - <thinking> spelled out in full - unterminated block, i.e. the response was cut off mid-thought by max_tokens The first two are now stripped. The third raises ValueError, because a truncated response holds no answer at all - only the abandoned guess. Raising routes it to the existing handler in evaluator.py, which passes the change through as important rather than dropping it; parse_eval_response deliberately does not catch ValueError, since its own fallback (important=False) would suppress the notification instead. Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-09-01 12:42:16 +02:00
Andrew Peabody	9e54ed3adb	fix(llm): string boolean parsing, reasoning model <think> stripping, and timestamp diff annotation (#4340) ... - Simplify _to_bool using changedetectionio.strtobool.strtobool - Strip <think>...</think> reasoning blocks in _extract_json for reasoning models - Fix _annotate_moved_lines short-circuit so standalone relative timestamps are always annotated - Add comprehensive unit tests in test_response_parser and test_prompt_builder	2026-09-01 11:52:40 +02:00
dgtlmoon	c24f338f95	Add watch UI - Tidying up logic around browser selection/visibility	2026-08-26 12:29:55 +02:00
dgtlmoon	bb2e6adece	Add watch UI should show which browser(s) are available and set default browser (#4334)	2026-08-25 20:15:59 +02:00
3 people	01cf56c8fb	feature: allow a watch or group to append to the inherited AI Change Summary prompt (#4294) ... Co-authored-by: snowyukitty <270071858+snowyukitty@users.noreply.github.com> Co-authored-by: dgtlmoon <dgtlmoon@gmail.com>	2026-08-20 15:14:59 +02:00
dgtlmoon	71d332d5a0	UI full refactor / upgrade (#4183)	2026-07-16 15:08:29 +02:00
dgtlmoon	a69ddbd787	LLM - Raise or remove LLM timeout when local endpoint detected #4225 (#4254)	2026-07-13 09:50:35 +02:00
dgtlmoon	0e3f1941b3	Code - LLM settings pydantic refactor (#4181)	2026-05-25 10:43:52 +02:00
dgtlmoon	701833b6ed	UI - LLM - Flag LLM_FEATURES_DISABLED to disable all LLM from the UI/system (#4171)	2026-05-21 12:51:56 +02:00
dgtlmoon	e9e8c8d218	LLM / AI Change detection rules and Summaries	2026-04-24 15:21:09 +02:00