ollama_chat 0.0.122 → 0.0.124

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d77fd2cddf7c921b77712a90d4d1d31b3daf0f80dc4170f71eb209e7ce46390b
-  data.tar.gz: af9f30997ca31d67d7ba1914a971b5abb165d1913b2723c0727f07929b4512e4
+  metadata.gz: 0d2664dce7c6742ff5c950e64330b84325bcbb573467edde9aceddc3fa209641
+  data.tar.gz: 87baa515acb398c9da1b7cf6c7fce173d946e4bd4d79ad0f1eb9dfbd2526235a
 SHA512:
-  metadata.gz: ba243ffe79c5062b0feb5fc2d6389efff95216961567dbe9275f020cbdf811d1f04f238e95972d007e611109c3bcc795057c8a2c4afeeaf7d1b739301b91c0f5
-  data.tar.gz: badb4e4ccca4ee006cdb48fd66b107367c81d7bf3ee3717482e4c61f3bc4d6fcda80d4cc54edefb9a0b5af5a6dbcf32173eeb3e0f48f545d32f5c3508d472ba1
+  metadata.gz: a091addc87c893f700f405147386dc8fe8fcc5c3134ad12bb1ffda570ec8a0f64ac4acbaeaed70116a6c61d0765e14e2f085fa8d2c0b98496fb0881a56fdb0f8
+  data.tar.gz: 6d078a9c69b50719dda02e9c81a32d51929627ab6e50c7cae023630543e717dd2c1a86166495f339875178108e0ded60f9f451ebbec1275f16f06771c9b1b215

data/CHANGES.md

@@ -1,5 +1,167 @@
 # Changes
 
+## 2026-10-02 v0.0.124
+
+### Added
+
+*   `OllamaChat::Feedback` module to replace raw `STDOUT.puts` and
+    `STDERR.puts` calls with typed, testable system notifications.
+    *   Supports types: `:success`, `:cancel`, `:denied`, `:warn`, `:info`,
+        `:alarm`.
+    *   Integrates with `use_pager` and handles newline formatting via
+        `output.print`.
+*   `memorize` tool to embed timestamped entries into per-persona
+    `memory-<persona_name>` Documentrix collections.
+*   `forget` tool to clear a single memory record by its ISO-8601 timestamp
+    tag.
+*   `/collection query` subcommand to debug collections, supporting optional
+    `-e` (edit) and `-r` (rerank) flags.
+*   `/config env` subcommand to display the Ollama Chat environment variable
+    tree using `OC.view`.
+*   `/last -v` flag to voice previous assistant messages via
+    `MessageList#speak_last`.
+*   `OllamaChat::CollectionSearch` module extracted from `SearchKnowledge`
+    tool, providing `find_document_records` and `rerank_records` methods mixed
+    into `Chat`.
+*   `refresh_system_prompt` method in `SystemPromptManagement` to
+    re-interpolate the active system prompt with fresh `persona` and
+    `runtime_info` values after collection mutations.
+*   Voice announcement in the compaction report, including
+    `context_filled_before`, `context_filled_after`, and `duration` in
+    `Compaction::Result`.
+*   `Speaker#wait_for_speaker` method to join the speaker thread and block
+    until completion.
+*   `spec/ollama_chat/speaker_spec.rb` with tests for `OllamaChat::Speaker`.
+
+### Changed
+
+*   Replaced `str % {…}` with `named_placeholders_interpolate({…})` for
+    DB-prompt call sites to handle unknown placeholders gracefully.
+*   Updated `directory_structure` tool description from "Tree viewer" to "File
+    locator" and added guidance to prefer it over shell `find` or `ls -R`.
+*   Routed prompt change feedback through the `chat` instance in `app_state.rb`
+    to ensure messages target the active chat session.
+*   Switched spec stubs from `allow` to `expect` in `http_handling_spec.rb`,
+    `message_list_spec.rb`, `execute_shell_spec.rb`, `tts_spec.rb`,
+    `compaction_spec.rb`, `audio_player_spec.rb`, and `asr_spec.rb` to enforce
+    required calls.
+*   Bumped `const_conf` dependency from `~> **0.3**` to `~> **0.9**`.
+*   Updated `rerank_records` to accept an optional `prompt_name:` keyword
+    argument.
+*   Improved new session name generation by extracting
+    `new_random_session_name` into `SessionManagement` and handling `nil`
+    cancellation in `determine_valid_new_name_for_session`.
+*   Allowed naming new sessions via `choose_session` by threading an optional
+    `name:` keyword through `new_session` and `Session.with_defaults`.
+*   Logged stored memory text in the `memorize` tool by adding `text:` to the
+    `chat.log` data hash.
+*   Extracted context usage helpers `context_usage_colored` and
+    `context_percentage` to eliminate duplicated format logic.
+*   Updated `output_eval_stats` in `follow_chat.rb` to print colored context
+    usage.
+
+### Fixed
+
+*   Fixed indentation bug in `model_handling.rb` import/export by changing
+    `sub` to `gsub`.
+*   Guarded source link rendering in `search_knowledge` against `nil` or empty
+    `source` values.
+*   Suppressed `report_on_exception` on `AudioPlayer` background thread.
+
+## 2026-09-25 v0.0.123
+
+### Added
+
+*   README section 5 documenting `/conversation compact`: token-aware
+    keep-recent budget, safe & retryable behavior, visible before/after
+    metrics, and iterative re-compaction.
+*   Three-step context escalation ladder in the README: `/conversation
+    compact` first, then `/conversation report` + `/clear` + `/input path`
+    as the preferred second step, and `/conversation clean` as the emergency
+    exit.
+*   `execute_shell` tool to the Filesystem row in the README, noted as running
+    shell commands as a last resort.
+*   `execute_jira_twg` tool to the Web/External row in the README for running
+    Jira CLI queries via `twg`.
+*   `lookup_group` tool to the Knowledge row in the README for retrieving prior
+    conversation groups by UUID.
+*   Speech Services (ASR) section documenting `OLLAMA_CHAT_ASR_URL`,
+    `OLLAMA_CHAT_ASR_CONVERT_COMMAND`, and `OLLAMA_CHAT_ASR_MODEL`.
+*   Audio Playback section documenting `OLLAMA_CHAT_AUDIO_PLAYER_CONFIG`.
+*   Invidious (YouTube Proxy) section documenting `OLLAMA_CHAT_INVIDIOUS_URL`,
+    `OLLAMA_CHAT_INVIDIOUS_COMPANION_KEY`, and
+    `OLLAMA_CHAT_INVIDIOUS_CAPTION_LANGUAGES`.
+*   `markdown:` keyword argument (default `true`) to
+    `kramdown_markdown_remove`; when `false`, skips the `kramdown_ansi_parse`
+    step while still removing emoji, ANSI, and box-drawing characters.
+*   Explanatory comment block to `eval_template` in
+    `lib/ollama_chat/tools/execute_grep.rb` clarifying that the `cmd` config
+    value is a Ruby string template whose `#{...}` interpolations are resolved
+    against the method's local parameters via `eval`.
+*   `cleaned` string prefix in `save_conversation` so the `STDOUT`/`STDERR`
+    confirmation messages read "Saved cleaned conversation to…" when `clean:
+    true` is passed.
+*   "Cancelled." message when the user skips saving in conversation report and
+    summarize flows.
+
+### Changed
+
+*   Renamed `report_session` to `generate_conversation_report` to clarify it
+    only builds the report text.
+*   Reworked `report_conversation` to always display in the pager first, then
+    optionally save to a file; removed the `save:` keyword argument.
+*   Reworked `summarize_conversation` in `session_management.rb` to always
+    render via `use_pager` first, then optionally save via `ask_for_filename?`
+    and `should_overwrite?`.
+*   Removed the `save:` keyword argument from `summarize_conversation` and the
+    `-f` flag from the `/conversation` command dispatch in `commands.rb`.
+*   Tightened the `/conversation` regex from `(?:[sf]|c)` to `[sc]` and updated
+    the `options:` help text to drop `-f save`.
+*   Changed "Nothing to summarize!" and "Nothing to report!" output from
+    `STDERR` to `STDOUT`.
+*   `kramdown_markdown_remove` now strips `\p{Extended_Pictographic}` emoji
+    before any further processing, preventing TTS engines from vocalizing them.
+*   `kramdown_markdown_remove` in `lib/ollama_chat/kramdown_ansi.rb` now strips
+    Unicode box-drawing characters (`U+2500`..`U+257F`) that kramdown renders
+    as table borders, preventing TTS engines from stammering on them.
+*   Collapses resulting multi-space runs and strips leading/trailing whitespace
+    in `kramdown_markdown_remove`.
+*   Moved the `kramdown_markdown_remove` call from `flush_buffer` into
+    `enqueue_tts` in `lib/ollama_chat/tts.rb` so all enqueue paths are covered,
+    passing `markdown: @chat.markdown.on?`.
+*   `multipart_form_data` in `lib/ollama_chat/asr.rb` now returns a hash
+    containing only `headers:`, `expects:`, and `body:`, which are the actual
+    Excon request options, instead of merging `rest` (`model:`, `language:`)
+    into the returned options hash.
+*   Updated YARD documentation to reflect the new parameter and emoji stripping
+    behavior.
+*   Updated `spec/ollama_chat/asr_spec.rb` expectations from
+    `hash_including(model: ...)` / `hash_including(language: ...)` to
+    `hash_including(body: kind_of(String))` to match the new option shape.
+*   Updated `commands_spec.rb` to remove the obsolete `/conversation summarize
+    -f` and `/conversation report -f` specs and drop `save:` from expectations.
+*   Updated `session_management_spec.rb` for the new show-then-save flow,
+    `STDOUT` stream, and `Cancelled.` expectation.
+*   Updated the corresponding expectation in `conversation_spec.rb` to match
+    the new message text.
+*   Renamed former section 5 "Session Reports" to section 6 "Conversation
+    Reports" to match the actual command name.
+*   Updated Conversation Archiving section from `/session summarize` to
+    `/conversation summarize`, removed obsolete `-f` flag reference, and
+    described the show-then-save flow.
+
+### Fixed
+*   Fixed `TTS_URL` to `OLLAMA_CHAT_TTS_URL` to match the actual env var name
+    in `oc.rb`.
+*   Wrapped `@prefix` with `Regexp.quote()` in `RedisCache#unpre` to ensure the
+    prefix is always matched as a literal string.
+*   Fixed typos in height validation error message.
+
+### Removed
+*   `context_spook` from development dependencies in `Rakefile` and
+    `ollama_chat.gemspec`.
+*   The `-f` flag from the `/report` command in `commands.rb`.
+
 ## 2026-09-25 v0.0.122
 
 ## Features

data/README.md

@@ -62,7 +62,7 @@ The following environment variables can be used to configure behavior:
 - `OLLAMA_URL` - Base URL for Ollama server (default: `http://localhost:11434`)
 - `OLLAMA_HOST` - Base hostname for Ollama server (default: `localhost:11434`)
 - `OLLAMA_SEARXNG_URL` - SearxNG search endpoint URL
-- `TTS_URL` - Base URL for the [audio.cpp](https://github.com/0xshug0/audio.cpp) TTS server (default: `http://localhost:8880`)
+- `OLLAMA_CHAT_TTS_URL` - Base URL for the [audio.cpp](https://github.com/0xshug0/audio.cpp) TTS server (default: `http://localhost:8880`)
 
 #### Chat Settings
 - `OLLAMA_CHAT_MODEL` - Default model to use (e.g., `llama3.1`)
@@ -75,6 +75,19 @@ The following environment variables can be used to configure behavior:
 - `OLLAMA_CHAT_LOG_DATABASE` - Database log file path (default: `$XDG_STATE_HOME/database.log`)
 - `OLLAMA_CHAT_LOG_TAIL_LINES` - Max lines to retain in log files (default: `10000`)
 
+#### Speech Services (ASR)
+- `OLLAMA_CHAT_ASR_URL` - Base URL for the ASR (Speech-to-Text) service (default: `http://localhost:8880`)
+- `OLLAMA_CHAT_ASR_CONVERT_COMMAND` - Shell command template to convert video to 16 kHz mono PCM WAV; use `%{input}` / `%{output}` as placeholders (default: `ffmpeg -y -i %{input} -vn -acodec pcm_s16le -ar 16000 -ac 1 %{output}`)
+- `OLLAMA_CHAT_ASR_MODEL` - ASR model identifier (default: `qwen3-asr-1.7b`)
+
+#### Audio Playback
+- `OLLAMA_CHAT_AUDIO_PLAYER_CONFIG` - JSON object with `command`, `frequency`, `bits`, `pause` keys controlling the ffplay-based TTS audio player
+
+#### Invidious (YouTube Proxy)
+- `OLLAMA_CHAT_INVIDIOUS_URL` - Base URL for an Invidious instance
+- `OLLAMA_CHAT_INVIDIOUS_COMPANION_KEY` - Bearer token for the Invidious companion player API (required when `URL` is set)
+- `OLLAMA_CHAT_INVIDIOUS_CAPTION_LANGUAGES` - JSON array of language-code regexes for caption selection priority (default: `["\\Aen\\z","\\Aen-","\\Ade\\z","\\Ade-"]`)
+
 #### Tool Configuration
 - `OLLAMA_CHAT_TOOLS_TEST_RUNNER` - Configured test runner for `run_tests` (default: `rspec`)
 - `OLLAMA_CHAT_TOOLS_CTAGS_TOOL` - Path to the ctags tool
@@ -243,14 +256,57 @@ switch. The profile system allows you to manage "Live" vs "Saved" settings:
     "bake" those live settings into a permanent profile using `options from
     session`.
 
-#### 4. Conversation Archiving (`/session summarize`)
+#### 4. Conversation Archiving (`/conversation summarize`)
 
 Turn your long-form brainstorming sessions into structured documents. The
-`/session summarize` command can distill an entire conversation into a concise
-summary.
+`/conversation summarize` command distills an entire conversation into a
+concise summary, displayed in the pager first, then optionally saved.
 *   **Quick View**: Use `-s` for a one-sentence executive summary.
-*   **Archiving**: Use `-f <filename>` to dump the full summary directly into a
-    Markdown file, creating an automatic journal of your project's evolution.
+*   **Archiving**: After the summary is displayed, you are prompted for a
+    filename to save it as a Markdown file, creating an automatic journal
+    of your project's evolution.
+
+#### 5. Context Compaction (`/conversation compact`)
+
+Long sessions inevitably fill up the model's context window. The
+`/conversation compact` command summarizes older messages into a single
+compact summary while preserving recent exchanges, freeing up space for
+continued work.
+
+*   **Token-aware**: The keep-recent budget is derived from the active
+    model's context length, so it adapts automatically.
+*   **Safe & retryable**: If the LLM summarization fails, the message list
+    is left untouched and you can simply retry.
+*   **Visible metrics**: After compaction, a report shows summarized
+    message count, summary size, and context usage before/after.
+*   **Iterative**: Repeated compactions merge into the existing summary
+    rather than stacking multiple summary messages.
+
+Run it whenever context usage climbs into the red zone (visible in the
+runtime info gauge) — the model stays sharp and the conversation keeps
+flowing.
+
+If compaction alone isn't enough, a practical escalation ladder:
+
+1. **`/conversation compact`** — summarize old messages, keep recent tail.
+   Try this first; it's the least destructive.
+2. **`/conversation report`** → **`/clear`** → **`/input path
+    standup.md`** — generate a standup-style report, save it, clear
+    the messages, then feed the report back as context. Do this
+    before `clean`, because `clean` strips the tool output and
+    thinking that make a good report.
+3. **`/conversation clean`** — strips tool results, images, and
+    thinking content from all messages. More radical, but the
+    conversation structure and text remain intact. The emergency
+    exit: if context is so stuffed that even a report can't fit,
+    `clean` carves out enough room for anything to work again.
+
+#### 6. Conversation Reports (`/conversation report`)
+
+Generate a structured report from your conversation using configurable
+prompt templates. The report is displayed in the pager first, then
+optionally saved to a file. Particularly useful for daily standup summaries
+— run it at the end of the day and save the output for your team sync.
 
 ### Using a Persona
 
@@ -467,12 +523,12 @@ context, manipulate files, and retrieve external information.
 
 | Category | Tools | Description |
 | :--- | :--- | :--- |
-| **Filesystem** | `read_file`, `write_file`, `patch_file`, `delete_file`, `move_file`, `directory_structure`, `execute_grep` | Read, write, and search files within allowed directories. |
+| **Filesystem** | `read_file`, `write_file`, `patch_file`, `delete_file`, `move_file`, `directory_structure`, `execute_grep`, `execute_shell` | Read, write, and search files within allowed directories; run shell commands as a last resort. |
 | **Ruby/Dev** | `resolve_tag`, `execute_ri`, `gem_path_lookup`, `run_tests`, `eval_ruby` | Introspect Ruby code, check documentation, and run test suites. |
-| **Web/External** | `search_web`, `get_url`, `browse`, `get_rfc`, `get_cve`, `get_endoflife`, `get_ghr`, `get_jira_issue` | Access the internet, fetch specific URLs, and look up technical standards. |
+| **Web/External** | `search_web`, `get_url`, `browse`, `get_rfc`, `get_cve`, `get_endoflife`, `get_ghr`, `get_jira_issue`, `execute_jira_twg` | Access the internet, fetch specific URLs, and look up technical standards; run Jira CLI queries via `twg`. |
 | **System/Util** | `get_time`, `get_location`, `get_current_weather`, `generate_password`, `compute_bmi`, `roll_dice` | General utility functions for time, location, and simple calculations. |
 | **Editor/Clip** | `copy_to_clipboard`, `paste_from_clipboard`, `paste_into_editor`, `open_file_in_editor` | Bridge the gap between the chat and the system clipboard or editor. |
-| **Knowledge** | `search_knowledge`, `file_context` | Semantic search for specific snippets vs. broad retrieval of structured project context. |
+| **Knowledge** | `search_knowledge`, `file_context`, `lookup_group` | Semantic search for specific snippets, broad retrieval of structured project context, or retrieving prior message groups by UUID. |
 | **Multimodal** | `generate_image` | Generate images via a local ComfyUI server. |
 
 ***Note on Knowledge Tools**: Use `search_knowledge` for precise,

data/Rakefile

@@ -55,7 +55,7 @@ GemHadar do
   dependency             'pdf-reader',            '~> 2.0'
   dependency             'bigdecimal',            '~> 3.1'
   dependency             'csv',                   '~> 3.0'
-  dependency             'const_conf',            '~> 0.3'
+  dependency             'const_conf',            '~> 0.9'
   dependency             'context_spook',         '~> 1.6'
   dependency             'infobar',               '>= 0.13.1'
   dependency             'rubyzip',               '~> 3.0'
@@ -68,7 +68,6 @@ GemHadar do
   development_dependency 'webmock'
   development_dependency 'debug'
   development_dependency 'simplecov'
-  development_dependency 'context_spook'
   development_dependency 'utils'
 
   licenses << 'MIT'

data/lib/ollama_chat/asr.rb

@@ -38,11 +38,11 @@ module OllamaChat
           executable = Shellwords.split(cmd).first
           result     = system(cmd, out: File::NULL, err: File::NULL)
           if result.nil?
-            STDERR.puts "ASR: #{executable} not found in PATH."
+            chat.feedback("ASR: #{executable} not found in PATH.", type: :warn)
             return
           end
           unless File.size(wav.path) > 0
-            STDERR.puts "ASR: #{executable} produced no output."
+            chat.feedback("ASR: #{executable} produced no output.", type: :warn)
             return
           end
 
@@ -61,7 +61,7 @@ module OllamaChat
           result = JSON.parse(response.body) rescue nil
         end
         chat.log(:error, e, data: { status:, result: })
-        STDERR.puts "ASR transcription failed: #{e.message}"
+        chat.feedback("ASR transcription failed: #{e.message}", type: :warn)
         nil
       end
 
@@ -99,10 +99,10 @@ module OllamaChat
         body << Excon::CR_NL
         body << "--#{boundary}--" << Excon::CR_NL
 
-        rest.symbolize_keys_recursive.compact | {
+        {
           headers: { 'Content-Type' => %{multipart/form-data; boundary="#{boundary}"} },
           expects: 200,
-          body:,
+          body:    ,
         }
       end
     end

data/lib/ollama_chat/chat.rb

@@ -34,6 +34,7 @@ require 'zlib'
 class OllamaChat::Chat
   include Tins::GO
   include Term::ANSIColor
+  include OllamaChat::Feedback
   include OllamaChat::TokenEstimator
   include OllamaChat::HTTPHandling
   include OllamaChat::Commands
@@ -64,6 +65,7 @@ class OllamaChat::Chat
   include OllamaChat::ConfigHandling
   include OllamaChat::PersonaeManagement
   include OllamaChat::SessionManagement
+  include OllamaChat::CollectionSearch
   include OllamaChat::RAGHandling
   include OllamaChat::FavouritesManagement
   include OllamaChat::PromptHandling
@@ -195,7 +197,7 @@ class OllamaChat::Chat
       abort "Failed to use to model: #{e}"
     end
 
-    STDOUT.puts
+    feedback ?\n
 
     setup_persona_from_session
     setup_system_prompt
@@ -203,7 +205,7 @@ class OllamaChat::Chat
     print_welcome
     info_session
 
-    STDOUT.puts "\nType /help to display the chat help."
+    feedback("\nType /help to display the chat help.")
 
     interact_with_user
   end
@@ -434,19 +436,19 @@ class OllamaChat::Chat
     case what
     when 'messages', nil
       messages.clear
-      STDOUT.puts "Cleared messages."
+      feedback("Cleared messages.", type: :info)
     when 'links'
       links.clear
-      STDOUT.puts "Cleared links."
+      feedback("Cleared links.", type: :info)
     when 'history'
       clear_history
-      STDOUT.puts "Cleared history."
+      feedback("Cleared history.", type: :info)
     when 'tags'
       @documents.clear
-      STDOUT.puts "Cleared all tags."
+      feedback("Cleared all tags.", type: :info)
     when 'images'
       messages.clear_images
-      STDOUT.puts "Cleared all images."
+      feedback("Cleared all images.", type: :info)
     when 'all'
       if confirm?(
           prompt: '🔔 Are you sure to clear messages and collection? (y/n) ',
@@ -457,9 +459,9 @@ class OllamaChat::Chat
         @documents.clear
         links.clear
         clear_history
-        STDOUT.puts "Cleared messages and collection #{bold{collection}}."
+        feedback("Cleared messages and collection #{bold{collection}}.", type: :info)
       else
-        STDOUT.puts 'Cancelled.'
+        feedback("Denied.", type: :denied)
       end
     end
     persona_profile
@@ -517,7 +519,7 @@ class OllamaChat::Chat
           type           = message.type.full?(:to_sym) || :socket_input
           content        = message.content
           @parse_content = message.parse
-          STDOUT.puts color(112) { "Received a server socket message. Processing now…" }
+          feedback color(112) { "Received a server socket message. Processing now…" }, type: :info
         else
           raise
         end
@@ -619,13 +621,13 @@ class OllamaChat::Chat
       msg = "Currently lost connection to ollama server and cannot send command."
       log(:warn, msg, warn: true)
     rescue Interrupt
-      STDOUT.puts "Type /quit to quit."
+      feedback("Type /quit to quit.")
     ensure
       self.server_socket_message = nil
     end
     0
   rescue OllamaChat::OllamaChatQuitError
-    STDOUT.puts "Goodbye."
+    feedback("Goodbye.")
   rescue ComplexConfig::AttributeMissing, ComplexConfig::ConfigurationSyntaxError => e
     log(:error, e)
     fix_config(e)
@@ -718,7 +720,7 @@ class OllamaChat::Chat
   # @note Progress is reported to STDOUT during processing
   def add_documents_from_argv(document_list)
     if document_list.any?(&:empty?)
-      STDOUT.puts "Clearing collection #{bold{documents.collection}}."
+      feedback("Clearing collection #{bold{documents.collection}}.", type: :info)
       documents.clear
       document_list.reject!(&:empty?)
     end
@@ -730,7 +732,7 @@ class OllamaChat::Chat
           File.expand_path(doc)
         end
       end
-      STDOUT.puts "Collection #{bold{documents.collection}}: Adding #{document_list.size} documents…"
+      feedback("Collection #{bold{documents.collection}}: Adding #{document_list.size} documents…", type: :info)
       count = 1
       document_list.each_slice(25) do |docs|
         docs.each do |doc|

data/lib/ollama_chat/clipboard.rb

@@ -116,11 +116,11 @@ module OllamaChat::Clipboard
     text = last_message_content(content: false)
     perform_copy_to_clipboard(text:, edit:)
     log(:info, "Copied to clipboard", data: { bytes: format_bytes(text.bytesize) }) if text
-    STDOUT.puts "The last response has been successfully copied to the system clipboard."
+    feedback("The last response has been successfully copied to the system clipboard.", type: :info)
     true
   rescue OllamaChat::OllamaChatError => e
     log(:error, e, data: { method: __method__ })
-    STDERR.puts e.message
+    feedback(e.message, type: :warn)
   end
 
   # Pastes content from the system clipboard into the chat.
@@ -137,11 +137,11 @@ module OllamaChat::Clipboard
   def paste_from_clipboard(edit: false)
     result = perform_paste_from_clipboard(edit:)
     log(:info, "Pasted from clipboard", data: { bytes: format_bytes(result.bytesize) }) if result
-    STDOUT.puts "The clipboard content has been successfully copied to the chat."
+    feedback("The clipboard content has been successfully copied to the chat.", type: :info)
     result
   rescue OllamaChat::OllamaChatError => e
     log(:error, e, data: { method: __method__ })
-    STDERR.puts e.message
+    feedback(e.message, type: :warn)
   end
 
   # Read the full text from STDIN and return it.

data/lib/ollama_chat/collection_search.rb

@@ -0,0 +1,66 @@
+# Shared collection search primitives for document retrieval and LLM
+# reranking.
+#
+# Extracted from {OllamaChat::Tools::SearchKnowledge} so that the
+# `/collection query` command and the trigger mechanism can reuse
+# the same search + rerank pipeline without duplicating logic.
+module OllamaChat::CollectionSearch
+  include Kramdown::ANSI::Width
+
+  # Searches the active document collection for records matching
+  # the given query.
+  #
+  # @param query [String] the search query
+  # @param tags [Array<String>, nil] tag filter
+  # @param text_size [Integer, nil] max snippet size
+  # @param text_count [Integer, nil] max number of snippets
+  # @param min_similarity [Float, nil] minimum similarity threshold
+  #
+  # @return [Array<Documentrix::Utils::TagResult>] matching records
+  def find_document_records(
+    query,
+    tags: nil, text_size: nil, text_count: nil, min_similarity: nil
+  )
+    tags = Documentrix::Utils::Tags.new(
+      tags, valid_tag: /\A#*([-\w.\]\[]+)/
+    )
+    @documents.find_where(
+      query.first(config.embedding.model.context_length),
+      tags:,
+      prompt:         config.embedding.model.prompt?,
+      text_size:,
+      text_count:,
+      min_similarity:
+    )
+  end
+
+  # Reranks a set of records using the LLM with the `rerank` prompt.
+  #
+  # @param query [String] the original search query
+  # @param records [Array<Documentrix::Utils::TagResult>] candidate records
+  # @param prompt_name [String, nil] the prompt template to use for
+  #   reranking; defaults to `'rerank'`
+  # @return [Array<Documentrix::Utils::TagResult>] filtered records
+  def rerank_records(query, records, prompt_name: nil)
+    candidates = records.each_with_index.map { |r, i|
+      "[#{i}] #{truncate(r.text.strip, length: 300)}"
+    }.join("\n")
+
+    prompt_name ||= 'rerank'
+    rerank_prompt = prompt(prompt_name) or
+      raise 'missing prompt %s' % prompt_name.inspect
+    rerank_prompt = rerank_prompt.to_s
+      .named_placeholders_interpolate({ query:, candidates: })
+
+    begin
+      if response = generate(prompt: rerank_prompt).full?
+        indices = response.scan(/\d+/).map(&:to_i)
+          .select { |i| (0...records.size).include?(i) }
+        records = records.values_at(*indices) if indices.any?
+      end
+    rescue => e
+      log(:error, e, data: { context: 'rerank' })
+    end
+    records
+  end
+end