self-evolving-workflow 0.0.0-stage → 0.1.3
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.
- package/LICENSE +27 -0
- package/README.md +90 -2
- package/dist/agent-memory-prompts.d.ts +13 -0
- package/dist/agent-memory-prompts.js +55 -0
- package/dist/cli.d.ts +2 -0
- package/dist/cli.js +6 -0
- package/dist/closeout.d.ts +105 -0
- package/dist/closeout.js +479 -0
- package/dist/code.d.ts +39 -0
- package/dist/code.js +124 -0
- package/dist/common.d.ts +9 -0
- package/dist/common.js +42 -0
- package/dist/context-envelope.d.ts +59 -0
- package/dist/context-envelope.js +23 -0
- package/dist/host-adapters.d.ts +34 -0
- package/dist/host-adapters.js +151 -0
- package/dist/http.d.ts +3 -0
- package/dist/http.js +90 -0
- package/dist/index.d.ts +16 -0
- package/dist/index.js +13 -0
- package/dist/knowledge-cli.d.ts +183 -0
- package/dist/knowledge-cli.js +654 -0
- package/dist/knowledge-reads.d.ts +71 -0
- package/dist/knowledge-reads.js +193 -0
- package/dist/memory.d.ts +97 -0
- package/dist/memory.js +250 -0
- package/dist/retrospective.d.ts +57 -0
- package/dist/retrospective.js +248 -0
- package/dist/search.d.ts +36 -0
- package/dist/search.js +112 -0
- package/dist/skill-addition.d.ts +25 -0
- package/dist/skill-addition.js +89 -0
- package/dist/skill-design.d.ts +96 -0
- package/dist/skill-design.js +226 -0
- package/dist/skill-replay.d.ts +55 -0
- package/dist/skill-replay.js +451 -0
- package/dist/skill-route.d.ts +30 -0
- package/dist/skill-route.js +75 -0
- package/dist/transcript-evidence.d.ts +3 -0
- package/dist/transcript-evidence.js +58 -0
- package/dist/upstream/chunker.d.ts +24 -0
- package/dist/upstream/chunker.js +96 -0
- package/dist/upstream/file-protocol.d.ts +45 -0
- package/dist/upstream/file-protocol.js +117 -0
- package/dist/upstream/frontmatter.d.ts +47 -0
- package/dist/upstream/frontmatter.js +86 -0
- package/dist/upstream/graph-search.d.ts +33 -0
- package/dist/upstream/graph-search.js +67 -0
- package/dist/upstream/l1-extraction.d.ts +26 -0
- package/dist/upstream/l1-extraction.js +405 -0
- package/dist/upstream/llm.d.ts +8 -0
- package/dist/upstream/llm.js +1 -0
- package/dist/upstream/merge.d.ts +50 -0
- package/dist/upstream/merge.js +153 -0
- package/dist/upstream/prompts.d.ts +53 -0
- package/dist/upstream/prompts.js +185 -0
- package/dist/upstream/search-utils.d.ts +34 -0
- package/dist/upstream/search-utils.js +55 -0
- package/dist/upstream/slug.d.ts +26 -0
- package/dist/upstream/slug.js +103 -0
- package/dist/upstream/template.d.ts +29 -0
- package/dist/upstream/template.js +80 -0
- package/dist/upstream/tokenize.d.ts +4 -0
- package/dist/upstream/tokenize.js +29 -0
- package/dist/wiki-change.d.ts +76 -0
- package/dist/wiki-change.js +299 -0
- package/dist/wiki-entry.d.ts +26 -0
- package/dist/wiki-entry.js +93 -0
- package/dist/wiki-ingest.d.ts +12 -0
- package/dist/wiki-ingest.js +126 -0
- package/dist/wiki-migration.d.ts +16 -0
- package/dist/wiki-migration.js +268 -0
- package/dist/wiki-tokens.d.ts +1 -0
- package/dist/wiki-tokens.js +46 -0
- package/dist/wiki.d.ts +103 -0
- package/dist/wiki.js +330 -0
- package/dist/workflow-cli.d.ts +2 -0
- package/dist/workflow-cli.js +258 -0
- package/dist/workflow-install.d.ts +36 -0
- package/dist/workflow-install.js +148 -0
- package/dist/workflow-knowledge.d.ts +16 -0
- package/dist/workflow-knowledge.js +24 -0
- package/dist/workflow-mcp.d.ts +2 -0
- package/dist/workflow-mcp.js +144 -0
- package/dist/workflow-names.d.ts +4 -0
- package/dist/workflow-names.js +18 -0
- package/dist/workflow-runtime.d.ts +622 -0
- package/dist/workflow-runtime.js +627 -0
- package/dist/workflow-skills.d.ts +48 -0
- package/dist/workflow-skills.js +141 -0
- package/package.json +76 -4
- package/skills/ew-odyssey/SKILL.md +237 -0
- package/skills/ew-odyssey/references/audit-artifacts.md +7 -0
- package/skills/ew-odyssey/references/odyssey-base-codex.md +3 -0
- package/skills/ew-odyssey/references/odyssey-base.md +278 -0
- package/skills/ew-odyssey/references/odyssey-debug.codex.md +305 -0
- package/skills/ew-odyssey/references/odyssey-debug.md +283 -0
- package/skills/ew-odyssey/references/odyssey-defensive.codex.md +395 -0
- package/skills/ew-odyssey/references/odyssey-defensive.md +369 -0
- package/skills/ew-odyssey/references/odyssey-improve.codex.md +270 -0
- package/skills/ew-odyssey/references/odyssey-improve.md +248 -0
- package/skills/ew-odyssey/references/odyssey-planex.codex.md +352 -0
- package/skills/ew-odyssey/references/odyssey-planex.md +312 -0
- package/skills/ew-odyssey/references/odyssey-review.codex.md +283 -0
- package/skills/ew-odyssey/references/odyssey-review.md +251 -0
- package/skills/ew-odyssey/references/odyssey-security.md +249 -0
- package/skills/ew-odyssey/references/odyssey-ui.codex.md +294 -0
- package/skills/ew-odyssey/references/odyssey-ui.md +250 -0
- package/skills/ew-odyssey/references/prepare/odyssey-debug.md +105 -0
- package/skills/ew-odyssey/references/prepare/odyssey-defensive.md +121 -0
- package/skills/ew-odyssey/references/prepare/odyssey-improve.md +93 -0
- package/skills/ew-odyssey/references/prepare/odyssey-planex.md +104 -0
- package/skills/ew-odyssey/references/prepare/odyssey-review.md +98 -0
- package/skills/ew-odyssey/references/prepare/odyssey-security.md +94 -0
- package/skills/ew-odyssey/references/prepare/odyssey-ui.md +87 -0
- package/skills/ew-orchestrate/SKILL.md +236 -0
- package/skills/ew-orchestrate/references/auto-policy.md +165 -0
- package/skills/ew-orchestrate/references/companion-route.md +52 -0
- package/skills/ew-orchestrate/references/ew-orchestrate.md +27 -0
- package/skills/ew-orchestrate/references/goal.md +53 -0
- package/skills/ew-orchestrate/references/knowledge-route.md +163 -0
- package/skills/ew-orchestrate/references/orchestrator-run-loop.md +36 -0
- package/skills/ew-orchestrate/references/planning.md +137 -0
- package/skills/ew-orchestrate/steps/ew-analyze/SKILL.md +62 -0
- package/skills/ew-orchestrate/steps/ew-analyze/references/boundary-grill.md +50 -0
- package/skills/ew-orchestrate/steps/ew-analyze/references/issue-gaps-analyze.md +59 -0
- package/skills/ew-orchestrate/steps/ew-analyze/references/prepare.md +42 -0
- package/skills/ew-orchestrate/steps/ew-analyze/references/workflow.md +401 -0
- package/skills/ew-orchestrate/steps/ew-brainstorm/SKILL.md +32 -0
- package/skills/ew-orchestrate/steps/ew-companion/SKILL.md +9 -0
- package/skills/ew-orchestrate/steps/ew-execute/SKILL.md +71 -0
- package/skills/ew-orchestrate/steps/ew-execute/references/prepare.md +69 -0
- package/skills/ew-orchestrate/steps/ew-execute/references/workflow.md +373 -0
- package/skills/ew-orchestrate/steps/ew-plan/SKILL.md +102 -0
- package/skills/ew-orchestrate/steps/ew-plan/references/boundary-grill.md +50 -0
- package/skills/ew-orchestrate/steps/ew-plan/references/prepare.md +51 -0
- package/skills/ew-orchestrate/steps/ew-plan/references/tdd.md +53 -0
- package/skills/ew-orchestrate/steps/ew-plan/references/workflow.md +278 -0
- package/skills/ew-orchestrate/steps/ew-review/SKILL.md +44 -0
- package/skills/ew-orchestrate/steps/ew-review/references/odyssey-base-codex.md +3 -0
- package/skills/ew-orchestrate/steps/ew-review/references/prepare.md +76 -0
- package/skills/ew-orchestrate/steps/ew-review/references/workflow.md +283 -0
- package/skills/ew-skill-design/SKILL.md +28 -0
- package/skills/ew-skill-design/references/package-contract.md +28 -0
- package/skills/ew-skill-design/references/validation.md +7 -0
- package/skills/team-swarm/SKILL.md +231 -0
- package/skills/team-swarm/references/mcp-coordination.md +10 -0
- package/skills/team-swarm/roles/analyst/role.md +181 -0
- package/skills/team-swarm/roles/ant/role.md +149 -0
- package/skills/team-swarm/roles/coordinator/commands/converge.md +154 -0
- package/skills/team-swarm/roles/coordinator/commands/init-swarm.md +134 -0
- package/skills/team-swarm/roles/coordinator/commands/iterate.md +202 -0
- package/skills/team-swarm/roles/coordinator/role.md +228 -0
- package/skills/team-swarm/roles/scorer/role.md +150 -0
- package/skills/team-swarm/scripts/aco.py +646 -0
- package/skills/team-swarm/scripts/pheromone.py +144 -0
- package/skills/team-swarm/scripts/scoring.py +111 -0
- package/skills/team-swarm/scripts/test_aco.py +606 -0
- package/skills/team-swarm/specs/ant-output-schema.md +127 -0
- package/skills/team-swarm/specs/convergence-criteria.md +108 -0
- package/skills/team-swarm/specs/pheromone-schema.md +125 -0
- package/skills/team-swarm/specs/swarm-config-template.json +71 -0
- package/skills/team-swarm/specs/swarm-protocol.md +123 -0
- package/skills/workflow-closeout/SKILL.md +10 -0
- package/skills/workflow-evolve/SKILL.md +79 -0
- package/skills/workflow-evolve/references/agy-gate.md +27 -0
- package/skills/workflow-evolve/references/auto-loop.md +20 -0
- package/skills/workflow-evolve/references/history-review.md +14 -0
- package/skills/workflow-evolve/scripts/codex-memory-replay.mjs +76 -0
- package/skills/workflow-evolve/scripts/codex-replay.mjs +1 -0
- package/skills/workflow-evolve/scripts/evolve-loop.mjs +259 -0
- package/skills/workflow-evolve/scripts/memory-codex-mcp.mjs +124 -0
- package/workflows/index.json +23 -0
|
@@ -0,0 +1,251 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-odyssey-review
|
|
3
|
+
prepare: odyssey-review
|
|
4
|
+
session-mode: inherited
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# Workflow: Odyssey Review
|
|
8
|
+
|
|
9
|
+
## State Chain
|
|
10
|
+
|
|
11
|
+
```
|
|
12
|
+
S_INTAKE → S_ARCHAEOLOGY → S_EXPLORE → S_REVIEW → S_FIX → S_CONFIRM → [back-half]
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
Back-half: `S_GENERALIZE → S_DISCOVER → S_RECORD → END` (see [shared phases](odyssey-base.md)).
|
|
16
|
+
|
|
17
|
+
---
|
|
18
|
+
|
|
19
|
+
## Boundary
|
|
20
|
+
|
|
21
|
+
**In scope:** Multi-dimensional deep review of target code → exhaustive fix ALL findings by severity → generalize patterns project-wide.
|
|
22
|
+
**Out of scope:** Root cause debug → `--mode debug` | Feature implementation → `--mode planex` | UI visual optimization → `--mode ui`. Zero-residual applies (fix ALL findings within fix_threshold, default all).
|
|
23
|
+
|
|
24
|
+
---
|
|
25
|
+
|
|
26
|
+
## Target Resolution
|
|
27
|
+
|
|
28
|
+
| Input | Resolution |
|
|
29
|
+
|-------|-----------|
|
|
30
|
+
| File/dir path | Review those files |
|
|
31
|
+
| `HEAD` / `staged` | `git diff HEAD` / `git diff --staged` |
|
|
32
|
+
| Phase number | state.json → changed files |
|
|
33
|
+
| PR number | `git diff main...HEAD` |
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## Session Fields
|
|
38
|
+
|
|
39
|
+
```json
|
|
40
|
+
{ "target": "", "dimensions": [], "review_result": {"remaining_actionable": 0},
|
|
41
|
+
"patterns": [], "confirmation": null, "generalization_stats": null }
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
---
|
|
45
|
+
|
|
46
|
+
## evidence.ndjson Phases
|
|
47
|
+
|
|
48
|
+
`archaeology|explore|review|fix|discovery|decision|self-iteration`
|
|
49
|
+
|
|
50
|
+
---
|
|
51
|
+
|
|
52
|
+
## phase_goals[]
|
|
53
|
+
|
|
54
|
+
| ID | Goal | done_when | phase | skip_when |
|
|
55
|
+
|----|------|-----------|-------|-----------|
|
|
56
|
+
| G1 | Review completed | all dimensions reviewed | S_REVIEW | — |
|
|
57
|
+
| G2 | Explore context | explore.json populated | S_EXPLORE | — |
|
|
58
|
+
| G3 | Zero remaining | `remaining_actionable == 0` | S_CONFIRM | skip_fix |
|
|
59
|
+
| G4 | Pattern generalized | patterns[] ≥1 | S_GENERALIZE | skip_generalize |
|
|
60
|
+
| G5 | Discoveries triaged | all hits classified | S_DISCOVER | skip_generalize |
|
|
61
|
+
| G6 | Learnings persisted | spec entries or no actionable | S_RECORD | — |
|
|
62
|
+
|
|
63
|
+
---
|
|
64
|
+
|
|
65
|
+
## understanding.md — 8 Sections
|
|
66
|
+
|
|
67
|
+
1. Target & Scope
|
|
68
|
+
2. Archaeology
|
|
69
|
+
3. Exploration
|
|
70
|
+
4. Review Results
|
|
71
|
+
5. Fix & Confirmation
|
|
72
|
+
6. Generalization
|
|
73
|
+
7. Discoveries
|
|
74
|
+
8. Learnings
|
|
75
|
+
|
|
76
|
+
Specs: `agent-memory wiki constraints --category review`.
|
|
77
|
+
|
|
78
|
+
---
|
|
79
|
+
|
|
80
|
+
## State Machine — Transitions
|
|
81
|
+
|
|
82
|
+
```
|
|
83
|
+
S_ARCHAEOLOGY → S_EXPLORE : complete
|
|
84
|
+
S_EXPLORE → S_REVIEW : complete
|
|
85
|
+
S_REVIEW → S_FIX : !skip_fix AND findings
|
|
86
|
+
S_REVIEW → S_GENERALIZE : skip_fix OR no findings, !skip_generalize
|
|
87
|
+
S_REVIEW → S_RECORD : both skip
|
|
88
|
+
S_FIX → S_CONFIRM : tier complete
|
|
89
|
+
S_CONFIRM → S_GENERALIZE : confirmed, !skip_generalize
|
|
90
|
+
S_CONFIRM → S_RECORD : confirmed, skip_generalize
|
|
91
|
+
S_CONFIRM → S_FIX : needs_rework
|
|
92
|
+
```
|
|
93
|
+
|
|
94
|
+
Discover routes: fixable sibling → S_FIX; new target needing review → S_REVIEW (loops < max_loops).
|
|
95
|
+
|
|
96
|
+
---
|
|
97
|
+
|
|
98
|
+
## Actions
|
|
99
|
+
|
|
100
|
+
### A_ARCHAEOLOGY
|
|
101
|
+
|
|
102
|
+
2 parallel Agents:
|
|
103
|
+
- **Timeline**: `git log --oneline -20 -- {files}`
|
|
104
|
+
- **Blame**: top 3 files `git blame -L {region}`
|
|
105
|
+
|
|
106
|
+
Evidence phase=archaeology.
|
|
107
|
+
|
|
108
|
+
`evolve delegate --role analyze --mode analysis` (`run_in_background: true`):
|
|
109
|
+
- PURPOSE: review recent modifications related to {target}
|
|
110
|
+
- EXPECTED: JSON `[{commit_sha, risk_level, analysis, could_cause_issue, explanation}]`
|
|
111
|
+
|
|
112
|
+
Update §2 (Archaeology).
|
|
113
|
+
|
|
114
|
+
If an archaeology agent fails, log W003 and proceed with available results.
|
|
115
|
+
|
|
116
|
+
### A_EXPLORE
|
|
117
|
+
|
|
118
|
+
Skip if no CLI tools (W006).
|
|
119
|
+
|
|
120
|
+
`evolve delegate --role explore --mode analysis` (`run_in_background: true`):
|
|
121
|
+
- PURPOSE: call chains, recent changes, error gaps, similar patterns
|
|
122
|
+
- EXPECTED: JSON `{call_chains, recent_changes, error_gaps, similar_patterns}`
|
|
123
|
+
|
|
124
|
+
Write `explore.json` + evidence phase=explore. Update §3 (Exploration). Mark G2.
|
|
125
|
+
|
|
126
|
+
**GATE: discovery-complete** — archaeology/explore evidence logged, understanding.md §2-§3 updated, G2 marked (W003 partial / W006 skip acceptable).
|
|
127
|
+
|
|
128
|
+
### A_REVIEW
|
|
129
|
+
|
|
130
|
+
Spawn N parallel Agents, one per dimension:
|
|
131
|
+
- **Correctness**: logic errors, boundary conditions, null/undefined, race conditions
|
|
132
|
+
- **Security**: injection, XSS, CSRF, data exposure, auth bypass
|
|
133
|
+
- **Performance**: hot paths, N+1, memory leaks, unnecessary recomputation
|
|
134
|
+
- **Architecture**: layer violations, circular deps, interface contracts, SoC
|
|
135
|
+
|
|
136
|
+
Each returns `[{title, severity, file, line, description, suggestion, cwe}]`. Merge → evidence phase=review. Write `review_result` + §4 severity matrix. Mark G1.
|
|
137
|
+
|
|
138
|
+
**GATE: all-dimensions-reviewed** — all 4 dimension agents (correctness, security, performance, architecture) completed, findings merged into review_result with severity classification, evidence phase=review logged, §4 severity matrix written, G1 marked. Zero dimensions reviewed is BLOCKED (W002 partial with ≥1 dimension allowed).
|
|
139
|
+
|
|
140
|
+
### A_FIX
|
|
141
|
+
|
|
142
|
+
Exhaustive iterative fix — descend by severity until `remaining_actionable == 0`:
|
|
143
|
+
```
|
|
144
|
+
for tier in [critical, high, medium, low].filter(>= threshold):
|
|
145
|
+
for each unfixed candidate: read ±20 lines → fix → evidence phase=fix
|
|
146
|
+
re-review modified area (new findings → append, continue; max 2 per tier)
|
|
147
|
+
tier done → auto-commit
|
|
148
|
+
```
|
|
149
|
+
Normal: request_user_input per tier | `-y`: auto-fix all. Remaining > 0 → retry (**MANDATORY hard limit: max_fix_rounds = 5**). Unchanged 2 rounds → classify each individually. After 5 rounds remaining > 0 → escalate: Normal: request_user_input (continue/accept/reclassify) | `-y`: classify remaining as `deferred`, proceed. **No partial-tier advancement** — a tier is complete only when every finding is fixed or individually classified. Blanket "pre-existing" forbidden. Commit per tier: `"odyssey-review({slug}): FIX-{tier} — {N} items fixed"`.
|
|
150
|
+
|
|
151
|
+
### A_CONFIRM
|
|
152
|
+
|
|
153
|
+
Run tests + `evolve delegate --role review --mode analysis` (`run_in_background: true`) zero-residual review. `remaining == 0 AND new == 0` → confirmed, mark G3; otherwise → needs_rework → S_FIX. Update `confirmation` + `remaining_actionable` + §5.
|
|
154
|
+
|
|
155
|
+
**GATE: zero-remaining** — exhaustive fix applied tier-by-tier, `remaining_actionable == 0` (or all remaining individually classified as deferred after 5-round escalation), tests pass, CLI re-review confirms no new findings, confirmation + §5 written, G3 marked. `needs_rework` routes back to FIX; skippable only when `skip_fix == true`.
|
|
156
|
+
|
|
157
|
+
---
|
|
158
|
+
|
|
159
|
+
## Generalize Source
|
|
160
|
+
|
|
161
|
+
Review findings with severity >= medium.
|
|
162
|
+
|
|
163
|
+
**Discover routing:** fixable sibling → S_FIX; new target → S_REVIEW.
|
|
164
|
+
|
|
165
|
+
---
|
|
166
|
+
|
|
167
|
+
## Knowledge Persistence (§8)
|
|
168
|
+
|
|
169
|
+
Include verified reusable findings in the Run summary and harvest the completed Session through Agent Memory closeout.
|
|
170
|
+
|
|
171
|
+
|
|
172
|
+
| Category | Content | Follow-up |
|
|
173
|
+
|----------|---------|-----------|
|
|
174
|
+
| Cross-dimension recurring pattern | Pattern + affected dimensions + coding standard | `stage spec → review` |
|
|
175
|
+
| Security finding | Vulnerability type + triggers + fix approach | `stage spec → debug` |
|
|
176
|
+
| Architecture violation pattern | Violation + correct boundary + verification | `stage spec → arch` |
|
|
177
|
+
| Reusable generalization pattern | Signature + risk + fix template + scope | `stage spec → coding` |
|
|
178
|
+
|
|
179
|
+
---
|
|
180
|
+
|
|
181
|
+
## Completion Summary
|
|
182
|
+
|
|
183
|
+
```
|
|
184
|
+
--- REVIEW-TEST-FIX ODYSSEY COMPLETE ---
|
|
185
|
+
Target: {target} Dimensions: {dims}
|
|
186
|
+
Findings: {C}C {H}H {M}M {L}L Fix: {fixed}, confirmed={yes|skip}
|
|
187
|
+
Patterns: {N} ({by_layer}) Scan hits: {total} ({cross} cross-layer)
|
|
188
|
+
Issues: {N} created
|
|
189
|
+
Decisions: {N} resolved, {M} pending, {K} deferred
|
|
190
|
+
Learnings: {N} persisted
|
|
191
|
+
Self-iter: {N} rounds across {M} stages
|
|
192
|
+
Goals: {done}/{total} ({skipped} skipped)
|
|
193
|
+
---
|
|
194
|
+
```
|
|
195
|
+
|
|
196
|
+
---
|
|
197
|
+
|
|
198
|
+
## `-y` Decision Points
|
|
199
|
+
|
|
200
|
+
| Decision Point | Normal | `-y` |
|
|
201
|
+
|---------------|--------|------|
|
|
202
|
+
| S_FIX tier candidates | request_user_input | auto-fix `deferred` |
|
|
203
|
+
| S_FIX re-review new findings | request_user_input | auto-append |
|
|
204
|
+
| S_CONFIRM needs_rework | request_user_input | auto proceed |
|
|
205
|
+
| A_DISCOVER routing | request_user_input | auto-fix w/ template, issue for rest |
|
|
206
|
+
|
|
207
|
+
---
|
|
208
|
+
|
|
209
|
+
## Mode-Specific Phase Gates
|
|
210
|
+
|
|
211
|
+
- **Discovery gate** (ARCHAEOLOGY/EXPLORE): evidence logged, understanding.md updated. Archaeology partial via W003 acceptable; explore W006 skip acceptable.
|
|
212
|
+
- **Audit gate** (REVIEW): all dimension agents completed, findings merged. Zero dimensions reviewed is BLOCKED (W002 partial allowed).
|
|
213
|
+
- **FIX gate:** current severity tier fully addressed. Per-fix evidence logged. Auto-commit per tier. No partial-tier advancement.
|
|
214
|
+
- **CONFIRM gate:** tests pass; `remaining_actionable == 0` and new findings == 0; confirmation written. needs_rework → route back to FIX.
|
|
215
|
+
|
|
216
|
+
---
|
|
217
|
+
|
|
218
|
+
## Error Codes (review-specific)
|
|
219
|
+
|
|
220
|
+
| Code | Severity | Condition | Recovery |
|
|
221
|
+
|------|----------|-----------|----------|
|
|
222
|
+
| W003 | warning | Archaeology agent failure | Proceed with available results |
|
|
223
|
+
| W006 | warning | No CLI tools | Skip explore |
|
|
224
|
+
|
|
225
|
+
---
|
|
226
|
+
|
|
227
|
+
## Success Criteria (review-specific)
|
|
228
|
+
|
|
229
|
+
- [ ] Session + 4 output files + prior knowledge searched
|
|
230
|
+
- [ ] Archaeology + CLI review → evidence
|
|
231
|
+
- [ ] CLI exploration → explore.json
|
|
232
|
+
- [ ] All 4 dimensions reviewed with findings merged
|
|
233
|
+
- [ ] understanding.md 8 sections progressive
|
|
234
|
+
- [ ] Exhaustive fix by severity tier + confirmed (unless --skip-fix)
|
|
235
|
+
- [ ] Generalization + scan (unless --skip-generalize)
|
|
236
|
+
- [ ] Discoveries classified; unfixed findings individually justified
|
|
237
|
+
- [ ] phase_goals + goal audit + resumable via -c
|
|
238
|
+
- [ ] Completion summary
|
|
239
|
+
|
|
240
|
+
---
|
|
241
|
+
|
|
242
|
+
## Next Step Routing (review-specific)
|
|
243
|
+
|
|
244
|
+
| Condition | Next |
|
|
245
|
+
|-----------|------|
|
|
246
|
+
| Discovery issues | `Open the follow-up findings in the project issue tracker` |
|
|
247
|
+
| Document pattern | `Review the module and stage the reusable method via Agent Memory closeout` |
|
|
248
|
+
| Debug root cause | `/ew-odyssey <issue> --mode debug` |
|
|
249
|
+
| Second opinion | `evolve delegate "<review prompt>" --mode analysis` |
|
|
250
|
+
| Related question | `Use an Evolve analyze step for the question` |
|
|
251
|
+
| Pending decisions | Filter evidence phase=decision status=pending |
|
|
@@ -0,0 +1,249 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-odyssey-security
|
|
3
|
+
prepare: odyssey-security
|
|
4
|
+
session-mode: inherited
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# Workflow: Odyssey Security
|
|
8
|
+
|
|
9
|
+
Read-only tiered security audit — OWASP Top 10 / dependency supply chain / secrets / CI/CD / STRIDE / git history → severity matrix report → generalize security patterns.
|
|
10
|
+
|
|
11
|
+
---
|
|
12
|
+
|
|
13
|
+
## State Chain
|
|
14
|
+
|
|
15
|
+
```
|
|
16
|
+
S_INTAKE → S_RECON → S_SCAN → S_REPORT → [back-half]
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
Back-half: `S_GENERALIZE → S_DISCOVER → S_RECORD → END` (see [shared phases](odyssey-base.md) §Shared Back-Half).
|
|
20
|
+
|
|
21
|
+
**No S_FIX / S_CONFIRM** — this mode is read-only. Findings route to `--mode improve` or `--mode debug` for remediation.
|
|
22
|
+
|
|
23
|
+
---
|
|
24
|
+
|
|
25
|
+
## Boundary
|
|
26
|
+
|
|
27
|
+
**In scope:** Read-only security audit — OWASP Top 10, dependency supply chain, secrets detection, CI/CD pipeline, STRIDE threat modeling, git history archaeology → severity matrix report → generalize security patterns.
|
|
28
|
+
**Out of scope:** Fixing vulnerabilities → `--mode improve` | Root cause debug → `--mode debug` | Feature implementation → `--mode planex` | UI → `--mode ui`. Read-only invariant applies: NEVER modify source code.
|
|
29
|
+
|
|
30
|
+
---
|
|
31
|
+
|
|
32
|
+
## Context
|
|
33
|
+
|
|
34
|
+
Target resolution (input → audit scope) and tier coverage (which audits each tier runs) are defined in [the selected mode preparation](prepare/odyssey-security.md) §Input Interpretation — that is the canonical wording.
|
|
35
|
+
|
|
36
|
+
### Session Fields
|
|
37
|
+
|
|
38
|
+
```json
|
|
39
|
+
{ "target": "", "tier": "standard", "scan_phases": [],
|
|
40
|
+
"audit_result": {}, "findings_count": {},
|
|
41
|
+
"generalization_stats": null }
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
### evidence.ndjson Phases
|
|
45
|
+
|
|
46
|
+
`recon|scan|report|discovery|decision|self-iteration`
|
|
47
|
+
|
|
48
|
+
- `recon`: `category` (tech_stack|entry_point|auth_module|data_flow), `detail`
|
|
49
|
+
- `scan`: `phase` (owasp|dependency|secrets|cicd|stride|git_history), `severity`, `cwe`
|
|
50
|
+
- `report`: `finding_ref`, `remediation`
|
|
51
|
+
|
|
52
|
+
### phase_goals[]
|
|
53
|
+
|
|
54
|
+
| ID | Goal | Phase | skip_when |
|
|
55
|
+
|----|------|-------|-----------|
|
|
56
|
+
| G1 | Recon completed | S_RECON | — |
|
|
57
|
+
| G2 | Scan completed (all tier phases) | S_SCAN | — |
|
|
58
|
+
| G3 | Report produced | S_REPORT | — |
|
|
59
|
+
| G4 | Pattern generalized | S_GENERALIZE | skip_generalize |
|
|
60
|
+
| G5 | Discoveries triaged | S_DISCOVER | skip_generalize |
|
|
61
|
+
| G6 | Learnings persisted | S_RECORD | — |
|
|
62
|
+
|
|
63
|
+
### understanding.md — 7 Sections
|
|
64
|
+
|
|
65
|
+
1. Target & Tier
|
|
66
|
+
2. Reconnaissance
|
|
67
|
+
3. Scan Findings (by phase)
|
|
68
|
+
4. Severity Matrix
|
|
69
|
+
5. Full Report (findings + remediation)
|
|
70
|
+
6. Generalization
|
|
71
|
+
7. Discoveries & Learnings
|
|
72
|
+
|
|
73
|
+
---
|
|
74
|
+
|
|
75
|
+
## State Machine
|
|
76
|
+
|
|
77
|
+
### Transitions
|
|
78
|
+
|
|
79
|
+
```
|
|
80
|
+
S_RECON → S_SCAN : complete
|
|
81
|
+
S_SCAN → S_REPORT : all tier phases complete
|
|
82
|
+
S_REPORT → S_GENERALIZE : report produced, !skip_generalize
|
|
83
|
+
S_REPORT → S_RECORD : report produced, skip_generalize
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
Discover routes: new security concern in sibling module → S_SCAN (re-scan with expanded scope, loops < max_loops).
|
|
87
|
+
|
|
88
|
+
---
|
|
89
|
+
|
|
90
|
+
## Actions
|
|
91
|
+
|
|
92
|
+
**A_INTAKE extra** — Tier resolution: parse `--tier` flag (default: standard). Record tier + applicable scan phases to `session.json.scan_phases`.
|
|
93
|
+
|
|
94
|
+
**A_RECON** — (1) Detect tech stack from package.json / go.mod / requirements.txt / Cargo.toml. (2) Identify entry points: HTTP handlers, API routes, CLI parsers, WebSocket handlers. (3) List authentication/authorization modules. (4) Map data flow: user input → processing → storage → output. (5) Evidence phase=recon. Update §2. Mark G1.
|
|
95
|
+
|
|
96
|
+
**GATE: recon-complete** — tech stack detected, entry points identified, auth/authz modules listed, data flow mapped. Evidence phase=recon logged. §2 updated. BLOCKED if no entry points found (E002).
|
|
97
|
+
|
|
98
|
+
Commit: `"odyssey-security({slug}): RECON — reconnaissance complete"`
|
|
99
|
+
|
|
100
|
+
**A_SCAN** — Tier-gated parallel scan phases:
|
|
101
|
+
|
|
102
|
+
- **OWASP Top 10** (all tiers): Spawn parallel agents per category (A01-A10). Each scans relevant source files using Grep pattern matching (`eval(`, `exec(`, `innerHTML`, `dangerouslySetInnerHTML`, `sql.*\+.*req\.`, `process\.env` without validation). Returns `[{title, severity, category, file, line, description, cwe, remediation}]`.
|
|
103
|
+
|
|
104
|
+
| # | Category | What to check |
|
|
105
|
+
|---|----------|--------------|
|
|
106
|
+
| A01 | Broken Access Control | Missing auth middleware, direct object references, path traversal |
|
|
107
|
+
| A02 | Cryptographic Failures | Weak algorithms, hardcoded keys, missing TLS, plaintext storage |
|
|
108
|
+
| A03 | Injection | SQL concatenation, shell exec with user input, template injection |
|
|
109
|
+
| A04 | Insecure Design | Missing rate limits, no CSRF tokens, predictable tokens |
|
|
110
|
+
| A05 | Security Misconfiguration | Debug mode, default credentials, verbose errors, open CORS |
|
|
111
|
+
| A06 | Vulnerable Components | Known CVEs in dependencies |
|
|
112
|
+
| A07 | Auth Failures | Weak password rules, missing brute-force protection, session fixation |
|
|
113
|
+
| A08 | Data Integrity | Deserialization of untrusted data, unsigned updates |
|
|
114
|
+
| A09 | Logging Failures | Missing audit logs, logging sensitive data |
|
|
115
|
+
| A10 | SSRF | Unvalidated URLs in server-side requests |
|
|
116
|
+
|
|
117
|
+
- **Dependency Audit** (all tiers): `npm audit --json` / lockfile integrity / typosquatting risk on critical dependencies.
|
|
118
|
+
- **Secrets Detection** (standard + deep): Grep for `(password|secret|api.?key|token|credential).*=.*['"][^'"]{8,}` in `*.{ts,js,json,env*}`. Check `.env.example` for leaked values. Check `.gitignore` for missing `.env` patterns. **NEVER log actual secret values.**
|
|
119
|
+
- **CI/CD Audit** (standard + deep): Scan `.github/workflows/*.yml` for overly permissive permissions, unpinned action versions, secrets in logs, `pull_request_target` injection risk.
|
|
120
|
+
- **STRIDE Threat Modeling** (deep only): For each critical module from recon:
|
|
121
|
+
|
|
122
|
+
| Threat | Question |
|
|
123
|
+
|--------|----------|
|
|
124
|
+
| **S**poofing | Can identity be faked? Is auth per-request? |
|
|
125
|
+
| **T**ampering | Can data be modified in transit/storage? Integrity checks? |
|
|
126
|
+
| **R**epudiation | Are actions logged with user identity? |
|
|
127
|
+
| **I**nformation Disclosure | Can unauthorized data be accessed? |
|
|
128
|
+
| **D**enial of Service | Resource limits? Rate limiting? |
|
|
129
|
+
| **E**levation of Privilege | Can roles be escalated? Input validation on role fields? |
|
|
130
|
+
|
|
131
|
+
- **Git History Archaeology** (deep only): Search for previously committed secrets (`git log --all --diff-filter=D -- "*.env" "*.key" "*.pem"`), password strings in history.
|
|
132
|
+
|
|
133
|
+
Merge all findings → evidence phase=scan. Write `session.json.audit_result`. Update §3 (findings by phase) + §4 (severity matrix). Mark G2.
|
|
134
|
+
|
|
135
|
+
**GATE: scan-complete** — all tier-required scan phases completed with structured findings, merged into severity matrix, evidence phase=scan logged per phase. Tier-required phase not attempted is BLOCKED (W001 tool unavailable / W002 git history failure are warnings, not blocks).
|
|
136
|
+
|
|
137
|
+
Commit: `"odyssey-security({slug}): SCAN — {tier} tier scan complete"`
|
|
138
|
+
|
|
139
|
+
**A_REPORT** — (1) Produce severity matrix: CRITICAL / HIGH / MEDIUM / LOW with file:line references and remediation for each finding. (2) Compute summary statistics. (3) Write understanding.md §5 (full report). (4) Write `session.json.findings_count`. (5) Evidence phase=report. Mark G3.
|
|
140
|
+
|
|
141
|
+
**GATE: report-produced** — severity matrix with file:line references and remediation for every finding; summary statistics computed; §5 written; `audit_result` populated.
|
|
142
|
+
|
|
143
|
+
Commit: `"odyssey-security({slug}): REPORT — severity matrix produced"`
|
|
144
|
+
|
|
145
|
+
---
|
|
146
|
+
|
|
147
|
+
## Generalize Source
|
|
148
|
+
|
|
149
|
+
Security findings with severity >= medium + vulnerability patterns across scan phases.
|
|
150
|
+
|
|
151
|
+
**Discover routing:** sibling module with same vulnerability class → S_SCAN (re-scan expanded scope); new critical finding → evidence phase=decision, recommend `--mode improve`.
|
|
152
|
+
|
|
153
|
+
---
|
|
154
|
+
|
|
155
|
+
## Knowledge Persistence (§7)
|
|
156
|
+
|
|
157
|
+
Include verified reusable findings in the Run summary and harvest the completed Session through Agent Memory closeout.
|
|
158
|
+
|
|
159
|
+
|
|
160
|
+
| Category | Content | Follow-up |
|
|
161
|
+
|----------|---------|-----------|
|
|
162
|
+
| Vulnerability pattern | CWE + trigger + detection pattern + remediation | `stage spec → debug` |
|
|
163
|
+
| Security constraint | Trust boundary + validation rule + enforcement | `stage spec → arch` |
|
|
164
|
+
| Dependency risk | Package + CVE + safe version + migration path | `stage spec → coding` |
|
|
165
|
+
| CI/CD hardening | Misconfiguration + fix + prevention check | `stage spec → coding` |
|
|
166
|
+
|
|
167
|
+
---
|
|
168
|
+
|
|
169
|
+
## Completion Summary
|
|
170
|
+
|
|
171
|
+
```
|
|
172
|
+
--- SECURITY ODYSSEY COMPLETE ---
|
|
173
|
+
Target: {target}
|
|
174
|
+
Tier: {tier}
|
|
175
|
+
Phases: {completed}/{total} ({skipped} skipped)
|
|
176
|
+
Findings: {critical}C / {high}H / {medium}M / {low}L
|
|
177
|
+
Categories: {owasp_hits} OWASP / {dep_vulns} dependency / {secrets} secrets
|
|
178
|
+
Patterns: {count} ({by_layer})
|
|
179
|
+
Scan hits: {total} ({cross_layer_confirmed} confirmed)
|
|
180
|
+
Issues: {N} created
|
|
181
|
+
Decisions: {N} resolved, {M} pending, {K} deferred
|
|
182
|
+
Learnings: {N} persisted
|
|
183
|
+
Self-iter: {N} rounds across {M} stages
|
|
184
|
+
Cross-loops: {N}
|
|
185
|
+
Goals: {done}/{total} ({skipped} skipped)
|
|
186
|
+
---
|
|
187
|
+
```
|
|
188
|
+
|
|
189
|
+
---
|
|
190
|
+
|
|
191
|
+
## Mode `-y` Points
|
|
192
|
+
|
|
193
|
+
| Decision Point | Normal | `-y` |
|
|
194
|
+
|---------------|--------|------|
|
|
195
|
+
| A_SCAN false positive dismissal | request_user_input | Dismiss only with recorded counter-evidence. Keep unresolved candidates as deferred. |
|
|
196
|
+
| A_REPORT severity downgrade | request_user_input | Downgrade only with documented counter-evidence. Keep the current severity when the decision is deferred. |
|
|
197
|
+
| A_DISCOVER routing | request_user_input | Record a deferred discovery with evidence. Route issue creation through an explicit follow-up. |
|
|
198
|
+
| Ambiguous items | request_user_input | all `deferred` |
|
|
199
|
+
|
|
200
|
+
---
|
|
201
|
+
|
|
202
|
+
## Phase Gates
|
|
203
|
+
|
|
204
|
+
- **Recon gate** (S_RECON): tech stack + entry points + auth modules + data flow mapped. Evidence logged, understanding.md §2 updated.
|
|
205
|
+
- **Scan gate** (S_SCAN): all tier-required phases completed. Per-phase evidence logged. Findings merged with severity classification. Tier-required phase missing is BLOCKED (W001/W002 partial allowed).
|
|
206
|
+
- **Report gate** (S_REPORT): severity matrix produced with file:line + remediation. Summary statistics. §5 written. Read-only invariant verified (no source modifications in session).
|
|
207
|
+
|
|
208
|
+
---
|
|
209
|
+
|
|
210
|
+
## Error Codes
|
|
211
|
+
|
|
212
|
+
| Code | Severity | Condition | Recovery |
|
|
213
|
+
|------|----------|-----------|----------|
|
|
214
|
+
| E001 | error | No target / scope provided | Provide target or -c |
|
|
215
|
+
| E002 | error | No source files found in scope / no entry points | Verify --scope path exists |
|
|
216
|
+
| W001 | warning | Dependency audit tool unavailable (npm audit etc.) | Skip dependency phase, note limitation |
|
|
217
|
+
| W002 | warning | Git history scan failed | Skip git history phase, note limitation |
|
|
218
|
+
| W003 | warning | Partial scan (some files inaccessible) | Report coverage gap in findings |
|
|
219
|
+
| W004 | warning | Generalization 0 hits after full 3-layer scan | Advance to S_RECORD |
|
|
220
|
+
| W005 | warning | Pending decisions | Filter evidence phase=decision |
|
|
221
|
+
|
|
222
|
+
---
|
|
223
|
+
|
|
224
|
+
## Success Criteria
|
|
225
|
+
|
|
226
|
+
- [ ] Target resolved; tier determined; session + output files created
|
|
227
|
+
- [ ] Recon completed: tech stack, entry points, auth modules, data flow mapped
|
|
228
|
+
- [ ] All tier-required scan phases completed (OWASP, dependencies, secrets, CI/CD, STRIDE, git history per tier)
|
|
229
|
+
- [ ] understanding.md sections written progressively (§1–§7)
|
|
230
|
+
- [ ] Severity matrix produced with file:line references and remediation for every finding
|
|
231
|
+
- [ ] Read-only invariant maintained — zero source code modifications
|
|
232
|
+
- [ ] Multi-layer generalization + discovery triage (unless --skip-generalize)
|
|
233
|
+
- [ ] phase_goals derived, tracked, and hardened-audited; goal_mode injected via prepare goal:true
|
|
234
|
+
- [ ] Session resumable via -c; completion summary emitted
|
|
235
|
+
|
|
236
|
+
---
|
|
237
|
+
|
|
238
|
+
## Next Step Routing
|
|
239
|
+
|
|
240
|
+
| Condition | Next |
|
|
241
|
+
|-----------|------|
|
|
242
|
+
| Critical findings need fix | `/ew-odyssey <finding> --mode improve` |
|
|
243
|
+
| Deeper debug needed | `/ew-odyssey <finding> --mode debug` |
|
|
244
|
+
| Discovery issues created | `Open the follow-up findings in the project issue tracker` |
|
|
245
|
+
| Need deeper audit tier | `/ew-odyssey <target> --mode security --tier deep` |
|
|
246
|
+
| Document pattern | `Review the module and stage the reusable method via Agent Memory closeout` |
|
|
247
|
+
| Second opinion | `evolve delegate "<review prompt>" --mode analysis` |
|
|
248
|
+
| Security pattern to persist | `stage spec → debug` |
|
|
249
|
+
| Pending decisions | Filter evidence phase=decision status=pending |
|