Ralph Chang
01bda7c134
fix(memory): freeze hot session prompt epoch
2026-05-20 12:38:16 +08:00
Ralph Chang
5bca3432b0
feat(memory-diag): add quality review board command
...
Add memory-diag quality command for objective review of memory-system
mechanisms and active memory content. The command is read-only and
non-authoritative, providing evidence, heuristic flags, and review
questions without making quality judgments or suggesting mutations.
Key components:
- quality-review-model.ts: builds ReviewBoardReport with provenance,
re-absorption detection, mechanism facts (rejection, reinforcement,
eviction/caps, identity/dedup), and memory content facts
- formatters/quality.ts: human and JSON output with separate
system-mechanism and memory-content sections
- commands/quality.ts: command entry point with --json, --verbose,
--no-emoji, --raw options
- cli.ts: parser whitelist for quality accepting --workspace, --json,
rejecting mutation/filter flags
co-author: code-execute-agent, comprehensive-code-reviewer,
systems-architect, creative-disruptor
Closes docs/plans/2026-05-11-memory-diag-quality-review-board.md
2026-05-12 14:13:03 +08:00
Ralph Chang
9b6955f490
docs(readme): remove roadmap section
2026-05-08 22:13:40 +08:00
Ralph Chang
e708e77e61
docs(release): prepare v1.6.1
2026-05-08 22:09:08 +08:00
Ralph Chang
9114b57dc1
feat(tui): consolidate memory dialog menu
2026-05-08 21:41:57 +08:00
Ralph Chang
65b3b2f2c3
fix(tui): clarify memory command surface
2026-05-08 19:49:56 +08:00
Ralph Chang
49bf866de2
feat(tui): add native memory visibility commands
2026-05-08 19:26:17 +08:00
Ralph Chang
09880c1840
feat(memory): add numbered compaction refs
2026-05-08 12:18:39 +08:00
Ralph Chang
06dcf61711
feat(hot-state): section-aware greedy renderer, accounting types, fix docs drift
...
Replace blunt .slice(0, maxRenderedChars) truncation with a greedy line
accumulator that fits whole lines and suppresses header-only sections.
Add accountHotSessionStateRender() returning prompt + omitted[] accounting.
Export HotStateSection, HotStateOmissionReason, HotStateOmittedItem,
HotSessionStateRenderAccounting types for v2 evidence extension.
Fix configuration.md ranking formula (ACTION_WEIGHT + count*3, weights
50/45/30/20). Clarify README injection order. Add 9 unit tests.
2026-05-05 12:22:09 +08:00
Ralph Chang
3c13773231
feat(memory-diag): publish diagnostics CLI
2026-05-02 20:36:58 +08:00
Ralph Chang
f19614565a
chore(release): prepare v1.5.2
2026-05-01 16:00:44 +08:00
Ralph Chang
1c6e143f4b
chore(release): prepare v1.5.0
2026-04-29 16:56:47 +08:00
Ralph Chang
c0a083ddaf
fix(memory): isolate test workspace cleanup
2026-04-28 14:50:30 +08:00
Ralph Chang
c7088a8a6e
docs(memory): document conservative quality cleanup migration
2026-04-28 14:19:18 +08:00
Ralph Chang
6a1fa525dc
docs: document concise compatibility limitations
2026-04-27 19:57:21 +08:00
Ralph Chang
909fec9abb
docs: prepare v1.3.0 release notes
2026-04-27 17:06:43 +08:00
sdwolf4103
2fc2172d59
Fix formatting in README.md
2026-04-27 13:00:26 +08:00
Ralph Chang
fd8d730e3b
docs: streamline README and document ongoing work
2026-04-27 12:38:11 +08:00
Ralph Chang
f6f35e87c1
feat: release v1.2.2 with multilingual memory hardening
2026-04-27 00:21:18 +08:00
Ralph Chang
f988af4453
docs: enhance README with visual three-layer architecture diagram
...
- Add table showing layer scope, tracking, and persistence
- Add visual ASCII diagram emphasizing cross-session capability
- Add compaction flow diagram showing no extra API call
- Highlight piggyback on existing compaction summary
2026-04-26 13:43:06 +08:00
Ralph Chang
606dcfac12
docs: fix hook names and prompt tags in documentation
...
- Fix outdated hook names: prompt:before → experimental.chat.system.transform
- Fix outdated hook names: tool.execute.before → (removed, file tracking is in tool.execute.after)
- Fix outdated hook names: compaction:before → experimental.session.compacting
- Add missing event hook documentation
- Fix README example to show correct <hot_session_state> tag instead of <workspace_memory_candidates>
2026-04-26 13:36:49 +08:00
Ralph Chang
802ef62636
docs: update documentation to Memory V2 architecture
...
- Replace four-tier architecture with three-layer Memory V2
- Remove references to non-existent tools (core_memory_*, working_memory_*)
- Update storage paths to ~/.local/share/opencode-working-memory/
- Update configuration to LONG_TERM_LIMITS and HOT_STATE_LIMITS
- Fix installation verification to check system prompt instead of tools
2026-04-26 13:27:14 +08:00
Ralph Chang
6fad91953c
docs: improve token-usage section readability
2026-02-18 16:59:47 +08:00
Ralph Chang
7b33b51c1e
docs: add token-usage guidance for session patterns
2026-02-18 16:57:40 +08:00
Ralph Chang
bb929fc578
Clean up comments, fix docs, bump to v1.0.1
2026-02-18 14:13:37 +08:00
Ralph Chang
98e5ecaa91
Fix installation: no npm install needed, OpenCode auto-installs from config
2026-02-18 11:08:09 +08:00
Ralph Chang
c008fb860f
Fix Quick Start: agent prompts instead of CLI commands
2026-02-18 10:59:22 +08:00
Ralph Chang
c743ddb331
Restore Quick Start example commands
2026-02-18 10:58:15 +08:00
Ralph Chang
0631286962
Improve README: simplify Quick Start and remove Phase labels
2026-02-18 10:51:01 +08:00
Ralph Chang
75c89747d8
Fix typecheck errors and update install docs for npm release
2026-02-18 10:46:03 +08:00
Ralph Chang
605524b674
Improve ASCII diagram alignment in README
...
- Fine-tuned spacing and padding for better visual alignment
- Ensured consistent right border alignment across all boxes
2026-02-18 10:15:53 +08:00
Ralph Chang
22cfd6ee3a
Fix pressure thresholds and ASCII diagram alignment
...
- Corrected pressure levels: 75% (moderate) / 90% (high)
- Removed incorrect 'critical' level (95%)
- Fixed ASCII diagram alignment in README
- Updated all documentation to match actual code implementation
- Pruning modes: < 75% (normal), 75-89% (aggressive), ≥ 90% (hyper-aggressive)
2026-02-18 10:13:28 +08:00
Ralph Chang
4b862ee79c
Fix ASCII diagram alignment in README
...
- Adjusted box borders for proper alignment
- Fixed spacing and padding
- Ensures monospace font rendering consistency
2026-02-18 10:10:56 +08:00
Ralph Chang
5c7dd0f421
Update GitHub URLs: yourusername → sdwolf4103
...
- Updated package.json repository URLs
- Updated README.md installation and support links
- Updated docs/installation.md clone URL
- Updated AGENTS.md clone URL
2026-02-18 10:10:03 +08:00
Ralph Chang
484cb420ca
Revert "Rename project: opencode-working-memory → oh-my-memory"
...
This reverts commit bf11c9d55c .
2026-02-18 10:06:20 +08:00
Ralph Chang
bf11c9d55c
Rename project: opencode-working-memory → oh-my-memory
...
- Updated package.json name and URLs
- Updated README.md title and references
- Updated docs/installation.md install commands
- Updated AGENTS.md project name
- Follows oh-my-opencode naming convention
2026-02-18 09:57:46 +08:00
Ralph Chang
32d5ddfb50
Initial commit: OpenCode Working Memory Plugin v1.0.0
...
- Four-tier memory architecture (Core, Working, Pruning, Pressure)
- Phase 1: Core Memory blocks (goal/progress/context)
- Phase 2: Smart Pruning with adaptive thresholds
- Phase 3: Working Memory with slots + pool decay
- Phase 4: Pressure monitoring with interventions
- Phase 4.5: Storage governance (session cleanup + cache sweep)
- Complete documentation (README, AGENTS, installation, architecture, configuration)
- MIT licensed
2026-02-18 09:49:09 +08:00