rubik 0.4.1 → 0.5.0

data/lib/rubik/plugin/storage.rb

@@ -6,6 +6,7 @@ require "time"
 # save_manifest atomik yazımı Platform.atomic_write kullanır; dosyanın tek başına
 # require edilmesi durumunda da çözümlenebilsin diye açık yüklenir.
 require_relative "../platform"
+require_relative "../log"
 require_relative "package_inventory"
 
 module Rubik
@@ -31,7 +32,7 @@ module Rubik
         [project_plugins_dir, global_plugins_dir].each do |dir|
           FileUtils.mkdir_p(dir)
         rescue SystemCallError => e
-          warn "[WARN] Failed to create plugin directory #{dir}: #{e.message}" if ENV["RUBIK_DEBUG"]
+          Rubik::Log.warn(:plugin, "Failed to create plugin directory #{dir}: #{e.class}: #{e.message}")
         end
       end
 
@@ -67,7 +68,7 @@ module Rubik
         save_manifest(dir, manifest)
       end
 
-      def verify_integrity(path, scope: :project)
+      def verify_integrity(path, scope: :project, content: nil)
         return :trusted if ENV["RUBIK_TRUST_OVERLAYS"] == "1"
 
         dir = scope.to_sym == :global ? global_plugins_dir : project_plugins_dir
@@ -78,12 +79,12 @@ module Rubik
         basename = File.basename(path)
         manifest = load_manifest(dir)
 
-        current_content = File.exist?(path) ? File.binread(path) : ""
+        current_content = content || (File.exist?(path) ? File.binread(path) : "")
         current_hash = PackageInventory.content_hash(current_content)
 
         if manifest.key?(basename)
           expected_hash = manifest[basename]["sha256"]
-          if current_hash == expected_hash
+          if PackageInventory.secure_compare(current_hash, expected_hash)
             :verified
           else
             warn "[SECURITY] Integrity check failed for plugin '#{basename}': file modified since adding."

data/lib/rubik/prompt/doctrine.rb

@@ -221,14 +221,15 @@ module Rubik
       def rule_nine_body(active_tools: nil, plan_mode: false)
         return "Keep the repository worktree free of agent workfiles, scratch notes, and temporary artifacts." if plan_mode
 
+        vakanuvis_on = tool_active?("vakanuvis", active_tools)
         storage_part = if tool_active?("storage", active_tools)
-                         Rubik::Prompt::ToolTeachings.teaching_for("storage")
+                         Rubik::Prompt::ToolTeachings.teaching_for("storage", vakanuvis_active: vakanuvis_on)
                        else
                          "Keep the repository worktree free of scattered agent workfiles; read any existing " \
                            "`rubik://storage/<type>/<id>` entities via `read_file` when a store is wired."
                        end
         parts = [storage_part]
-        parts << Rubik::Prompt::ToolTeachings.teaching_for("vakanuvis") if tool_active?("vakanuvis", active_tools)
+        parts << Rubik::Prompt::ToolTeachings.teaching_for("vakanuvis") if vakanuvis_on
         parts << Rubik::Prompt::ToolTeachings.teaching_for("show_file") if tool_active?("show_file", active_tools)
         parts << "Subagent transcripts are indexed automatically as `transcript` entities (alias `subagent-<storage-id>`) " \
                  "and are readable live or persisted via the canonical `rubik://subagent/<storage-id>/transcript` reference — " \
@@ -244,14 +245,10 @@ module Rubik
         if storage_on && vakanuvis_on
           "Persist pipeline knowledge in the central storage (`storage` tool): the decomposed plan, review findings, " \
             "and the final goal record — link stages with entity ids (`links: {\"goal\": \"goal.N.<hash16>\"}`) so the " \
-            "audit trail survives the session. Per-stage MEMORY notes go through the chronicler instead: " \
-            "`vakanuvis(action: 'record', topic: '...', body: '...')` mints the `mem.` ref, upserts and supersedes — " \
-            "never write memory with raw storage puts when `vakanuvis` is available " \
-            "(fall back to `storage` `put` only when `vakanuvis` is unavailable); re-enter prior context with " \
-            "`vakanuvis(action: 'recall', query: '...')` (also after compaction). Keep the repository worktree free of " \
-            "agent workfiles. Transcripts of finished " \
-            "subagents are indexed automatically (searchable via `storage` action 'search') and persist after the " \
-            "subagent is reaped."
+            "audit trail survives the session. Route durable memory through the chronicler (`vakanuvis` record/recall; " \
+            "see rule 9), never through raw storage puts. Keep the repository worktree free of agent workfiles. " \
+            "Transcripts of finished subagents are indexed automatically (searchable via `storage` action 'search') " \
+            "and persist after the subagent is reaped."
         elsif storage_on
           "Persist pipeline knowledge in the central storage (`storage` tool): the decomposed plan, review findings, " \
             "and the final goal record — link stages with entity ids (`links: {\"goal\": \"goal.N.<hash16>\"}`) so the " \
@@ -259,11 +256,9 @@ module Rubik
             "finished subagents are indexed automatically (searchable via `storage` action 'search') and persist after " \
             "the subagent is reaped."
         elsif vakanuvis_on
-          "Persist durable per-stage MEMORY notes through the chronicler: `vakanuvis(action: 'record', topic: '...', " \
-            "body: '...')` mints the `mem.` ref, upserts and supersedes; re-enter prior context with " \
-            "`vakanuvis(action: 'recall', query: '...')` (also after compaction). Keep the repository worktree free of " \
-            "agent workfiles. Transcripts of finished subagents remain readable via `rubik://subagent/<storage-id>/transcript` " \
-            "after the subagent is reaped."
+          "Route durable memory through the chronicler (`vakanuvis` record/recall; see rule 9). Keep the repository " \
+            "worktree free of agent workfiles. Transcripts of finished subagents remain readable via " \
+            "`rubik://subagent/<storage-id>/transcript` after the subagent is reaped."
         else
           "Keep the repository worktree free of agent workfiles. Transcripts of finished subagents remain readable via " \
             "`rubik://subagent/<storage-id>/transcript` after the subagent is reaped."

data/lib/rubik/prompt/tool_teachings.rb

@@ -2,21 +2,23 @@
 
 module Rubik
   module Prompt
-    # Tool teachings keyed by canonical tool name (architecture review
-    # 2026-10-01, candidate 1): the sentences that teach HOW a specific tool
-    # is used live here, one key per tool, instead of being embedded unnamed
-    # in Doctrine.operational_rules_xml's heredoc. Identity (the tool) lives in
-    # its Tools::Declaration; prose (the presentation) lives here — a prompt
-    # layer concern. test_tool_teachings welds the two: every key must
-    # resolve to a declared (Catalog) tool, so a rename that forgets the
-    # prompt fails the suite.
-    #
-    # The strings are interpolated into the operational rules HEREDOC at the
-    # same positions they originally occupied — the rendered rules are
-    # byte-identical (pinned by the substring tests in
-    # test_structured_context_builder, test_agent_command_contract,
-    # test_buffer_apply_conflict, test_repl_tool_separation_and_guardrails).
+    # Tool teachings keyed by canonical tool name (architecture review 2026-10-01, candidate 1):
+    # the sentences that teach HOW a specific tool is used live here, one key per tool.
+    # Identity lives in its Tools::Declaration; prose lives here — a prompt layer concern.
+    # test_tool_teachings welds the two: every key must resolve to a declared Catalog tool.
     module ToolTeachings
+      STORAGE_BASE =
+        "Persist agent workfiles — goals, plans, reviews, and work notes — in the central " \
+        "`storage` database (`storage` tool: put/get/list/search/set_ref/delete), NOT as scattered files in " \
+        "the repository worktree. Read, list, and search all entity types (`goal`, `plan`, `memory`, `wiki`, " \
+        "`transcript`, `review`, `note`) via `storage` or `read_file(path: 'rubik://storage/<type>/<id>')` " \
+        "(browse with `rubik://storage/index` and `rubik://storage/<type>` listings)."
+
+      STORAGE_FALLBACK =
+        "#{STORAGE_BASE[0...-1]}; write durable `memory` cards and compiled `wiki` pages through direct " \
+        "`storage` `put` on `memory`/`wiki` (reserving direct `storage` `put` on `memory`/`wiki` for sessions " \
+        "where `vakanuvis` is unavailable).".freeze
+
       TEACHINGS = {
         "replace_file_content" =>
           "For modifying existing files, prefer `replace_file_content` with `path`, exact verbatim `target_content`, " \
@@ -35,15 +37,7 @@ module Rubik
           "params_schema: { type: 'object', properties: { ... }, required: [...] }, code: '->(args) { ... }')` " \
           "(always provide `params_schema` when the handler reads arguments from `args`; omit it or pass an empty " \
           "`{ type: 'object', properties: {} }` schema only for tools that take no arguments).",
-        "storage" =>
-          "Persist agent workfiles — goals, plans, reviews, and work notes — in the central " \
-          "`storage` database (`storage` tool: put/get/list/search/set_ref/delete), NOT as scattered files in " \
-          "the repository worktree. Read, list, and search all entity types (`goal`, `plan`, `memory`, `wiki`, " \
-          "`transcript`, `review`, `note`) via `storage` or `read_file(path: 'rubik://storage/<type>/<id>')` " \
-          "(browse with `rubik://storage/index` and `rubik://storage/<type>` listings); write durable `memory` " \
-          "cards and compiled `wiki` pages through `vakanuvis` (`record` / `digest`) whenever `vakanuvis` is in " \
-          "your toolbelt, reserving direct `storage` `put` on `memory`/`wiki` for sessions where `vakanuvis` is " \
-          "unavailable.",
+        "storage" => STORAGE_BASE,
         "run_command" =>
           "GitHub facts must be verified, not assumed: after `gh pr merge` (which can succeed with EMPTY output) " \
           "confirm the merge with `gh pr view <number> --json state`; `mergeable: UNKNOWN` right after a push means " \
@@ -57,17 +51,13 @@ module Rubik
           "while your context stays lean; only fall back to read_file when YOU must reason about the content.",
         "vakanuvis" =>
           "The background chronicler keeps compiled knowledge (memory cards, wiki pages) in rubik://storage. " \
-          "At task start — and again after any compaction — ask it with `vakanuvis(action: 'recall', query: '...')` " \
-          "instead of pre-loading pages: it returns a deterministic digest plus rubik:// source links. When " \
-          "dispatching a subagent, paste the relevant recall digest (or its rubik:// link) into the task brief. " \
-          "At the end of a task, persist only the durable knowledge with `vakanuvis(action: 'record', topic: '...', " \
-          "body: '...')` — memory writes go through record (ref minting, upsert, supersede come free), never " \
-          "through raw storage puts when `vakanuvis` is available. Recall is keyword-AND over card/page text, so END " \
-          "every recorded body and digest query with its own vocabulary: include a `Keywords:` line listing 5-10 " \
-          "synonyms in BOTH working languages (e.g. TR + EN) — a Turkish query cannot otherwise find an English page. " \
-          "If recall is too shallow, queue `vakanuvis(action: 'digest', query: '...')`: it returns a deterministic " \
-          "receipt and compiles the wiki page asynchronously. Make the session close a standard digest point: review " \
-          "the session's new cards, queue one digest per open topic, and let the home index refresh.",
+          "At task start, ask it with `vakanuvis(action: 'recall', query: '...')`: it returns a deterministic " \
+          "digest plus rubik:// source links. Recall is keyword-AND over card/page text: use 2-3 core terms. " \
+          "If the result is empty, retry once with other-language synonyms. When dispatching a subagent, paste " \
+          "the relevant recall digest (or its rubik:// link) into the task brief. At the end of a task, persist " \
+          "durable conclusions with `vakanuvis(action: 'record', topic: '...', body: '...')` — memory writes go " \
+          "through record (ref minting, upsert, supersede come free), never through raw storage puts. End the body " \
+          "with a `Keywords:` line (TR+EN) if you can; it is auto-extracted otherwise.",
         "prune_context" =>
           "When long sessions leave stale exploration and superseded tool output weighing on the ROOT window, " \
           "check `prune_context(action: 'status')` (window estimate vs ceiling, staged plan state) and force a " \
@@ -79,7 +69,11 @@ module Rubik
 
       module_function
 
-      def teaching_for(tool_name) = TEACHINGS[tool_name.to_s]
+      def teaching_for(tool_name, vakanuvis_active: true)
+        return vakanuvis_active ? STORAGE_BASE : STORAGE_FALLBACK if tool_name.to_s == "storage"
+
+        TEACHINGS[tool_name.to_s]
+      end
     end
   end
 end

data/lib/rubik/repair/loop.rb

@@ -27,20 +27,34 @@ module Rubik
 
           @snapshot_store.create_snapshot(@buffer_manager)
 
-          prompt = build_repair_prompt(current_diag, target_file, @attempts_made)
-          res = @provider.complete([{ role: "user", content: prompt }])
-          proposed_code = extract_code(res.text)
-
-          @buffer_manager.write(target_file, proposed_code)
-
-          # Verify syntax against in-memory buffer via tempfile
-          check_res = check_buffer_syntax(target_file, lang)
-
-          return { ok: true, attempts: @attempts_made, code: proposed_code } if check_res[:ok]
-
-          current_diag = Rubik::Diagnostics::Parser.parse(check_res[:output], lang)
-          @snapshot_store.undo(@buffer_manager)
-
+          begin
+            prompt = build_repair_prompt(current_diag, target_file, @attempts_made)
+            res = @provider.complete([{ role: "user", content: prompt }])
+            proposed_code = extract_code(res.text)
+
+            if proposed_code.empty?
+              @snapshot_store.undo(@buffer_manager)
+              next
+            end
+
+            @buffer_manager.write(target_file, proposed_code)
+
+            # Verify syntax against in-memory buffer via tempfile
+            check_res = check_buffer_syntax(target_file, lang)
+
+            return { ok: true, attempts: @attempts_made, code: proposed_code } if check_res[:ok]
+
+            if check_res[:unverified]
+              @snapshot_store.undo(@buffer_manager)
+              return { ok: false, attempts: @attempts_made, unverified: true, error: check_res[:error] }
+            end
+
+            current_diag = Rubik::Diagnostics::Parser.parse(check_res[:output], lang)
+            @snapshot_store.undo(@buffer_manager)
+          rescue StandardError => e
+            @snapshot_store.undo(@buffer_manager)
+            return { ok: false, attempts: @attempts_made, error: "#{e.class}: #{e.message}" }
+          end
         end
 
         { ok: false, attempts: @attempts_made, last_diagnostics: current_diag }
@@ -50,7 +64,7 @@ module Rubik
 
       def check_buffer_syntax(target_file, lang)
         adapter = @adapter_registry.get(lang.to_s)
-        return { ok: true } unless adapter
+        return { ok: false, unverified: true, error: "No adapter registered for #{lang}" } unless adapter
 
         content = @buffer_manager.read(target_file)
         ext = File.extname(target_file)

data/lib/rubik/repl/commands/agent_context.rb

@@ -97,6 +97,7 @@ module Rubik
             config: context_cfg,
             force: true
           )
+          Rubik::Storage::Vakanuvis::Orientation.inject_after_compaction!(ctx.conversation_history, ctx.runtime_manager, config: ctx.config)
           after_tokens = Rubik::Prompt::TokenEstimator.estimate_history(ctx.conversation_history)
           delta = before_tokens - after_tokens
           ctx.out.puts "Context compaction completed: #{before_tokens} -> #{after_tokens} tokens (reduced #{delta} tokens)."

data/lib/rubik/repl/commands/system.rb

@@ -57,11 +57,13 @@ module Rubik
 
           shell.register_command("clear", description: "Clear conversation history / dialogue turns") do |_args, ctx|
             ctx.conversation_history.clear
+            Rubik::Storage::Vakanuvis::Orientation.reset_session!(ctx.runtime_manager)
             ctx.out.puts "Conversation context cleared. Starting fresh topic."
           end
 
           shell.register_command("reset", description: "Reset conversation history and in-memory dialogue turns") do |_args, ctx|
             ctx.conversation_history.clear
+            Rubik::Storage::Vakanuvis::Orientation.reset_session!(ctx.runtime_manager)
             ctx.out.puts "Conversation context reset. Starting fresh topic."
           end
 

data/lib/rubik/repl/turn_recorder.rb

@@ -191,6 +191,8 @@ module Rubik
       def apply_staged_prune_plan!
         return if @replaying
 
+        Rubik::Storage::Vakanuvis::Orientation.inject_session_start!(@conversation_history, @runtime_manager, config: @config) if @conversation_history.empty?
+
         harness = Rubik::Coeffects.get(@runtime_manager&.context, Rubik::Coeffects::PRUNER)
         return unless harness
 
@@ -198,6 +200,7 @@ module Rubik
         return unless new_window
 
         @conversation_history = new_window
+        Rubik::Storage::Vakanuvis::Orientation.inject_after_compaction!(@conversation_history, @runtime_manager, config: @config)
         line = "[Pruner] Applied staged plan: dropped #{receipt[:dropped]} unit(s), " \
                "summarized #{receipt[:summarized]} (#{receipt[:skipped_stale]} stale op(s) skipped) — " \
                "window ~#{receipt[:before_tokens]} -> ~#{receipt[:after_tokens]} tokens."

data/lib/rubik/security/redactor.rb

@@ -38,16 +38,20 @@ module Rubik
         return text unless text.is_a?(String)
         return text if text.empty?
 
-        # scrub: redact ham geçmişe (tool çıktısı, prompt) dokunur — geçersiz
-        # UTF-8 gsub!'ı ArgumentError ile düşürür; total olmak maskenin
-        # kendisi bir arıza kaynağı olmasın demektir.
-        result = text.valid_encoding? ? text.dup : text.scrub
+        # PERF: Fast-path for valid encoding strings: test QUICK_CHECK_REGEX
+        # directly on input text before calling dup or scrub. This short-circuits
+        # clean strings without allocating extra intermediate string copies or
+        # running scrub/gsub passes (~2.7x speedup, ~50% fewer allocations).
+        if text.valid_encoding?
+          return text.dup unless text.match?(QUICK_CHECK_REGEX)
 
-        # PERF: kısa devre — sır tetikleyicisi yoksa 11 gsub turu atlanır.
-        # Tetik testi scrub'lanmış sonuç üstünde yapılır: match? ham geçersiz
-        # UTF-8'de ArgumentError düşürür; scrub sonrası metin hep geçerlidir
-        # ve desenler zaten bu metne uygulanıyordu, dolayısıyla eşdeğerdir.
-        return result unless result.match?(QUICK_CHECK_REGEX)
+          result = text.dup
+        else
+          # Fall back safely for invalid UTF-8 / binary strings: scrub first so
+          # match? and gsub! do not raise ArgumentError.
+          result = text.scrub
+          return result unless result.match?(QUICK_CHECK_REGEX)
+        end
 
         # Keep replacement order: masking one credential can expose a word
         # boundary needed to recognize the next (for example, a bearer token).

data/lib/rubik/storage/vakanuvis/gate.rb

@@ -54,8 +54,11 @@ module Rubik
           # hemen ardından doğum denemesi AYRI bir @lock penceresinde
           # (iki fazlı — tek büyük kritik bölüm İÇİNE ALMA). Doğum
           # başarısızsa iş kuyrukta kalır: yarım durum birikmez.
-          # Dönen makbuz dizgesi bayt-bayt eski Harness#digest çıktısıdır.
-          def submit(query)
+          # Dönen makbuz dizgesi bayt-bayt eski Harness#digest çıktısıdır;
+          # submit_with_status aynı kabulü [makbuz, durum] ikilisi olarak
+          # verir (:accepted|:duplicate|:full) — otomatik damıtım red'i
+          # makbuz dizgesinden ayırt edebilsin diye (review #346).
+          def submit_with_status(query, spawn: true)
             target = Vocabulary.wiki_ref(query)
             # v2 §4-V5: aynı hedefli iş zaten kuyrukta ya da uçuştaysa makbuz
             # 'already queued' varyantına düşer — çift doğum yok.
@@ -68,18 +71,20 @@ module Rubik
               :accepted
             end
             if admission == :duplicate
-              return "Digest already queued for '#{target}' (#{AnnalWriter.one_line(query, 60)}): the chronicler is " \
-                     "compiling it — recall it later with vakanuvis(action: 'recall', query: '...')."
+              return ["Digest already queued for '#{target}' (#{AnnalWriter.one_line(query, 60)}): the chronicler is " \
+                      "compiling it — recall it later with vakanuvis(action: 'recall', query: '...').", admission]
             end
             if admission == :full
-              return "Digest not accepted for '#{target}': capacity #{@max_digest_jobs} is full. " \
-                     "Existing jobs are preserved; retry after a digest finishes."
+              return ["Digest not accepted for '#{target}': capacity #{@max_digest_jobs} is full. " \
+                      "Existing jobs are preserved; retry after a digest finishes.", admission]
             end
 
-            spawned = spawn_job!(batch: false)
-            DistillGate.receipt(query: query, target: target, spawned: !spawned.nil?)
+            spawned = spawn ? spawn_job!(batch: false) : nil
+            [DistillGate.receipt(query: query, target: target, spawned: !spawned.nil?), admission]
           end
 
+          def submit(query, spawn: true) = submit_with_status(query, spawn: spawn)[0]
+
           # ---- Seam 2: worker thread'i (Harness#handle_subagent çağırır) ---
 
           # Ham subagent tamamlanma olayı. İş sicilden @lock altında