diff --git a/tests/test_lesson_kind.py b/tests/test_lesson_kind.py index 7753af7e..0760c8c6 100644 --- a/tests/test_lesson_kind.py +++ b/tests/test_lesson_kind.py @@ -1,18 +1,17 @@ """The `lesson` kind — its trigger, its title, and its place in the vocabulary. -WHY THIS EXISTS (milestone 385 step 2, #3729) +WHY THIS EXISTS A lesson is a note that must be findable by WHEN IT APPLIES rather than by what it is about. That is a document-shape fact: the trigger has to reach the -embedded text, and decision #4157 put it in `notes.data` with a mirror in the -title and the head of the body — the shape snippets already use. +embedded text, so it lives in `notes.data` with a mirror in the title and the +head of the body — the shape snippets use. THE ONE THAT MATTERS MOST `test_one_join_builds_every_trigger_title`. Three kinds now rank on a -`{subject} — {trigger}` title: rules, snippets and lessons. That join had three -implementations before this step and would have had four; #3207 records what -that costs. The guard is behavioural rather than `assert a is b`, because the +`{subject} — {trigger}` title: rules, snippets and lessons, through ONE join — +a copy per kind is a fix that has to be found in three places. The guard is behavioural rather than `assert a is b`, because the three are reached through different public names and a test that compared identities would pass on a re-implementation that merely re-exported. @@ -75,7 +74,7 @@ def test_one_join_builds_every_trigger_title(): expected = f"{subject} — {trigger}" assert trigger_title(subject, trigger) == expected - # The two note kinds reach it through the EMBEDDED title (milestone 427), + # The two note kinds reach it through the EMBEDDED title, # from their own mirror key — never a hand-rolled join. from scribe.services.embeddings import document_title assert document_title(subject, "lesson", {"when_to_apply": trigger}) == expected @@ -95,7 +94,7 @@ def test_the_kind_is_in_the_browse_vocabulary(): Asserted through the public table rather than a literal, because the door's validation, the counts and both dialects of the type filter are all - generated from it (#3161) — so this is the one place that decides. + generated from it — so this is the one place that decides. """ assert lessons_svc.LESSON_NOTE_TYPE in knowledge_svc.FACET_TYPES assert lessons_svc.LESSON_NOTE_TYPE in knowledge_svc.NON_TASK_FACETS @@ -104,7 +103,7 @@ def test_the_kind_is_in_the_browse_vocabulary(): def test_the_global_kinds_list_names_the_lesson_and_nothing_else(): """`embeddings.GLOBAL_NOTE_TYPES` spells "lesson" as a literal because `services.lessons` imports `trigger_title` from that module, so importing - it back would close a cycle (milestone 385 step 3). The copy is pinned + it back would close a cycle. The copy is pinned here instead — the one thing a literal costs is that it can drift, and this is what stops it. """ @@ -114,7 +113,7 @@ def test_the_global_kinds_list_names_the_lesson_and_nothing_else(): def test_a_lesson_is_not_a_task_on_either_arm_of_the_filter(): - """The cell left empty on purpose (#3163). + """The cell left empty on purpose. `is_task` IS `status is not None`, so a lesson that acquired a status would become a task and start appearing in open-work listings — the one way diff --git a/tests/test_pre_act_checkpoint.py b/tests/test_pre_act_checkpoint.py index c8325afd..173026b4 100644 --- a/tests/test_pre_act_checkpoint.py +++ b/tests/test_pre_act_checkpoint.py @@ -1,13 +1,12 @@ -"""A rule put IN FRONT of an act, not beside its result (#4214, milestone 419). +"""A rule put IN FRONT of an act, not beside its result. WHY THIS EXISTS Every other rule surface in this plugin returns `additionalContext`, which Claude Code delivers alongside the tool RESULT. By the time the line is read the call is written, so the rule reads as commentary on a decision already -made. Milestone 419 measured the cost over one session: seven misses, three -caught by the operator and none by this system, five of them the same move — -acting on the thing in hand without reading the contract around it. +made — and the common miss is acting on the thing in hand without reading +the contract around it. A checkpoint spends the same retrieval differently. The hook returns a `deny`, the act does not run, and the rule's own text can be read before the call @@ -22,11 +21,10 @@ itself (a tuning value, and a test asserting 0.80 would fail on every retune while proving nothing) or the wording of the reason (prose, and it will be rewritten). The cases below express scores relative to the constant. -THE ONE BOUNDARY THAT IS A RECORDED DECISION, NOT A DESIGN CHOICE. Only the +THE ONE BOUNDARY THAT IS A STANDING DECISION, NOT A DESIGN CHOICE. Only the ACTION arm can hold. `scribe_prior_art.sh` carries a tested property that it -never returns a permissionDecision — the operator's decision that a recall aid -may not stand in the way of a write — and this milestone does not get to -quietly overturn it. The write-path arm computes the same block and returns +never returns a permissionDecision — a recall aid may not stand in the way of +a write — and a checkpoint does not get to quietly overturn that. The write-path arm computes the same block and returns it, so the decision can be revisited with evidence; the hook ignores it. The last test here asserts that boundary holds, because it is exactly the kind of property that erodes when someone extends the feature later. @@ -101,7 +99,7 @@ def test_a_preference_never_holds_an_act(): def test_a_rule_the_session_already_opened_never_holds_an_act(): """`held` is observable — a PostToolUse hook watches for the `get_rule` - call (#4100) — so this is a recorded event, not a model's self-report + call — so this is a recorded event, not a model's self-report about its own context. A session that read the rule has already had the thing the checkpoint exists to produce, and holding it again would punish the behaviour being asked for.""" @@ -167,7 +165,7 @@ def test_a_rule_with_no_trigger_renders_without_an_empty_bracket(): def test_every_held_act_carries_a_rendered_reason(): """Rendered at the one call site inside `checkpoint_for`, never by each arm: two arms that each remember to render it are two arms that can stop - agreeing on what a stop says, which is #3497's history for this pair.""" + agreeing on what a stop says.""" assert hold([hit(0.99, 1)])["reason"].strip() @@ -253,8 +251,8 @@ def test_only_the_action_hook_can_hold_an_act(): than left to memory. `scribe_prior_art.sh` runs before every Write and Edit and has never been - able to stop one. That is the operator's decision — a recall aid may not - stand in the way of the work — and `test_hook_never_returns_a_permission_ + able to stop one. That is a standing decision — a recall aid may not stand + in the way of the work — and `test_hook_never_returns_a_permission_ decision` in test_write_path_trigger.py holds the other half of it. This milestone has a live argument for extending the checkpoint to writes: @@ -273,7 +271,7 @@ def test_only_the_action_hook_can_hold_an_act(): def test_the_action_hook_caps_every_hold_it_emits(): - """Structural, and able to fail (rule 167): the deny and the ledger call + """Structural, and able to fail: the deny and the ledger call must appear together. A deny emitted outside the guard is a session that can be held by the same rule on every command, which is the one outcome both guards exist to prevent.""" diff --git a/tests/test_reply_discipline.py b/tests/test_reply_discipline.py index 36150859..97957800 100644 --- a/tests/test_reply_discipline.py +++ b/tests/test_reply_discipline.py @@ -1,17 +1,13 @@ -"""A reply's sections are chosen, not filled (#4153, milestone 409 step 7). +"""A reply's sections are chosen, not filled. WHY THIS EXISTS -Step 6 measured the scaffold on live sessions and found the two halves -disagreeing: **adherence passed and the read test failed.** Completion replies -carried every section the table asks for — placement, what changed, what needs -the operator, what comes next — and the operator still could not read them. - -The cause was in the skill rather than in compliance with it. It said to pick a -kind of reply "then fill its sections… keep them even when one is short", which -is an instruction to complete a form. Nothing anywhere set a ceiling, and a -section with a heading and nothing to say gets filled rather than dropped. So a -faithful reply and an unreadable one were the same reply. +A reply can carry every section the table asks for — placement, what changed, +what needs the operator, what comes next — and still be unreadable: adherence +passes and the read test fails. An instruction to pick a kind of reply "then +fill its sections" is an instruction to complete a form, and with no ceiling a +section with a heading and nothing to say gets filled rather than dropped. A +faithful reply and an unreadable one become the same reply. WHAT IS PINNED @@ -25,18 +21,18 @@ unchanged and are not this file's subject: 3. "Needs you" takes BOTH tests: theirs to decide, and blocking. 4. A decision already made is acted on rather than re-argued. -RULE 167, AND WHY THERE IS NO ABSENCE CHECK HERE +WHY THERE IS NO ABSENCE CHECK HERE -The obvious guard — assert the skill no longer tells anyone to "fill" a -section — is the trap snippet #3352 names. This skill legitimately discusses +The obvious guard — assert the skill never tells anyone to "fill" a section — +is a trap. This skill legitimately discusses filling in order to warn against it ("not a form to complete", "a section filled because it was in the table"), so an absence check would fail on the corrected text: a false alarm about the very thing it protects. So every assertion here is a PRESENCE check, and one is POSITIONAL — `test_the_needs_you_test_sits_with_the_needs_you_section` pins where the test -lives, not merely that the words occur somewhere in the file. All four were -falsified against the pre-#4153 text before being committed. +lives, not merely that the words occur somewhere in the file. Each fails +against a skill that says to fill its sections. """ from __future__ import annotations @@ -111,7 +107,7 @@ def test_the_needs_you_test_sits_with_the_needs_you_section(): def test_a_settled_decision_is_acted_on_rather_than_re_argued(): """Re-opening a decision reads as self-contradiction, not as diligence. - Phrased as a practice rather than a prohibition (rule 165): the instruction + Phrased as a practice rather than a prohibition: the instruction is what to DO with a decision, with the failure named after it. """ text = _flat() @@ -126,14 +122,13 @@ def test_the_scaffold_itself_is_untouched(): """This step changed the discipline AROUND the sections, not the sections. If a future edit deletes a category while tightening the prose, that is a - change to #4009's subject and should not ride along silently here. + change to the scaffold itself and should not ride along silently here. """ text = _flat() for section in ("where this sits", "what now works", "how / why", "needs you", "next"): assert section in text, f"completion-report section {section!r} is gone" - # The kinds live in the delivered shapes since milestone 500 step 4; the - # skill keeps the reasoning and the worked completion report. + # The kinds live in the delivered shapes; the skill keeps the reasoning and the worked completion report. from scribe.services import reply_shapes shapes = " ".join(s.title + " " + s.text for s in reply_shapes.SHAPES.values()).lower() diff --git a/tests/test_reply_shapes.py b/tests/test_reply_shapes.py index d4941850..d22fd3b7 100644 --- a/tests/test_reply_shapes.py +++ b/tests/test_reply_shapes.py @@ -1,4 +1,4 @@ -"""The default reply shapes and the moments they ride (milestone 500 step 1). +"""The default reply shapes and the moments they ride. What this pins is what delivery will depend on: every shape rides a moment that exists, the core is small enough to pay for on every turn, no slice grows back @@ -15,7 +15,7 @@ _REAL_RECORD = reply_shapes.record_delivery def test_there_is_a_core_and_at_least_one_slice(): - """The sweeps below are vacuous over an empty catalog (rule 167).""" + """The sweeps below are vacuous over an empty catalog.""" assert reply_shapes.CORE_KEY in reply_shapes.SHAPES assert len(reply_shapes.SHAPES) >= 2 @@ -74,16 +74,16 @@ def test_every_shape_says_what_it_is_and_when_it_arrives(key): def test_the_core_carries_the_length_discipline(): - """Milestone 409's live read: replies that had every section were still - too long. Delivery cannot fix that; the core has to say it.""" + """A reply that has every section can still be too long. Delivery cannot + fix that; the core has to say it.""" text = reply_shapes.core().text.lower() assert "shortest reply that carries the answer" in text assert "what can go" in text def test_who_decides_what_rides_every_reply_and_every_ask(): - """The operator's line (milestone 500 step 2): the agent settles what - only it can see, the operator decides direction. A one-liner every turn, + """Who decides: the agent settles what only it can see, the operator + decides direction. A one-liner every turn, in full where a question is about to be handed back.""" core = reply_shapes.core().text.lower() asks = reply_shapes.SHAPES["asks"].text.lower() @@ -130,7 +130,7 @@ def test_the_tool_is_registered_as_a_read(): def test_both_doors_read_one_catalog(): - """Rule 33 parity: the session and the Settings view cannot show + """Parity: the session and the Settings view cannot show different defaults.""" from scribe.mcp.tools import moments as tool from scribe.routes import retrieval as routes @@ -158,7 +158,7 @@ async def test_the_route_returns_the_operators_overview_with_a_bounded_window(): assert view.await_args.kwargs == {"days": days} -# ── the operator's view (milestone 500 step 5) ────────────────────────── +# ── the Settings view ─────────────────────────────────────────────────── async def test_the_overview_lists_the_preferences_mounted_on_each_shapes_moment(): @@ -226,7 +226,7 @@ async def test_delivery_counts_tally_each_shape_by_form_and_skip_what_does_not_p assert "bogus" not in counts -# ── delivery (milestone 500 step 3) ───────────────────────────────────── +# ── delivery ──────────────────────────────────────────────────────────── @pytest.mark.parametrize("key", list(reply_shapes.SHAPES)) diff --git a/tests/test_retrieval_registry.py b/tests/test_retrieval_registry.py index a87c2796..f5efbb22 100644 --- a/tests/test_retrieval_registry.py +++ b/tests/test_retrieval_registry.py @@ -1,10 +1,10 @@ -"""Every retrieval point is declared, derived from the CALL SITES (#3431). +"""Every retrieval point is declared, derived from the CALL SITES. WHY AST AND NOT GREP, demonstrated rather than asserted. Two of the sources in this system reach their recorder as `source=SOURCE` through a module-level constant — `wide_net` and `preference_slot` — so a grep for `source="` finds neither. A registry test built on that grep would pass while being blind to -two arms, which is the narrowing #3191 warns about: a check that looks +two arms — a check that looks thorough and quietly covers less than it claims. So the extractor below parses each module, resolves module-level string @@ -35,13 +35,13 @@ from scribe.services.retrieval_surfaces import SURFACES SRC = Path(__file__).resolve().parents[1] / "src" # The recorders, plus the one FORWARDER. `rules_payload` takes a `source` and -# passes it to `record_rule_surfaced` on its caller's behalf (snippet #2858), +# passes it to `record_rule_surfaced` on its caller's behalf, # so its callers are the real declaration site and a scan of recorders alone # would miss every ambient rule surfacing. RECORDERS = { "record_retrieval", "record_surfaced", "record_pulled", "record_rule_surfaced", "record_rule_pulled", "rules_payload", - # The rulings arm (#4769): its two recorders, and `rulings_for_paths`, + # The rulings arm: its two recorders, and `rulings_for_paths`, # which forwards its caller's `source` the way `rules_payload` does. "record_system_surfaced", "record_system_pulled", "rulings_for_paths", } @@ -90,7 +90,7 @@ def call_sites() -> tuple[dict[str, set[str]], list[str]]: def test_the_extractor_finds_something() -> None: - """The guard has to be able to fail (rule 167). + """The guard has to be able to fail. An extractor that silently matched nothing would make every assertion below vacuously true — a green suite proving the opposite of what it @@ -130,7 +130,7 @@ def test_every_unresolved_call_site_is_declared() -> None: # EQUALITY, not prefix. The first spelling of this compared against a # prefix that could never match — the paths begin `scribe/` — so the check # passed by matching nothing, which is the failure mode a guard is most - # likely to have and least likely to show (rule 167). + # likely to have and least likely to show. undeclared = sorted({u for u in unresolved if u not in FAN_OUT_SITES}) assert not undeclared, ( "these call sites pass `source` as a value this test cannot resolve, " @@ -157,7 +157,7 @@ def test_every_tunable_surface_is_also_a_registered_point() -> None: def test_a_quiet_point_says_why() -> None: - """A justified silence must carry its justification (#2475). + """A justified silence must carry its justification. Without the reason the reader cannot tell a decision from an oversight, which is the whole difference this field exists to record. diff --git a/tests/test_retrieval_tuning.py b/tests/test_retrieval_tuning.py index 39564dc3..50c37113 100644 --- a/tests/test_retrieval_tuning.py +++ b/tests/test_retrieval_tuning.py @@ -1,11 +1,10 @@ -"""Moving a floor, and the reason that has to come with it (#4102). +"""Moving a floor, and the reason that has to come with it. WHY THIS EXISTS -The operator handed the dial to the model: *"the user should be able to touch it -but the model should be the thing handling it 9 times out of 10."* Everything -here guards the half of that sentence people skip — the operator still has to be -able to see what was done on their behalf and disagree with it. +The model moves these dials most of the time, and a person can too. Everything +here guards the half of that arrangement people skip — the person still has to +be able to see what was done on their behalf and disagree with it. WHAT THIS PINS @@ -20,7 +19,7 @@ WHAT THIS PINS question anyone asks of a surface behaving oddly. 3. **A clamp is reported, never swallowed.** A caller that believes it set 1.4 will read the next telemetry as evidence about a bar that was never in - force — the same class of error as #3739, one layer up. + force. 4. **An unknown surface is refused before anything is written.** Settings keys are free-form strings, so a typo'd surface would write a key nothing reads: a change that reports success and alters nothing. @@ -167,7 +166,7 @@ async def test_an_unknown_actor_is_refused(): def test_the_tool_teaches_reading_the_records_not_the_percentile(): - """The contract an agent actually reads (rule 167). + """The contract an agent actually reads. The failure this prevents is a model moving a bar because `near_misses.p90` sat close to it. That has been measured pointing the wrong way — 69 declines @@ -198,20 +197,19 @@ def test_every_tool_in_the_module_is_registered(): ] -# ── record_release_defaults / floor_moves_since (#4225) ─────────────────── +# ── record_release_defaults / floor_moves_since ─────────────────────────── # # THE HOLE THESE FILL. This table records dial turns — a person or a model -# choosing a number. It was silent about the other way a floor moves: somebody -# edits `floor_default` in the registry and ships it. That change is invisible -# to every consumer of this table, and one consumer is `band_hugs_floor`, which -# compares a band against a floor and could not notice they came from different -# regimes. +# choosing a number. The other way a floor moves is somebody editing +# `floor_default` in the registry and shipping it, and without a release row +# that change is invisible to every consumer of this table — including +# `band_hugs_floor`, which compares a band against a floor and cannot notice +# they came from different regimes. # -# Measured on the instance that found it: `write_path_rule` went 0.68 -> 0.72 -# on 2026-09-02 as a shipped default, so a 30-day window opening 2026-08-22 -# held six days of calls made under the old bar. The readout reported the band -# sitting "-0.0216 above" its floor — which is what a two-population comparison -# looks like when it finally says so out loud. +# The symptom: a window that spans a shipped default change holds calls made +# under the old bar, and the readout reports the band a negative distance +# "above" its floor — what a two-population comparison looks like when it +# finally says so out loud. def _release_rows(rows): @@ -350,12 +348,10 @@ async def test_a_baseline_is_not_reported_as_a_floor_move(): # WATCHING. Before an arm's first row there is nothing to move, nothing to # report, and no way to tell a steady floor from an unrecorded change. # -# Measured the day the ledger was seeded on this instance: its earliest event -# of any kind is 2026-09-17, its `write_path_rule` floor rows begin at -# 2026-09-21, and a 30-day window opening 2026-08-22 reported that arm's band -# sitting "-0.0208 above" its floor. That negative distance is the documented -# tell of a raise inside the window — announced by the check the suspension -# was built to stop, because the suspension had nothing to read. +# The symptom: a window that opens before an arm's first floor row reports the +# band a negative distance "above" its floor. That is the documented tell of a +# raise inside the window — announced by the check the suspension exists to +# stop, because the suspension has nothing to read. def _gap_rows(rows): diff --git a/tests/test_services_dedup.py b/tests/test_services_dedup.py index 3a13cffc..7906991b 100644 --- a/tests/test_services_dedup.py +++ b/tests/test_services_dedup.py @@ -43,7 +43,7 @@ async def test_short_body_skips_semantic_check(): @pytest.mark.asyncio async def test_semantic_match_when_body_substantial(): - # A note blocks only in the copy band (#4306). + # A note blocks only in the copy band. hit = fake_note(id=20, title="Existing", note_type="note") sem = AsyncMock(return_value=[(0.99, hit)]) with patch("scribe.services.dedup.async_session", @@ -60,8 +60,8 @@ async def test_semantic_match_when_body_substantial(): @pytest.mark.asyncio async def test_a_near_note_is_surfaced_not_blocked(): - """#4306: sibling notes — the next dev-log, another part of one design — - measured 0.90–0.98, so a match there is shown for the session to judge + """Sibling notes — the next dev-log, another part of one design — measure + 0.90–0.98, so a match there is shown for the session to judge instead of refusing the write.""" from scribe.services.dedup import _NOTE_OVERLAP_FLOOR @@ -133,9 +133,9 @@ def test_a_batch_overlap_names_its_record(): @pytest.mark.asyncio async def test_gate_catches_a_duplicate_hiding_in_a_later_chunk(): - """The capability #280 adds to the gate: a long candidate that duplicates - an existing record in ONE SECTION is caught, where the whole-document - query this replaces diluted exactly the section that mattered. The gate + """A long candidate that duplicates an existing record in ONE SECTION is + caught; a whole-document query would dilute exactly the section that + matters. The gate queries once per chunk and any chunk's hit blocks.""" para = ("This section restates an existing decision in enough words to be " "a real paragraph of content for the chunker to keep. ") * 4 @@ -202,13 +202,13 @@ def test_duplicate_response_shape(): assert "update_task" in r["message"] -# --- snippet structural identity (#2518) ------------------------------------- +# --- snippet structural identity --------------------------------------------- # -# The gate used to compare a snippet's rendered DOCUMENT, which is mostly prose -# about the code. Measured on the button corpus, that failed in both directions -# at once: two deliberately-parallel variants were refused at 0.92, while a -# verbatim re-record of one snippet under a different name scored below 0.90 and -# was created. These tests pin the structural signals that replaced it. +# A snippet's rendered DOCUMENT is mostly prose about the code, and comparing +# it fails in both directions at once: two deliberately-parallel variants +# refused at 0.92, while a verbatim re-record under a different name scores +# below 0.90 and is created. These tests pin the structural signals used +# instead. def _session_sequence(results): @@ -371,7 +371,7 @@ def test_duplicate_response_names_what_matched_for_structural_hits(): assert "identical code" in r["message"] -# --- the generalised report (#2547) ------------------------------------------ +# --- the generalised report ------------------------------------------------- @pytest.mark.asyncio @@ -404,7 +404,7 @@ def test_every_kind_has_a_suggestion_and_none_proposes_merging_notes(): """The suggestion is the report's point: what to DO differs by what the records are, and 'merge' is only ever the answer for snippets — folding two notes destroys what each said, which is why consolidated_at was dropped - rather than built (#2483).""" + rather than built.""" from scribe.services.dedup import _KIND_SUGGESTION, _REPORT_KINDS for kind in _REPORT_KINDS: @@ -418,7 +418,7 @@ def test_every_kind_has_a_suggestion_and_none_proposes_merging_notes(): assert "supersedes" in _KIND_SUGGESTION["note"] -# ── the plan gate (milestone 415, step 4) ───────────────────────────────────── +# ── the plan gate ───────────────────────────────────────────────────────────── @pytest.mark.asyncio diff --git a/tests/test_services_forge.py b/tests/test_services_forge.py index af9c2f9f..c84b9070 100644 --- a/tests/test_services_forge.py +++ b/tests/test_services_forge.py @@ -1,4 +1,4 @@ -"""Forge adapter contract tests (#2689) — the Gitea implementation against a +"""Forge adapter contract tests — the Gitea implementation against a mocked transport, plus the configuration gate. httpx.MockTransport is the fake forge: the adapter takes an injectable @@ -9,7 +9,7 @@ reproduce. The most load-bearing tests are the OFF ones: a user with no usable connection must get an empty selector, because every consumer treats that as "behave as -if the module didn't exist" (rule #115 — the baseline user has no forge). +if the module didn't exist" (the baseline user has no forge). DB-backed keyring behavior (get_forges: rows, the project pin, the admin-only env entry) lives in tests/test_integration_forge_keyring.py. """ @@ -175,9 +175,9 @@ def test_full_values_build_a_github_adapter(): ) -# --- the selector (#2778): host-keyed resolution over a keyring --------------- +# --- the selector: host-keyed resolution over a keyring ---------------------- -def test_empty_selector_is_the_rule_115_baseline(): +def test_empty_selector_is_the_no_forge_baseline(): selector = ForgeSelector() assert not selector.configured assert selector.resolve(f"{BASE}/alice/widget") is None @@ -204,7 +204,7 @@ def test_forge_error_taxonomy_is_catchable_as_one_family(): def test_adapter_contract_surface(): """Both adapters implement exactly this surface — the second - implementation is what proves it's a contract (#2693).""" + implementation is what proves it's a contract.""" from scribe.services.forge import FORGE_KINDS, GitHubForge for cls in (GiteaForge, GitHubForge): @@ -222,7 +222,7 @@ def test_forge_routes_registered_at_their_post_2778_homes(): """Connections are USER settings; only the webhook secret stays admin. The old instance-wide /api/admin/forge endpoints must be GONE, not coexisting — a legacy config surface that still wrote admin settings - would silently configure nothing (rule #22: no dual path).""" + would silently configure nothing (one path, not two).""" from scribe.app import create_app from scribe.routes import admin as admin_routes @@ -239,11 +239,10 @@ def test_forge_routes_registered_at_their_post_2778_homes(): def test_settings_kv_surface_masks_the_webhook_secret(): - """The generic /api/settings dump masked nothing — the admin endpoints' - masking was bypassable by reading the raw KV rows (found while wiring the - forge token; smtp_password had the same exposure). forge_token left the - KV with #2778 (keyring rows carry it now), so it is deliberately no - longer a secret KEY here.""" + """The generic /api/settings dump masks secrets too — otherwise the admin + endpoints' masking is bypassable by reading the raw KV rows. The forge + token lives on keyring rows, not in the KV, so it is deliberately not a + secret KEY here.""" from scribe.routes.settings import _SECRET_KEYS, _masked out = _masked({"forge_webhook_secret": "sec", "smtp_password": "pw", "theme": "dark"}) @@ -270,7 +269,7 @@ def test_config_has_the_docker_secret_channel(): assert hasattr(Config, attr) -# --- the GitHub adapter (#2693) ---------------------------------------------- +# --- the GitHub adapter ----------------------------------------------------- # Same contract, second implementation. Where behavior below differs from the # Gitea tests above, that difference IS the adapter's job: API host mapping, # Bearer auth, the missing last_commit_sha, the codeload redirect.