eagle-mem 4.10.2 → 4.10.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/CHANGELOG.md +130 -0
  2. package/README.md +3 -82
  3. package/package.json +3 -2
package/CHANGELOG.md ADDED
@@ -0,0 +1,130 @@
1
+ # Changelog
2
+
3
+ All notable changes to the **Eagle Mem** project are documented here.
4
+
5
+ ---
6
+
7
+ ## v4.10.2 Patch
8
+
9
+ This release expands the Eagle Mem adapter layer and addresses multi-agent planning synchronization and gap remediations across all four supported agents:
10
+
11
+ - **Google Antigravity SDK Hook**: Fully integrated programmatic, asynchronous Python async hooks (`google_antigravity_hook.py`) mapping turn lifecycles (`SessionStart` to `Stop`/`SessionEnd`) and context survival.
12
+ - **Automatic Brain Artifact Synchronization**: Extracted and mirrored `implementation_plan.md`, `task.md`, and `walkthrough.md` generated by Claude, Codex, and Antigravity directly to SQLite and FTS5 search indexes.
13
+ - **PreToolUse Codex Enhancement**: Removed early-exits to enable full advisory, command rewrite, and feature verification support on Codex shell paths.
14
+ - **Agent Settings Backups**: Added timestamped configurations backups (`settings.json.bak` and `config.toml.bak`) before any mutations by the installer/update process.
15
+ - **Unified 4-Agent Documentation**: Generalization of the architecture tutorial (`architecture.html`), product README (`README.md`), and developer instructions (`AGENTS.md`) to treat all four agents as first-class, natively supported surfaces.
16
+
17
+ ---
18
+
19
+ ## v4.10.1 Patch
20
+
21
+ This documentation patch clarifies npm download-count behavior and Eagle Mem privacy expectations:
22
+
23
+ - npm download counts are aggregate tarball-serving statistics.
24
+ - Package maintainers cannot identify who downloaded the package from npm's public stats.
25
+ - Eagle Mem remains local-first and does not include install telemetry or phone-home analytics.
26
+
27
+ ---
28
+
29
+ ## v4.10.0 Minor Release
30
+
31
+ This release makes Eagle Mem broader and safer across agent workflows:
32
+
33
+ - Grok is now a first-class skill/CLI target: install detects `~/.grok`, links Eagle Mem skills into `~/.grok/skills`, and adds `eagle-mem grok-bootstrap`.
34
+ - `eagle-mem compaction` reports Compaction Survival readiness from shared project state: enriched summaries, durable tasks, stale tasks, active lanes, and last durable update.
35
+ - `eagle-mem test` provides a built-in smoke harness for the memory layer.
36
+ - `eagle-mem tasks stale` and `[STALE - Nd]` warnings make long-running task drift visible.
37
+ - `eagle-mem health` now surfaces orchestration lanes, learned command rules, and curator timing.
38
+
39
+ ---
40
+
41
+ ## v4.9.7 Patch
42
+
43
+ This patch is a release-readiness and UX-hardening pass:
44
+
45
+ - `eagle-mem doctor` reports the install footprint, selected SQLite binary, FTS5 availability, hook registration, statusline wiring, install-manifest health, and runtime drift.
46
+ - Install/update show a clear preflight plan, refresh the manifest, and keep rollback backups aware of the manifest/version files.
47
+ - Uninstall supports `--dry-run`, backs up config files, removes Claude/Codex hook and instruction integrations, cleans up skill links, and preserves runtime data by default.
48
+ - Claude statusline/HUD rendering is centralized through `scripts/statusline-em.sh --hud`.
49
+ - Statusline project resolution now prefers the live session row and avoids `$HOME` ancestor leakage, so new projects show their own sessions/memories instead of stale counts from older workspaces.
50
+ - Default hook/search/memory output follows the visible-surface UX contract: branded, compact, freshness-aware, and free of raw IDs/paths unless `--raw`, `--debug`, or `--json` is requested.
51
+
52
+ ---
53
+
54
+ ## v4.9.6 Patch
55
+
56
+ `eagle-mem update` now queues project-key backfill in the background by default, so install/update can finish, write the installed version marker, and return control to the user. Use `EAGLE_MEM_UPDATE_BACKFILL=sync eagle-mem update` only when you intentionally want to wait for a full backfill.
57
+
58
+ ---
59
+
60
+ ## v4.9.5 Patch
61
+
62
+ Stop hooks now use a fast path: they save heuristic summaries immediately, extract explicit summary blocks when present, and queue LLM enrichment in the background so Codex/Claude lifecycle hooks do not time out. SQLite access now goes through a shared FTS5-capable binary resolver used by migrations, DB helpers, updater backups, install checks, and the statusline, avoiding Android SDK or other PATH shims that shadow working SQLite builds.
63
+
64
+ ---
65
+
66
+ ## v4.9.4 Patch
67
+
68
+ Project-key hardening for agents that move between folders: hooks now keep a per-session project identity instead of recalculating from every new cwd, and statuslines prefer the stored session project before falling back to folder paths. Install/update also repairs older embedded Eagle Mem statusline blocks so nested-repo projects stop showing `Memories: 0` when the session belongs to the parent workspace.
69
+
70
+ ---
71
+
72
+ ## v4.9.3 Patch
73
+
74
+ Follow-up hardening for the v4.9.2 project-key repair: Claude transcript workspace detection now reads complete early JSONL records instead of a fixed byte slice, so large SessionStart hook context cannot hide the first `cwd`. Metadata-only memory/plan/task repairs also avoid touching FTS-indexed columns, preventing SQLite FTS update triggers from firing during safe project/source rekeys.
75
+
76
+ ---
77
+
78
+ ## v4.9.2 Patch
79
+
80
+ Nested-repo Claude Code projects now use one stable project key. When a Claude workspace contains a git repo subdirectory, hooks prefer the Claude transcript workspace root while repo-local CLI commands can still use git-root keys where appropriate. Memory sync and backfill also repair unchanged memory rows whose content hash stayed the same but whose project key was stale. FTS5 update triggers now ignore metadata-only project rekeys, avoiding SQLite virtual-table errors during safe repairs.
81
+
82
+ Installer parity also improved: first-time install now auto-provisions RTK when Cargo is available, the Eagle Mem statusline shows version/session/memory/turn counts, `eagle-mem statusline` is available as a CLI command, and Codex instructions explicitly call out that Codex currently has hook recall plus the statusline command rather than Claude Code's persistent custom statusline UI.
83
+
84
+ ---
85
+
86
+ ## v4.9.1 Patch
87
+
88
+ `eagle-mem updates status` now refreshes the npm version live, and install/update seed the local latest-version cache with the installed version. This avoids confusing status output immediately after an update.
89
+
90
+ ---
91
+
92
+ ## v4.9.0 Patch
93
+
94
+ Eagle Mem now auto-updates by default for patch bug fixes. SessionStart performs a throttled background npm check, applies eligible patch releases with a lock and runtime/database backup, runs `eagle-mem update`, and records a one-time notice for the next session. Minor and major releases stay outside the default auto-apply range unless users opt in with `eagle-mem updates enable minor` or `eagle-mem updates enable major`.
95
+
96
+ ---
97
+
98
+ ## v4.8.6 Patch
99
+
100
+ `eagle-mem session save --summary "..."` now exists as a clean manual fallback for agents that need to persist an explicit session note. It writes through the same `sessions` and `summaries` tables used by Stop hooks, keeps Claude Code/Codex source attribution, and is immediately searchable through normal recall.
101
+
102
+ ---
103
+
104
+ ## v4.8.5 Patch
105
+
106
+ First-run configuration no longer exits silently when Ollama is not listening on `localhost:11434`; Eagle Mem falls through to the installed Codex/Claude CLI provider or API-key providers. SQLite/FTS5 failures are now surfaced before DB-backed commands run, including the exact `sqlite3` binary being used and PATH guidance for common macOS Android SDK shadowing. Worker worktree paths are also canonicalized back to the main project key so backfill cannot move feature guardrails into disposable orchestration worktrees.
107
+
108
+ ---
109
+
110
+ ## v4.8.4 Patch
111
+
112
+ The orchestration handoff path is now Bash 3.2-safe, so `eagle-mem orchestrate handoff` works even when no lane options are present. This patch was verified with a real Codex coordinator -> Claude Code worker proof lane using `claude-opus-4-7` at `xhigh`; the completed lane is visible through `eagle-mem orchestrate --json`, `eagle-mem tasks completed`, and the generated handoff output. Release-boundary detection also ignores Eagle Mem's own `feature verify`/`waive` commands, so verification notes can mention dry-run checks without blocking themselves.
113
+
114
+ ---
115
+
116
+ ## v4.8.3 Patch
117
+
118
+ GitHub Pages now keeps hero text readable over the terminal background and the homepage explicitly explains installer-created/updated `CLAUDE.md` and `AGENTS.md` sections plus orchestrator/worker mode. Installer/update output also uses the new clean-output Codex wording instead of saying it added eagle-summary instructions.
119
+
120
+ ---
121
+
122
+ ## v4.8.2 Patch
123
+
124
+ Codex no longer gets instructed to print large user-visible `<eagle-summary>` XML blocks. The installer/update path rewrites existing `~/.codex/AGENTS.md` Eagle Mem instructions to the clean-output contract, context-pressure nudges use normal prose, and Codex-oriented skills/worker prompts avoid raw capture templates.
125
+
126
+ ---
127
+
128
+ ## v4.8.1 Patch
129
+
130
+ `eagle-mem memories sync` is now safe on large Claude Code/Codex memory files. The memory mirror parser no longer uses early-exit pipelines under `pipefail`, avoiding exit `141` during sync.
package/README.md CHANGED
@@ -11,7 +11,7 @@
11
11
 
12
12
  Eagle Mem turns AI coding sessions into compounding project knowledge. It gives Claude Code, Codex, and Google Antigravity hook-backed shared memory, gives Grok the same skills and CLI memory surface, labels which agent created each memory, blocks risky release commands until affected features are verified, and lets broad work split into durable worker lanes.
13
13
 
14
- **v4.10.0 and onward focuses on Grok, Google Antigravity support, and Compaction Survival:** Grok users get first-class skill linking and `eagle-mem grok-bootstrap`, while Antigravity users get native Python SDK hook integration via `google_antigravity_hook.py`. Claude Code, Codex, and Antigravity receive the deepest automatic lifecycle support through hooks; Grok currently uses the shared CLI and skill workflow.
14
+ **v4.10.2 and onward focuses on Grok, Google Antigravity support, and Compaction Survival:** Grok users get first-class skill linking and `eagle-mem grok-bootstrap`, while Antigravity users get native Python SDK hook integration via `google_antigravity_hook.py`. Claude Code, Codex, and Antigravity receive the deepest automatic lifecycle support through hooks; Grok currently uses the shared CLI and skill workflow.
15
15
 
16
16
  **Website:** [Product](https://eagleisbatman.github.io/eagle-mem/) |
17
17
  [Architecture](https://eagleisbatman.github.io/eagle-mem/architecture.html) |
@@ -199,88 +199,9 @@ curl https://api.npmjs.org/downloads/range/last-month/eagle-mem
199
199
 
200
200
  Use these numbers as directional popularity signals only. They are useful for spotting broad distribution patterns, but they are not a reliable count of users, installs, projects, or companies.
201
201
 
202
- ### v4.10.1 Patch
202
+ ### Changelog
203
203
 
204
- This documentation patch clarifies npm download-count behavior and Eagle Mem privacy expectations:
205
-
206
- - npm download counts are aggregate tarball-serving statistics.
207
- - Package maintainers cannot identify who downloaded the package from npm's public stats.
208
- - Eagle Mem remains local-first and does not include install telemetry or phone-home analytics.
209
-
210
- ### v4.10.0 Minor Release
211
-
212
- This release makes Eagle Mem broader and safer across agent workflows:
213
-
214
- - Grok is now a first-class skill/CLI target: install detects `~/.grok`, links Eagle Mem skills into `~/.grok/skills`, and adds `eagle-mem grok-bootstrap`.
215
- - `eagle-mem compaction` reports Compaction Survival readiness from shared project state: enriched summaries, durable tasks, stale tasks, active lanes, and last durable update.
216
- - `eagle-mem test` provides a built-in smoke harness for the memory layer.
217
- - `eagle-mem tasks stale` and `[STALE - Nd]` warnings make long-running task drift visible.
218
- - `eagle-mem health` now surfaces orchestration lanes, learned command rules, and curator timing.
219
-
220
- ### v4.9.7 Patch
221
-
222
- This patch is a release-readiness and UX-hardening pass:
223
-
224
- - `eagle-mem doctor` reports the install footprint, selected SQLite binary, FTS5 availability, hook registration, statusline wiring, install-manifest health, and runtime drift.
225
- - Install/update show a clear preflight plan, refresh the manifest, and keep rollback backups aware of the manifest/version files.
226
- - Uninstall supports `--dry-run`, backs up config files, removes Claude/Codex hook and instruction integrations, cleans up skill links, and preserves runtime data by default.
227
- - Claude statusline/HUD rendering is centralized through `scripts/statusline-em.sh --hud`.
228
- - Statusline project resolution now prefers the live session row and avoids `$HOME` ancestor leakage, so new projects show their own sessions/memories instead of stale counts from older workspaces.
229
- - Default hook/search/memory output follows the visible-surface UX contract: branded, compact, freshness-aware, and free of raw IDs/paths unless `--raw`, `--debug`, or `--json` is requested.
230
-
231
- ### v4.9.6 Patch
232
-
233
- `eagle-mem update` now queues project-key backfill in the background by default, so install/update can finish, write the installed version marker, and return control to the user. Use `EAGLE_MEM_UPDATE_BACKFILL=sync eagle-mem update` only when you intentionally want to wait for a full backfill.
234
-
235
- ### v4.9.5 Patch
236
-
237
- Stop hooks now use a fast path: they save heuristic summaries immediately, extract explicit summary blocks when present, and queue LLM enrichment in the background so Codex/Claude lifecycle hooks do not time out. SQLite access now goes through a shared FTS5-capable binary resolver used by migrations, DB helpers, updater backups, install checks, and the statusline, avoiding Android SDK or other PATH shims that shadow working SQLite builds.
238
-
239
- ### v4.9.4 Patch
240
-
241
- Project-key hardening for agents that move between folders: hooks now keep a per-session project identity instead of recalculating from every new cwd, and statuslines prefer the stored session project before falling back to folder paths. Install/update also repairs older embedded Eagle Mem statusline blocks so nested-repo projects stop showing `Memories: 0` when the session belongs to the parent workspace.
242
-
243
- ### v4.9.3 Patch
244
-
245
- Follow-up hardening for the v4.9.2 project-key repair: Claude transcript workspace detection now reads complete early JSONL records instead of a fixed byte slice, so large SessionStart hook context cannot hide the first `cwd`. Metadata-only memory/plan/task repairs also avoid touching FTS-indexed columns, preventing SQLite FTS update triggers from firing during safe project/source rekeys.
246
-
247
- ### v4.9.2 Patch
248
-
249
- Nested-repo Claude Code projects now use one stable project key. When a Claude workspace contains a git repo subdirectory, hooks prefer the Claude transcript workspace root while repo-local CLI commands can still use git-root keys where appropriate. Memory sync and backfill also repair unchanged memory rows whose content hash stayed the same but whose project key was stale. FTS5 update triggers now ignore metadata-only project rekeys, avoiding SQLite virtual-table errors during safe repairs.
250
-
251
- Installer parity also improved: first-time install now auto-provisions RTK when Cargo is available, the Eagle Mem statusline shows version/session/memory/turn counts, `eagle-mem statusline` is available as a CLI command, and Codex instructions explicitly call out that Codex currently has hook recall plus the statusline command rather than Claude Code's persistent custom statusline UI.
252
-
253
- ### v4.9.1 Patch
254
-
255
- `eagle-mem updates status` now refreshes the npm version live, and install/update seed the local latest-version cache with the installed version. This avoids confusing status output immediately after an update.
256
-
257
- ### v4.9.0 Patch
258
-
259
- Eagle Mem now auto-updates by default for patch bug fixes. SessionStart performs a throttled background npm check, applies eligible patch releases with a lock and runtime/database backup, runs `eagle-mem update`, and records a one-time notice for the next session. Minor and major releases stay outside the default auto-apply range unless users opt in with `eagle-mem updates enable minor` or `eagle-mem updates enable major`.
260
-
261
- ### v4.8.6 Patch
262
-
263
- `eagle-mem session save --summary "..."` now exists as a clean manual fallback for agents that need to persist an explicit session note. It writes through the same `sessions` and `summaries` tables used by Stop hooks, keeps Claude Code/Codex source attribution, and is immediately searchable through normal recall.
264
-
265
- ### v4.8.5 Patch
266
-
267
- First-run configuration no longer exits silently when Ollama is not listening on `localhost:11434`; Eagle Mem falls through to the installed Codex/Claude CLI provider or API-key providers. SQLite/FTS5 failures are now surfaced before DB-backed commands run, including the exact `sqlite3` binary being used and PATH guidance for common macOS Android SDK shadowing. Worker worktree paths are also canonicalized back to the main project key so backfill cannot move feature guardrails into disposable orchestration worktrees.
268
-
269
- ### v4.8.4 Patch
270
-
271
- The orchestration handoff path is now Bash 3.2-safe, so `eagle-mem orchestrate handoff` works even when no lane options are present. This patch was verified with a real Codex coordinator -> Claude Code worker proof lane using `claude-opus-4-7` at `xhigh`; the completed lane is visible through `eagle-mem orchestrate --json`, `eagle-mem tasks completed`, and the generated handoff output. Release-boundary detection also ignores Eagle Mem's own `feature verify`/`waive` commands, so verification notes can mention dry-run checks without blocking themselves.
272
-
273
- ### v4.8.3 Patch
274
-
275
- GitHub Pages now keeps hero text readable over the terminal background and the homepage explicitly explains installer-created/updated `CLAUDE.md` and `AGENTS.md` sections plus orchestrator/worker mode. Installer/update output also uses the new clean-output Codex wording instead of saying it added eagle-summary instructions.
276
-
277
- ### v4.8.2 Patch
278
-
279
- Codex no longer gets instructed to print large user-visible `<eagle-summary>` XML blocks. The installer/update path rewrites existing `~/.codex/AGENTS.md` Eagle Mem instructions to the clean-output contract, context-pressure nudges use normal prose, and Codex-oriented skills/worker prompts avoid raw capture templates.
280
-
281
- ### v4.8.1 Patch
282
-
283
- `eagle-mem memories sync` is now safe on large Claude Code/Codex memory files. The memory mirror parser no longer uses early-exit pipelines under `pipefail`, avoiding exit `141` during sync.
204
+ All notable releases and patch updates are documented in the separate [CHANGELOG.md](CHANGELOG.md) file.
284
205
 
285
206
  ### Search Modes
286
207
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "eagle-mem",
3
- "version": "4.10.2",
3
+ "version": "4.10.3",
4
4
  "description": "Shared memory, release guardrails, RTK token protection, and worker lanes for Claude Code, Codex, Grok, and Google Antigravity",
5
5
  "bin": {
6
6
  "eagle-mem": "bin/eagle-mem"
@@ -14,7 +14,8 @@
14
14
  "skills/",
15
15
  "docs/",
16
16
  "architecture.html",
17
- "integrations/"
17
+ "integrations/",
18
+ "CHANGELOG.md"
18
19
  ],
19
20
  "keywords": [
20
21
  "claude-code",