xonecas.io
60255
Zn

Zoea-Nova / commit 2914760

docs: fix broken links, add missing providers, vim keys, and update known issues

Phase 1.2 of cleanup execution plan (user-facing documentation):

User-Facing Documentation Fixes:
- Fix broken CONTEXT_COMPRESSION.md link in README.md
- Add missing providers to README: ollama-qwen, ollama-qwen-small, zen-nano
- Mark opencode_zen as default provider
- Add vim navigation keys (k/j) to keyboard shortcuts table
- Add vim keys to help screen (↑/↓/k/j)
- Clarify --start-swarm excludes errored myses

Documentation Index Updates:
- Add 19 missing 2026-02-07 reports to documentation/README.md
- Add OpenAI Compatibility reference to architecture section
- Update last-modified date to 2026-02-07

Known Issues Updates (KNOWN_ISSUES.md):
- Add subcategories: State Machine, Prompt System, Testing, TUI, etc.
- Add 5 new issues:
  * Broadcast doesn't start idle myses (High Priority, regression)
  * Myses idle despite pending broadcasts (Medium Priority)
  * TestStateTransition_Running_To_Idle hangs (Medium Priority)
  * Inconsistent JSON rendering in tool messages (Low Priority)
  * TUI integration tests skipped (Low Priority)
- Add 3 new recently resolved items:
  * Goroutine cleanup on exit (2026-02-06)
  * OpenCode Zen 500 errors (2026-02-07)
  * Session ID claim→login loops (2026-02-07)

Known Server Issues Updates (KNOWN_SERVER_ISSUES.md):
- Reorganize into sections: SpaceMolt MCP Server, OpenCode Zen API
- Add OpenCode Zen system-only message crash issue
- Document workaround implementation in openai_common.go
- Reference GitHub issue #8228 and implementation reports

All changes verified with make build.

xonecas2026-02-07 29147609e6f4900d71ed80038e883275bfd6aebc parent c9ecef0

21 files changed

This diff is too big to show in full. The first 1000 lines are below, and every file is listed with its counts.

README.md+8−3
@@ -23,7 +23,7 @@ Zoea-Nova is a high-performance command center designed to orchestrate massive s
2323 - **Tool Calling**: Myses use MCP to interact with SpaceMolt (mine, trade, navigate, etc.)
2424 - **Focus Mode**: View detailed conversation logs for any Mysis
2525 - **Provider Flexibility**: Use local Ollama or remote OpenCode Zen models per-Mysis
26-- **Context Compression**: Sliding window keeps LLM context small for fast inference while full history remains searchable (see [documentation](documentation/CONTEXT_COMPRESSION.md))
26+- **Context Compression**: Sliding window keeps LLM context small for fast inference while full history remains searchable (see [documentation](documentation/architecture/CONTEXT_COMPRESSION.md))
2727 - **Memory Search**: Myses can search past messages and broadcasts to recall older information
2828
2929 ## Terminology
@@ -61,7 +61,7 @@ or
6161 - `--config <path>` - Path to config file (default: `./config.toml` or `~/.zoea-nova/config.toml`)
6262 - `--debug` - Enable debug logging
6363 - `--offline` - Run in offline mode (stub MCP server)
64-- `--start-swarm` - Auto-start all idle myses on launch (default: disabled)
64+- `--start-swarm` - Auto-start all idle myses on launch (excludes errored myses; default: disabled)
6565
6666 ## Creating a Mysis
6767
@@ -70,8 +70,11 @@ Press `n` to create a new mysis. You'll be prompted for:
7070 1. **Name** (required) - Unique identifier for the mysis
7171 2. **Provider** (optional) - Leave empty to use default from config, or specify:
7272 - `ollama` - Local Ollama with qwen3:8b
73+ - `ollama-qwen` - Local Ollama with qwen3:8b
74+ - `ollama-qwen-small` - Local Ollama with qwen3:4b
7375 - `ollama-llama` - Local Ollama with llama3.1:8b
74- - `opencode_zen` - OpenCode Zen with gpt-5-nano
76+ - `opencode_zen` - OpenCode Zen with gpt-5-nano (default)
77+ - `zen-nano` - OpenCode Zen with gpt-5-nano
7578 - `zen-pickle` - OpenCode Zen with big-pickle
7679
7780 The model is determined by the provider's configuration in `config.toml`.
@@ -90,6 +93,8 @@ The model is determined by the provider's configuration in `config.toml`.
9093 | `Enter` | Focus on selected Mysis |
9194 | `Esc` | Return to dashboard |
9295 | `v` | Toggle verbose JSON (focus) |
96+| `k / ↑` | Navigate up / Scroll up |
97+| `j / ↓` | Navigate down / Scroll down |
9398 | `?` | Show help |
9499 | `q` | Quit |
95100
documentation/README.md+46−11
@@ -33,6 +33,7 @@ Core system design and architectural decisions.
3333 - **[Context Compression](architecture/CONTEXT_COMPRESSION.md)** - Memory management and sliding window
3434 - **[Rate Limiting](architecture/RATE_LIMITING_PLAN.md)** - Provider rate limiting strategy
3535 - **[Offline Mode](architecture/OFFLINE_MODE.md)** - Stub MCP server for development
36+- **[OpenAI Compatibility](architecture/OPENAI_COMPATIBILITY.md)** - OpenAI API compliance and provider guidelines
3637
3738 ### `guides/`
3839 How-to guides and reference material for developers and users.
@@ -58,6 +59,25 @@ Active tracking documents (frequently updated).
5859 Completed implementation and analysis reports.
5960
6061 **Recent (2026-02-07):**
62+- **[Cleanup Execution Plan](reports/CLEANUP_EXECUTION_PLAN_2026-02-07.md)** - Phase 1 user-facing docs and quick wins
63+- **[Dead Code Audit](reports/DEAD_CODE_AUDIT_2026-02-07.md)** - Unused code identification and removal
64+- **[Documentation Accuracy Audit](reports/DOCUMENTATION_ACCURACY_AUDIT_2026-02-07.md)** - Verification of docs against codebase
65+- **[Documentation Organization Audit](reports/DOCUMENTATION_ORGANIZATION_AUDIT_2026-02-07.md)** - Structure and navigation improvements
66+- **[Hardcoded Config Audit](reports/HARDCODED_CONFIG_AUDIT_2026-02-07.md)** - Configuration consistency check
67+- **[Import Cleanup](reports/IMPORT_CLEANUP_2026-02-07.md)** - Unused import removal
68+- **[Known Issues Consolidation](reports/KNOWN_ISSUES_CONSOLIDATION_2026-02-07.md)** - Issue tracking organization
69+- **[LLM Behavior Analysis Session ID](reports/LLM_BEHAVIOR_ANALYSIS_SESSION_ID_2026-02-07.md)** - Session ID error investigation
70+- **[Login Flow Verification](reports/LOGIN_FLOW_VERIFICATION_2026-02-07.md)** - Account claiming flow analysis
71+- **[Loop Context Composition](reports/LOOP_CONTEXT_COMPOSITION_IMPLEMENTATION_2026-02-07.md)** - Context building refactor
72+- **[OpenCode Zen Fix](reports/OPENCODE_ZEN_FIX_2026-02-07.md)** - System-only message crash fix
73+- **[Outdated Tests Audit](reports/OUTDATED_TESTS_AUDIT_2026-02-07.md)** - Comprehensive test cleanup recommendations
74+- **[Prompt Reconstruction Tool](reports/PROMPT_RECONSTRUCTION_TOOL_2026-02-07.md)** - Debug tool for LLM prompt analysis
75+- **[Session ID Error Message Audit](reports/SESSION_ID_ERROR_MESSAGE_AUDIT_2026-02-07.md)** - Error message improvement analysis
76+- **[Session ID Loop Fix](reports/SESSION_ID_LOOP_FIX_IMPLEMENTATION_2026-02-07.md)** - Infinite loop fix for session errors
77+- **[Skipped Tests Audit](reports/SKIPPED_TESTS_AUDIT_2026-02-07.md)** - Analysis of t.Skip() tests
78+- **[Test Coverage Gaps](reports/TEST_COVERAGE_GAPS_2026-02-07.md)** - Missing test identification
79+- **[TODO Organization](reports/TODO_ORGANIZATION_2026-02-07.md)** - Task tracking cleanup
80+- **[Turn-Aware Context](reports/TURN_AWARE_CONTEXT_IMPLEMENTATION_2026-02-07.md)** - Context management improvements
6181 - **[ClaimAccount Race Analysis](reports/CLAIM_ACCOUNT_RACE_ANALYSIS_2026-02-07.md)** - Edge case analysis and concurrency safety validation
6282
6383 **Recent (2026-02-06):**
@@ -81,20 +101,10 @@ Completed implementation and analysis reports.
81101 ### `plans/`
82102 Implementation plans for features and fixes.
83103
84-**2026-02-06:**
85-- **[Goroutine Cleanup Fixes](plans/2026-02-06-goroutine-cleanup-fixes.md)** - 8-phase cleanup plan
86-
87104 **2026-02-05:**
88-- **[Broadcast Sender Tracking](plans/2026-02-05-broadcast-sender-tracking.md)**
89-- **[Context Size Logging](plans/2026-02-05-context-size-logging.md)**
90105 - **[Statusbar Tick Timestamps](plans/2026-02-05-statusbar-tick-timestamps.md)**
91106 - **[TUI Enhancements](plans/2026-02-05-tui-enhancements.md)**
92107
93-**2026-02-04:**
94-- **[Captain's Log Bug](plans/2026-02-04-captains-log-bug.md)**
95-- **[Context Compaction](plans/2026-02-04-context-compaction-plan.md)**
96-- **[Tool Payload Bloat](plans/2026-02-04-remove-tool-payload-bloat.md)**
97-
98108 **Milestone Plans:**
99109 - **[UI Fixes for RC](plans/ui-fixes-for-rc.md)**
100110 - **[V1 Complete](plans/v1-complete.md)**
@@ -113,6 +123,31 @@ See `investigations/README.md` for details.
113123 ### `archive/`
114124 Historical investigations and reports (completed, superseded, or obsolete).
115125
126+**Completed Plans (2026-02-04 to 2026-02-07):**
127+- **[Loop Context Checklist](archive/2026-02-07-loop-context-checklist.md)** - Completed
128+- **[Loop Context Composition](archive/2026-02-07-loop-context-composition.md)** - Completed
129+- **[Loop Context Parallel Workflow](archive/2026-02-07-loop-context-parallel-workflow.md)** - Completed
130+- **[Loop Context README](archive/2026-02-07-loop-context-README.md)** - Completed
131+- **[Loop Context Workflow Diagram](archive/2026-02-07-loop-context-workflow-diagram.md)** - Completed
132+- **[Goroutine Cleanup Fixes](archive/2026-02-06-goroutine-cleanup-fixes.md)** - Completed
133+- **[Broadcast Sender Tracking](archive/2026-02-05-broadcast-sender-tracking.md)** - Completed
134+- **[Context Size Logging](archive/2026-02-05-context-size-logging.md)** - Completed
135+- **[Captain's Log Bug](archive/2026-02-04-captains-log-bug.md)** - Completed
136+- **[Context Compaction](archive/2026-02-04-context-compaction-plan.md)** - Completed
137+- **[Tool Payload Bloat](archive/2026-02-04-remove-tool-payload-bloat.md)** - Completed
138+
139+**Resolved Investigations (2026-02-06 to 2026-02-07):**
140+- **[OpenCode Zen API Tests](archive/OPENCODE_ZEN_API_TESTS_2026-02-06.md)** - System-only message bug confirmed
141+- **[OpenCode Zen Bug Verdict](archive/OPENCODE_ZEN_BUG_VERDICT_2026-02-06.md)** - API limitation verified
142+- **[Real Provider Race Investigation](archive/AGENT6_REAL_PROVIDER_RACE_INVESTIGATION.md)** - Race condition resolved
143+
144+**Restart Bug Investigation Reports (2026-02-06):**
145+- **[Restart Bug Index](archive/RESTART_BUG_INDEX.md)** - Investigation coordination
146+- **[Goroutine Cleanup Verification](archive/AGENT7_GOROUTINE_CLEANUP_VERIFICATION.md)** - Cleanup order verified
147+- **[Race Reproduction Report](archive/AGENT_3_RACE_REPRODUCTION_REPORT.md)** - Race condition reproduced
148+- **[Timing Test Report](archive/TIMING_TEST_REPORT.md)** - Timing analysis
149+- **[State Machine Test Report](archive/STATE_MACHINE_TEST_REPORT.md)** - State transition analysis
150+
116151 **Superseded Investigations:**
117152 - **[Auto-Scroll Investigation](archive/AUTO_SCROLL_INVESTIGATION.md)** - Replaced by reports/SMART_AUTO_SCROLL_IMPLEMENTATION.md
118153 - **[Cleanup Order Analysis](archive/CLEANUP_ORDER_ANALYSIS.md)** - Implemented in commit 4613e12
@@ -196,4 +231,4 @@ Historical investigations and reports (completed, superseded, or obsolete).
196231
197232 ---
198233
199-Last updated: 2026-02-06
234+Last updated: 2026-02-07
documentation/architecture/CONTEXT_COMPRESSION.md+12−9
@@ -22,7 +22,8 @@ Without compression, Mysis context grows unbounded:
2222 ├─────────────────────────────────────────────────────┤
2323 │ [1] System Prompt (always first) │
2424 ├─────────────────────────────────────────────────────┤
25-│ [2] Prompt Source (chosen by priority) │
25+│ [2] Current Turn Start │
26+│ Selected by recency (most recent wins): │
2627 │ • Commander direct message │
2728 │ • Last commander broadcast │
2829 │ • Last swarm broadcast │
@@ -54,13 +55,15 @@ The most recent loop slice is always included in context to maintain tool-callin
5455
5556 ### Prompt Source Priority
5657
57-Prompt sources are user messages that drive Mysis behavior. Priority order:
58+Prompt sources are user messages that drive Mysis behavior and mark the start of the current turn. Selection order (most recent message wins):
5859
59-1. **Commander direct message** (`source="direct"`) - Highest priority, always used if present
60+1. **Commander direct message** (`source="direct"`) - Direct command from user
6061 2. **Last commander broadcast** (`source="broadcast"`, `sender_id=""`) - Commander identified by empty sender_id
6162 3. **Last swarm broadcast** (`source="broadcast"`, `sender_id!=""`) - Most recent broadcast from another Mysis
6263 4. **Synthetic nudge** (generated, not stored) - Fallback when no prompt sources exist
6364
65+See [Terminology](#terminology) for definitions of turn boundaries and context composition.
66+
6467 ### Context Composition Algorithm
6568
6669 ```go
@@ -78,14 +81,14 @@ func (m *Mysis) getContextMemories() ([]*store.Memory, error) {
7881 result.append(system)
7982 }
8083
81- // Step 2: Select prompt source by priority
82- promptSource := selectPromptSource(allMemories)
83- if promptSource == nil {
84+ // Step 2: Find current turn boundary (most recent user message)
85+ turnStart := selectPromptSource(allMemories)
86+ if turnStart == nil {
8487 // Generate synthetic nudge (not stored in DB)
8588 nudge := createEphemeralNudge()
8689 result.append(nudge)
8790 } else {
88- result.append(promptSource)
91+ result.append(turnStart)
8992 }
9093
9194 // Step 3: Extract latest tool loop
@@ -312,8 +315,8 @@ func (s *Store) SearchBroadcasts(query string, limit int) ([]*BroadcastMessage,
312315
313316 The loop slice model has minimal tuning surface:
314317
315-- **`MaxContextMessages`**: Scanning window for finding prompt sources and tool loops. Larger values increase DB query cost but provide more history to search. Default: 20 messages (~2 server ticks).
316-- **Prompt source priority**: Fixed order defined by game design (commander > broadcasts > nudge).
318+- **`MaxContextMessages`**: Scanning window for finding turn boundaries and tool loops. Larger values increase DB query cost but provide more history to search. Default: 20 messages (~2 server ticks).
319+- **Turn boundary selection**: Most recent user message wins (commander direct > commander broadcast > swarm broadcast > nudge).
317320 - **Nudge intervals**: Control how often idle Myses are prompted. Faster intervals increase responsiveness but may interrupt LLM processing.
318321
319322 ## Migration Notes
documentation/archive/README.md+32−1
@@ -18,6 +18,37 @@ This directory contains documentation that:
1818
1919 ## Categories
2020
21+### Completed Plans (2026-02-04 to 2026-02-07)
22+Implementation plans that were executed and completed.
23+
24+- **2026-02-07-loop-context-checklist.md** - Completed
25+- **2026-02-07-loop-context-composition.md** - Completed
26+- **2026-02-07-loop-context-parallel-workflow.md** - Completed
27+- **2026-02-07-loop-context-README.md** - Completed
28+- **2026-02-07-loop-context-workflow-diagram.md** - Completed
29+- **2026-02-06-goroutine-cleanup-fixes.md** - Completed
30+- **2026-02-05-broadcast-sender-tracking.md** - Completed
31+- **2026-02-05-context-size-logging.md** - Completed
32+- **2026-02-04-captains-log-bug.md** - Completed
33+- **2026-02-04-context-compaction-plan.md** - Completed
34+- **2026-02-04-remove-tool-payload-bloat.md** - Completed
35+
36+### Resolved Investigations (2026-02-06 to 2026-02-07)
37+Investigations that identified and resolved specific issues.
38+
39+- **OPENCODE_ZEN_API_TESTS_2026-02-06.md** - System-only message bug confirmed
40+- **OPENCODE_ZEN_BUG_VERDICT_2026-02-06.md** - API limitation verified
41+- **AGENT6_REAL_PROVIDER_RACE_INVESTIGATION.md** - Race condition resolved
42+
43+### Restart Bug Investigation Reports (2026-02-06)
44+Series of reports investigating async race conditions during mysis restart.
45+
46+- **RESTART_BUG_INDEX.md** - Investigation coordination
47+- **AGENT7_GOROUTINE_CLEANUP_VERIFICATION.md** - Cleanup order verified
48+- **AGENT_3_RACE_REPRODUCTION_REPORT.md** - Race condition reproduced
49+- **TIMING_TEST_REPORT.md** - Timing analysis
50+- **STATE_MACHINE_TEST_REPORT.md** - State transition analysis
51+
2152 ### Superseded Investigations
2253 Investigations that led to implementations (code now shipped).
2354
@@ -77,4 +108,4 @@ Early development phase reports (no longer relevant for current work).
77108
78109 ---
79110
80-Last updated: 2026-02-06
111+Last updated: 2026-02-07
documentation/current/KNOWN_ISSUES.md+45−7
@@ -4,21 +4,53 @@ Active todo list of known issues, bugs, and planned improvements for Zoea Nova.
44
55 ## High Priority
66
7-None currently.
7+### State Machine / Broadcast System
8+- [ ] **REGRESSION: Broadcast doesn't start idle myses** - Broadcasting to idle myses doesn't trigger Start()
9+ - **Impact:** Idle myses don't respond to broadcasts
10+ - **Root Cause:** State machine allows broadcasts to idle state (commit f7797cc) without triggering Start()
11+ - **Action:** Verify behavior, add test coverage, fix
12+ - **Test Coverage Gap:** No integration test for broadcast → idle → running transition
813
914 ## Medium Priority
1015
16+### Prompt System
17+- [ ] **Myses idle despite pending broadcasts** - Myses transition to idle even when broadcasts are queued
18+ - **Impact:** Broadcasts not consumed as user messages, lost communication
19+ - **Root Cause:** ContinuePrompt doesn't check broadcast queue before idling
20+ - **Action:** Modify idle transition logic to check message queue
21+
22+### Testing / Concurrency
23+- [ ] **TestStateTransition_Running_To_Idle hangs** - Test hangs during cleanup
24+ - **Location:** `internal/core/state_machine_test.go:260`
25+ - **Skip Reason:** "Goroutine not exiting after idle transition"
26+ - **Action:** Investigate potential goroutine leak in idle transition
27+
1128 ## Low Priority
1229
30+### TUI / Rendering
31+- [ ] **Exit splash screen** - Display branding, connection cleanup status, and animated loading bar during shutdown
32+ - **Trigger:** User presses q/ESC/CTRL+C
33+ - **Purpose:** Provide visual feedback during graceful shutdown
34+ - **Needs:** Splash screen design with loading animation
35+
36+- [ ] **Inconsistent JSON rendering in tool messages** - Some tool results render as raw text with tool call ID prefix
37+ - **Example:** `chatcmpl-tool-XXX:{"player": {...}}` instead of tree view
38+ - **Location:** `internal/tui/focus.go` - `renderLogEntry()`
39+ - **Action:** Audit JSON detection logic for consistency
40+
41+### Testing / Coverage
42+- [ ] **TUI integration tests skipped (config setup)** - Two tests skipped due to missing provider config
43+ - **Tests:** `TestIntegration_NewMysisInput`, `TestIntegration_CreateAndStartMysis`
44+ - **Root Cause:** Tests need temp config file after DefaultConfig() removal (commit 068a5a6)
45+ - **Action:** Update tests to use setupTUITest() pattern from tui_test.go:32-56
46+
1347 ### Provider Reliability
1448 - [ ] **Investigate Ollama timeout errors** - Occasional "context deadline exceeded" errors when calling Ollama chat completions
1549 - **Error:** `Post "http://localhost:11434/v1/chat/completions": context deadline exceeded`
1650 - **Needs:** Root cause analysis (model size, request timeout configuration, rate limiting interaction)
1751 - **Recent evidence (2026-02-05):** Ollama logs show prompt truncation (`limit=32768`, `prompt=41611`) followed by bursts of `400` responses on `/v1/chat/completions` and one `500` response. No corresponding errors in `~/.zoea-nova/zoea.log`.
1852
19-
2053 ### Documentation & Tooling
21-
2254 - [ ] **Add plan enforcement command** - OpenCode slash command to require plan/todo creation before implementation
2355 - **Purpose:** Enforce workflow discipline for complex changes
2456
@@ -27,7 +59,7 @@ None currently.
2759
2860 ### Operations
2961 - [ ] **Validate game server API changes** - Monitor and validate MCP and SpaceMolt game server updates for breaking changes
30- - **Reference:** `documentation/KNOWN_SERVER_ISSUES.md`
62+ - **Reference:** `documentation/current/KNOWN_SERVER_ISSUES.md`
3163 - **Process:** Periodic checks against upstream API
3264
3365 ---
@@ -38,7 +70,7 @@ None currently.
3870
3971 - [x] **Testing coverage expansion** (2026-02-05) - Added config validation tests (11 subtests), provider error handling tests, HTTP mocking for tool calls, MCP proxy tests, and concurrent write benchmark (p50: 0.3ms, p99: 1.9ms).
4072
41-- [x] **Memory growth analysis** (2026-02-05) - Documented memory growth rate (279 memories/hour, 0.96 MB/hour DB growth). DB size is not a concern for v1. See `documentation/MEMORY_GROWTH_REPORT.md`.
73+- [x] **Memory growth analysis** (2026-02-05) - Documented memory growth rate (279 memories/hour, 0.96 MB/hour DB growth). DB size is not a concern for v1. See `documentation/reports/MEMORY_GROWTH_REPORT.md`.
4274
4375 - [x] **Ollama reliability investigation** (2026-02-05) - Analyzed 24h of Ollama logs. Found 65 HTTP 500s, 19 HTTP 400s, 3 prompt truncations, 23 client disconnects. Evidence documented in KNOWN_ISSUES.md for future investigation.
4476
@@ -52,6 +84,12 @@ None currently.
5284
5385 - [x] **Tool payload bloat removal** (2026-02-04) - Removed `provider` and `state` fields from MysisInfo struct and `zoea_list_myses` tool payload. Added `GetStateCounts()` method to Commander for `zoea_swarm_status`. Saves ~22 tokens per mysis, ~352 tokens for full swarm (16 myses).
5486
55-- [x] **Context snapshot compaction** (2026-02-04) - Implemented snapshot compaction in `getContextMemories()` to keep only most recent result for each snapshot tool (get_ship, get_system, get_poi, get_nearby, get_cargo, zoea_swarm_status, zoea_list_myses). Added search tool reminders to SystemPrompt and ContinuePrompt. See `documentation/CONTEXT_COMPRESSION.md` for details.
87+- [x] **Context snapshot compaction** (2026-02-04) - Implemented snapshot compaction in `getContextMemories()` to keep only most recent result for each snapshot tool (get_ship, get_system, get_poi, get_nearby, get_cargo, zoea_swarm_status, zoea_list_myses). Added search tool reminders to SystemPrompt and ContinuePrompt. See `documentation/architecture/CONTEXT_COMPRESSION.md` for details.
88+
89+- [x] **Database reset with account backup** (2026-02-05) - Added `make db-reset-accounts` target to safely wipe database while preserving account credentials via export/import cycle.
90+
91+- [x] **Goroutine cleanup on exit** (2026-02-06) - Fixed terminal hangs and errored state on quit. Implemented complete goroutine cleanup with timeouts, WaitGroup tracking, and graceful shutdown sequence. See `documentation/plans/2026-02-06-goroutine-cleanup-fixes.md`.
92+
93+- [x] **OpenCode Zen 500 errors** (2026-02-07) - Fixed system-only message crashes, added Stream parameter, improved message merging, added validation. See `documentation/reports/OPENCODE_ZEN_FIX_2026-02-07.md`.
5694
57-- [x] **Database reset with account backup** - Added `make db-reset-accounts` target to safely wipe database while preserving account credentials via export/import cycle.
95+- [x] **Session ID claim→login loops** (2026-02-07) - Fixed infinite loops caused by session_required errors. Added prompt reinforcement and error message interception. See `documentation/reports/SESSION_ID_LOOP_FIX_IMPLEMENTATION_2026-02-07.md`.
documentation/current/KNOWN_SERVER_ISSUES.md+74−3
@@ -1,8 +1,12 @@
11 # Known SpaceMolt Server Issues
22
3-This document tracks known issues with the upstream SpaceMolt MCP server API. We do not modify or validate the game server's API behavior. Issues are documented here, and we improve prompts and error handling instead.
3+This document tracks known issues with upstream APIs (SpaceMolt MCP server, OpenCode Zen). We do not modify or validate external API behavior. Issues are documented here, and we improve prompts, error handling, and workarounds instead.
44
5-## captains_log_add: empty_entry Error
5+---
6+
7+## SpaceMolt MCP Server Issues
8+
9+### captains_log_add: empty_entry Error
610
711 **Issue:** The `captains_log_add` tool returns an `empty_entry` error when:
812 - The `entry` field is an empty string
@@ -18,7 +22,9 @@ This document tracks known issues with the upstream SpaceMolt MCP server API. We
1822 - System prompt includes explicit examples of correct usage
1923 - Error messages provide actionable guidance when this error occurs
2024
21-## ~~get_notifications: Missing current_tick Field~~ ✅ RESOLVED
25+---
26+
27+### ~~get_notifications: Missing current_tick Field~~ ✅ RESOLVED
2228
2329 **Status:** ✅ **RESOLVED** in server v0.44.4
2430
@@ -53,3 +59,68 @@ Prior to v0.44.4, the `get_notifications` endpoint did not return tick informati
5359 For historical investigation details, see:
5460 - `documentation/investigations/GET_NOTIFICATIONS_API_INVESTIGATION.md`
5561 - `documentation/investigations/TICK_INVESTIGATION_FINDINGS.md`
62+
63+---
64+
65+## OpenCode Zen API Issues
66+
67+### OpenCode Zen: System-Only Message Crash
68+
69+**Issue:** The OpenCode Zen API returns a 500 Internal Server Error when request messages contain ONLY system messages (no user or assistant turns).
70+
71+**Server Response:**
72+```json
73+{
74+ "type": "error",
75+ "error": {
76+ "type": "error",
77+ "message": "Cannot read properties of undefined (reading 'prompt_tokens')"
78+ }
79+}
80+```
81+
82+**Root Cause:**
83+OpenCode Zen's token counting logic fails when response metadata is missing or in unexpected format. The API attempts to read token counts from an undefined object, indicating an unhandled null/undefined case in their response parsing.
84+
85+**Related Issue:**
86+OpenCode GitHub Issue #8228: Similar token counting crash with Gemini models
87+- URL: https://github.com/anomalyco/opencode/issues/8228
88+- Error: `"Cannot read properties of undefined (reading 'promptTokenCount')"`
89+- Status: OPEN (as of 2026-02-07)
90+
91+**Workaround:**
92+Zoea Nova implements fallback logic in `internal/provider/openai_common.go`:
93+- Detects system-only message arrays
94+- Appends fallback user message: `{"role": "user", "content": "Continue."}`
95+- Prevents hitting the upstream API bug
96+
97+**Implementation:**
98+```go
99+// If only system messages remain, add a dummy user message
100+if allMessagesAreSystem {
101+ messages = append(messages, openAIMessage{
102+ Role: "user",
103+ Content: "Continue.",
104+ })
105+}
106+```
107+
108+**Status:** ✅ **WORKAROUND IMPLEMENTED**
109+
110+**Resolution Date:** 2026-02-07
111+**Implementation:** Commit `9348f50` - fix: improve system message merging to preserve conversation
112+
113+**Impact on Zoea Nova:**
114+- OpenCode Zen provider sends valid API requests
115+- Conversation history preserved correctly
116+- Message validation prevents invalid API calls
117+- Provider coverage: 87.0%
118+
119+**Monitoring:**
120+- Watch OpenCode issue tracker for upstream fix
121+- Keep workaround in place until server-side bug is resolved
122+- No Zoea Nova code changes needed if upstream fixes issue
123+
124+For implementation details, see:
125+- `documentation/investigations/OPENCODE_ZEN_BUG_VERDICT_2026-02-06.md`
126+- `documentation/reports/OPENCODE_ZEN_FIX_2026-02-07.md`
documentation/current/TODO.md+3−57
@@ -13,62 +13,11 @@
1313
1414 ---
1515
16-- REGRESSION: broadcast doesn't start idle myses. test coverage gap!!
16+- Myses become idle even when there are broadcasts from both commander and other mysis. Broadcasts should be sent as user messages to keep myses active.
1717
18-- include most recent comander broadcast if exits in nudges.
18+- When nudging idle myses, encourage use of broadcasts to restart other idle myses in the swarm.
1919
20-- myses become idle even when a broadcasts.
21-
22-- Auto start mysis on app start: make it into an option `--start-swarm`, default off.
23-- default provider/model selection:
24- - update new mysis flow to prompt for config values, provider and model
25- - name is required, provider can be empty. If it is empty then use the default provider and model.
26- - if a provider was chosen, model becomes required (to ensure provider->model relation)
27- - add default provider and model to the config file. (config.toml)
28-
29-- Investigate
30-
31-```
32- T0 ⬡ [05:49] TOOL: ───────────────────────────────────────────────────────────────── │
33- call_nhgyw9u8:Error calling zoea_broadcast: broadcast failed: │
34- broadcast failed for 1 mysis: mysis │
35- 378f805e-be8e-48ee-97f4-d3594d512286: mysis stopped - press 'r' │
36- to relaunch
37- [...]
38-
39- and raw json in tui
40-
41- T10462 ⬡ [08:00] AI: ──────────────────────────────────────────────────────────────────────────────────────────────── │
42- ⚡ Calling tools: │
43- • get_status(session_id: "d5d2f6c5bc8d0c113e45fb0c6c3fe2cd") │
44- │
45- T10462 ⬡ [08:00] TOOL: ────────────────────────────────────────────────────────────────────────────────────────────── │
46- chatcmpl-tool-8b4ad55fe5e842ef8fb65e63e221ff52:{ │
47- "player": { │
48- "id": "756c1c972b8699e25275318aea0a8c45", │
49- "username": "CrabZoea", │
50- "empire": "voidborn", │
51- "credits": 814, │
52- "created_at": "2026-02-06T02:30:30.808969221Z", │
53- "last_login_at": "2026-02-07T07:57:45.771921803Z", │
54- "last_active_at": "2026-02-07T07:58:47.315025653Z", │
55- "status_message": "", │
56- "clan_tag": "", │
57- "primary_color": "", │
58- "secondary_color": "", │
59- "anonymous": false, │
60- "is_cloaked": false, │
61- "current_ship_id": "e52832c032e5dc043e8e127f8d301150", │
62- "current_system": "nexus",
63-```
64-
65-- When the app is exiting, as the user presses `q` or `ESC` or `CTRL+C`, show a splash screen with branding, a text saying the app is closing connections and animated infinite loading bar, once connections are cleaned up, exit.. So the users knows what he is waiting for.
66-
67-- tool messages need JSON rendering properly
68-
69-- when nudging, encourage broadcast to restart other idle mysis
70-
71-> RELEASE CUTOFF ----~ 8< ~----
20+> RELEASE CUTOFF ----~ 8< ~---- STOP HERE **DON'T TOUCH** ----~ 8< ~----
7221
7322 - Refactor Help/controls pannel and error message displays in TUI.
7423 - Compact all controls in one help panel, show only [HELP h/H] on the right edge of the line.
@@ -78,9 +27,6 @@
7827
7928 - when run with -debug, reset the log file for a clean run.
8029
81-- call\_-7908546343142072217:Error calling zoea_broadcast: broadcast failed: broadcast failed for 2
82- Broadcast should never fail. Commander counts as online in broadcast.
83-
8430 Follow-up (optional):
8531
8632 1. Clean up skipped tests (8 tests with documented rationale)
documentation/investigations/README.md+11−8
@@ -4,20 +4,23 @@ This folder contains investigation reports for issues both active and resolved.
44
55 ## Active Investigations
66
7-### OpenCode Zen API System-Only Messages Bug
7+None currently.
88
9-**Issue:** OpenCode Zen API returns `"Cannot read properties of undefined (reading 'input_tokens')"` error when messages contain only system messages (no user or assistant turns).
9+---
1010
11-**Investigation Documents:**
12-- `OPENCODE_ZEN_API_TESTS_2026-02-06.md` - Direct curl testing proving system-only requests crash
11+## Resolved Issues
1312
14-**Status:** Confirmed as API limitation. Workaround implemented in `internal/provider/opencode.go` (fallback to add dummy user message).
13+### OpenCode Zen API System-Only Messages Bug
1514
16-**Next Steps:** Consider reporting to OpenCode team.
15+**Issue:** OpenCode Zen API returns `"Cannot read properties of undefined (reading 'input_tokens')"` error when messages contain only system messages (no user or assistant turns).
1716
18----
17+**Resolution Date:** 2026-02-07
18+**Resolution:** Workaround implemented in `internal/provider/opencode.go` (fallback to add dummy user message).
1919
20-## Resolved Issues
20+**Investigation Documents:**
21+- `archive/OPENCODE_ZEN_API_TESTS_2026-02-06.md` - Direct curl testing proving system-only requests crash
22+- `archive/OPENCODE_ZEN_BUG_VERDICT_2026-02-06.md` - API limitation verified
23+- `reports/OPENCODE_ZEN_FIX_2026-02-07.md` - Implementation report
2124
2225 ### get_notifications Missing Tick Field
2326
documentation/plans/2026-02-07-codebase-cleanup-workflow.md+452−0
@@ -0,0 +1,452 @@
1+# Codebase and Documentation Cleanup Workflow
2+
3+> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
4+
5+**Goal:** Remove dead code, fix outdated tests, reorganize documentation, consolidate known issues, and organize TODO.md using 10 autonomous agents working in parallel.
6+
7+**Architecture:** Split work into 10 independent audit tasks executed by parallel agents, each producing a report with recommended deletions/moves/merges, then execute all changes in a single verification phase.
8+
9+**Tech Stack:** Go 1.22, ripgrep, git, markdown
10+
11+---
12+
13+## Phase 1: Parallel Code Audits (10 Agents)
14+
15+Each agent audits a specific area and produces a report with actionable recommendations.
16+
17+---
18+
19+### Agent 1: Dead Code Detection
20+
21+**Task:** Find unused functions, variables, and imports in production code.
22+
23+**Search for:**
24+- Unexported functions with no references
25+- Unused constants
26+- Commented-out code blocks
27+- Imports marked as unused by LSP
28+
29+**Exclude:**
30+- Test files (*_test.go)
31+- Exported functions (may be used externally)
32+
33+**Output:** `reports/DEAD_CODE_AUDIT_2026-02-07.md` with:
34+- List of dead code with file:line
35+- Reason it's unused (no references found)
36+- Recommended deletion
37+
38+**Verification command:**
39+```bash
40+rg "functionName" --type go
41+```
42+
43+---
44+
45+### Agent 2: Skipped and Disabled Tests
46+
47+**Task:** Find all skipped tests and determine if they should be enabled or removed.
48+
49+**Search for:**
50+- `t.Skip()`
51+- `t.SkipNow()`
52+- `// TODO: test`
53+- `// FIXME: test`
54+- Commented-out test functions
55+
56+**Output:** `reports/SKIPPED_TESTS_AUDIT_2026-02-07.md` with:
57+- List of skipped tests with reason
58+- Recommendation: enable, fix, or remove
59+- Estimated effort to fix
60+
61+**Verification:**
62+```bash
63+rg "t\.Skip|SkipNow" --type go
64+```
65+
66+---
67+
68+### Agent 3: Outdated Test Logic
69+
70+**Task:** Find tests that verify removed or changed functionality.
71+
72+**Search for:**
73+- Tests referencing removed functions (zoea_swarm_status, selectPromptSource, DefaultConfig)
74+- Tests using old architecture (loop-based context vs turn-aware)
75+- Tests with hardcoded provider names that should be dynamic
76+
77+**Cross-reference:**
78+- Recent commits removing features
79+- Architecture changes in reports/
80+
81+**Output:** `reports/OUTDATED_TESTS_AUDIT_2026-02-07.md` with:
82+- Tests that need updating
83+- What changed that invalidates them
84+- Recommended fix or removal
85+
86+**Verification:**
87+```bash
88+git log --oneline --since="2026-02-06" | grep "remove\|delete\|refactor"
89+```
90+
91+---
92+
93+### Agent 4: Hardcoded Config References
94+
95+**Task:** Find remaining hardcoded provider/model references that should use config.
96+
97+**Search for:**
98+- String literals: "ollama", "opencode_zen" in non-provider implementation files
99+- Hardcoded model names in validation
100+- Provider switch statements
101+
102+**Exclude:**
103+- internal/provider/*.go (provider implementations)
104+- Test files (allowed to use hardcoded fixtures)
105+
106+**Output:** `reports/HARDCODED_CONFIG_AUDIT_2026-02-07.md` with:
107+- Hardcoded values with location
108+- Should be dynamic or is acceptable
109+- Recommended fix
110+
111+**Verification:**
112+```bash
113+rg '"ollama"|"opencode_zen"' --type go | grep -v "_test.go" | grep -v "internal/provider"
114+```
115+
116+---
117+
118+### Agent 5: Documentation File Organization
119+
120+**Task:** Audit documentation/ directory for misplaced, duplicate, or outdated files.
121+
122+**Check:**
123+- Files in wrong directories (plans in reports/, reports in investigations/)
124+- Duplicate information across files
125+- Outdated reports superseded by newer implementations
126+- Missing index entries in documentation/README.md
127+
128+**Output:** `reports/DOCUMENTATION_ORGANIZATION_AUDIT_2026-02-07.md` with:
129+- Files to move (source → destination)
130+- Files to merge (list duplicates)
131+- Files to archive
132+- Index updates needed
133+
134+**Verification:**
135+```bash
136+ls -R documentation/
137+```
138+
139+---
140+
141+### Agent 6: Known Issues Consolidation
142+
143+**Task:** Consolidate KNOWN_ISSUES.md, KNOWN_SERVER_ISSUES.md, and issues scattered in other docs.
144+
145+**Check:**
146+- Issues mentioned in multiple places
147+- Fixed issues still listed as known issues
148+- Server issues that should be in KNOWN_SERVER_ISSUES.md
149+- Issues in reports/ that should be in KNOWN_ISSUES.md
150+
151+**Cross-reference:**
152+- Recent commits fixing issues
153+- Git history for "fix:" commits
154+
155+**Output:** `reports/KNOWN_ISSUES_CONSOLIDATION_2026-02-07.md` with:
156+- Issues to remove (fixed)
157+- Issues to add (found in other docs)
158+- Issues to move (wrong file)
159+- Proposed new KNOWN_ISSUES.md structure
160+
161+**Verification:**
162+```bash
163+git log --oneline --grep="fix:" --since="2026-02-05"
164+```
165+
166+---
167+
168+### Agent 7: TODO.md Organization
169+
170+**Task:** Organize TODO.md into categories and remove completed items.
171+
172+**Check:**
173+- Completed items (marked with [x] or mentioned in recent commits)
174+- Duplicate items
175+- Vague items without clear success criteria
176+- Items that should be issues in KNOWN_ISSUES.md instead
177+
178+**Output:** `reports/TODO_ORGANIZATION_2026-02-07.md` with:
179+- Items to remove (completed)
180+- Items to move to KNOWN_ISSUES.md
181+- Items to clarify
182+- Proposed new TODO.md structure with categories
183+
184+**Verification:**
185+```bash
186+git log --oneline --since="2026-02-05" | grep -i "session\|context\|prompt"
187+```
188+
189+---
190+
191+### Agent 8: Test Coverage Gaps
192+
193+**Task:** Find production code without test coverage.
194+
195+**Check:**
196+- Functions in internal/ without corresponding tests
197+- Critical paths (CreateMysis, SendMessage, getContextMemories) test coverage
198+- Error paths not tested
199+
200+**Output:** `reports/TEST_COVERAGE_GAPS_2026-02-07.md` with:
201+- Functions without tests
202+- Critical paths with insufficient coverage
203+- Recommended tests to add (with priority)
204+
205+**Verification:**
206+```bash
207+go test ./... -cover
208+```
209+
210+---
211+
212+### Agent 9: Import Cleanup
213+
214+**Task:** Find unused imports and missing imports across codebase.
215+
216+**Check:**
217+- LSP diagnostics for unused imports
218+- Missing imports causing build failures
219+- Imports that could be stdlib instead of external
220+
221+**Output:** `reports/IMPORT_CLEANUP_2026-02-07.md` with:
222+- Files with unused imports
223+- Recommended removals
224+- Build verification commands
225+
226+**Verification:**
227+```bash
228+go build ./...
229+```
230+
231+---
232+
233+### Agent 10: Documentation Accuracy Audit
234+
235+**Task:** Verify documentation matches current implementation.
236+
237+**Check:**
238+- README.md - keyboard shortcuts, features, providers
239+- AGENTS.md - terminology, architecture, workflow
240+- architecture/*.md - diagrams, state machines, compression strategy
241+- guides/*.md - configuration examples, terminal requirements
242+
243+**Cross-reference:**
244+- Current code (keyboard mappings, features)
245+- Recent architectural changes (turn-aware context)
246+- Provider list (config.toml)
247+
248+**Output:** `reports/DOCUMENTATION_ACCURACY_AUDIT_2026-02-07.md` with:
249+- Inaccurate documentation with corrections
250+- Missing documentation
251+- Outdated examples
252+- Recommended updates
253+
254+**Verification:**
255+```bash
256+diff <(actual_code) <(documented_behavior)
257+```
258+
259+---
260+
261+## Phase 2: Consolidation and Review
262+
263+**Task:** Merge all 10 audit reports into execution plan.
264+
265+**Agent:** Single coordinator agent
266+
267+**Actions:**
268+1. Read all 10 audit reports
269+2. Identify conflicts (same file edited by multiple audits)
270+3. Prioritize changes (critical fixes first)
271+4. Create consolidated change list
272+5. Group by file for efficient editing
273+
274+**Output:** `reports/CLEANUP_EXECUTION_PLAN_2026-02-07.md` with:
275+- Ordered list of all changes
276+- File-by-file change groups
277+- Conflict resolutions
278+- Estimated time per change
279+
280+---
281+
282+## Phase 3: Execution (Batched by File)
283+
284+**Task:** Execute all changes in file-batched order.
285+
286+**Agent:** Single execution agent
287+
288+**Process:**
289+1. For each file with changes:
290+ - Read current state
291+ - Apply all changes to that file
292+ - Run relevant tests
293+ - Commit if tests pass
294+ - Rollback if tests fail
295+
296+**Safety:**
297+- One file at a time
298+- Test after each file change
299+- Commit frequently
300+- Stop on first failure
301+
302+**Commands:**
303+```bash
304+# For each change batch
305+go test ./path/to/affected/package -v
306+git add file.go
307+git commit -m "cleanup: [description]"
308+```
309+
310+---
311+
312+## Phase 4: Documentation Reorganization
313+
314+**Task:** Move/merge/archive documentation files.
315+
316+**Agent:** Documentation agent
317+
318+**Actions:**
319+1. Execute moves (investigation → archive, etc.)
320+2. Merge duplicate content
321+3. Update documentation/README.md index
322+4. Update cross-references
323+5. Verify no broken links
324+
325+**Verification:**
326+```bash
327+rg "]\(.*\.md\)" documentation/ --only-matching | sort | uniq
328+```
329+
330+---
331+
332+## Phase 5: Final Verification
333+
334+**Task:** Verify entire codebase after cleanup.
335+
336+**Agent:** Verification agent
337+
338+**Checks:**
339+1. Full test suite passes
340+2. Build succeeds
341+3. No dead code remains
342+4. No skipped tests (unless documented)
343+5. Documentation accurate
344+6. TODO.md organized
345+7. KNOWN_ISSUES.md complete
346+
347+**Commands:**
348+```bash
349+make test
350+make build
351+go vet ./...
352+```
353+
354+**Output:** `reports/CLEANUP_VERIFICATION_2026-02-07.md` with:
355+- Test results
356+- Build status
357+- Remaining issues (if any)
358+- Cleanup statistics (lines removed, files moved, etc.)
359+
360+---
361+
362+## Success Criteria
363+
364+**Code:**
365+- [ ] No dead code in production files
366+- [ ] No skipped tests without documentation
367+- [ ] No tests for removed functionality
368+- [ ] No hardcoded config outside provider implementations
369+- [ ] All tests passing
370+- [ ] Clean build
371+
372+**Documentation:**
373+- [ ] All files in correct directories
374+- [ ] No duplicate content
375+- [ ] KNOWN_ISSUES.md accurate and complete
376+- [ ] TODO.md organized by category
377+- [ ] Index up to date
378+- [ ] No broken links
379+
380+---
381+
382+## Rollback Plan
383+
384+If Phase 5 verification fails:
385+
386+```bash
387+# List commits from cleanup
388+git log --oneline --since="[start_time]"
389+
390+# Revert all cleanup commits
391+git revert [commit_range]
392+
393+# Or reset to before cleanup
394+git reset --hard [pre_cleanup_commit]
395+```
396+
397+---
398+
399+## Execution Strategy
400+
401+**Parallel Phase (Agents 1-10):**
402+```
403+Agent 1 (dead code) │
404+Agent 2 (skipped tests) │
405+Agent 3 (outdated tests) ├─→ 10 parallel audits → 10 reports
406+Agent 4 (hardcoded config) │
407+Agent 5 (doc organization) │
408+Agent 6 (known issues) │
409+Agent 7 (TODO organization) │
410+Agent 8 (test coverage) │
411+Agent 9 (imports) │
412+Agent 10 (doc accuracy) │
413+```
414+
415+**Sequential Phase (Single agents):**
416+```
417+Consolidation agent → execution plan
418+ ↓
419+Execution agent → apply changes (file-by-file)
420+ ↓
421+Documentation agent → reorganize docs
422+ ↓
423+Verification agent → final checks
424+```
425+
426+**Estimated time:** 30-45 minutes total
427+
428+---
429+
430+## Agent Prompts
431+
432+### Launch Command for All 10 Agents
433+
434+```
435+Launch agents 1-10 in parallel with their respective tasks from Phase 1.
436+Each agent produces a report in documentation/reports/.
437+Wait for all 10 reports before proceeding to Phase 2.
438+```
439+
440+### After Reports Complete
441+
442+```
443+Launch consolidation agent to merge reports into execution plan.
444+Then launch execution agent with the plan.
445+Then launch documentation agent for reorganization.
446+Finally launch verification agent for final checks.
447+```
448+
449+---
450+
451+**Plan Complete**
452+**Ready for autonomous execution with 10 parallel agents**
documentation/reports/CLEANUP_EXECUTION_PLAN_2026-02-07.md+721−0
@@ -0,0 +1,721 @@
1+# Cleanup Execution Plan - 2026-02-07
2+
3+Consolidated execution plan for 10 audit reports covering dead code, tests, documentation, configuration, and coverage gaps.
4+
5+---
6+
7+## Summary
8+
9+- **Total changes:** 127 discrete changes
10+- **Files affected:** 58 files (18 production, 25 test, 15 documentation)
11+- **Estimated time:** 47.5 hours (6 full work days)
12+- **Coverage impact:** 28% → ~75% (+47%)
13+- **Test count:** Remove 6 obsolete, fix 5 skipped, add 15 new test suites
14+
15+---
16+
17+## Priority 1: Critical (Must Fix)
18+
Cut short: this commit's diff is over 1000 lines.
documentation/reports/DEAD_CODE_AUDIT_2026-02-07.md+332−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/DOCUMENTATION_ACCURACY_AUDIT_2026-02-07.md+489−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/DOCUMENTATION_ORGANIZATION_AUDIT_2026-02-07.md+494−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/HARDCODED_CONFIG_AUDIT_2026-02-07.md+248−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/IMPORT_CLEANUP_2026-02-07.md+372−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/KNOWN_ISSUES_CONSOLIDATION_2026-02-07.md+741−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/OUTDATED_TESTS_AUDIT_2026-02-07.md+373−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/SKIPPED_TESTS_AUDIT_2026-02-07.md+340−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/TEST_COVERAGE_GAPS_2026-02-07.md+723−0
Cut short: this commit's diff is over 1000 lines.
documentation/reports/TODO_ORGANIZATION_2026-02-07.md+329−0
Cut short: this commit's diff is over 1000 lines.
internal/tui/help.go+1−1
Cut short: this commit's diff is over 1000 lines.