Amp and Zencoder both use shallow session-file roots, so migrating them together keeps the provider stack moving without introducing another source helper.
The concrete providers preserve legacy filename filters, raw/full ID lookup, deleted-path classification, fingerprint propagation, and parse normalization while continuing to compose the shared JSON source mechanics explicitly.
fix(parser): preserve JSONL symlink file sources
Migrated providers are intended to preserve legacy source discovery while moving behind the provider facade. Several legacy JSON/JSONL discoveries accepted matching symlinked session files and the parsers read through those symlink targets, so the shared source helper needs an explicit opt-in for that source shape instead of treating every symlink as non-regular metadata.
This keeps the default helper behavior strict while allowing shallow and directory JSONL providers to opt into the compatibility path they already had before the migration.
Validation: go test -tags "fts5" ./internal/parser -run 'Test(Amp|Zencoder)ProviderSourceMethodsFollowSymlinkedSessionFile' -count=1; go test -tags "fts5" ./internal/parser -run 'Test(Amp|Zencoder|DeepSeekTUI)ProviderSourceMethodsFollowSymlinkedSessionFile|Test(CommandCode|Iflow)ProviderDiscoversSymlinkedProjectDirectory|TestGptmeProvider' -count=1; go test -tags "fts5" ./internal/parser -count=1; go vet ./...; make test-short; make nilaway; git diff --check
test(parser): opt amp zencoder into provider shadow
Amp and Zencoder now have concrete facade providers on this branch, so their migration modes should fail closed through the shared shadow-compare harness instead of leaving those implementations additive.
Earlier provider opt-ins stay inherited from lower stack branches, and later provider families remain legacy-only until their own branches introduce concrete providers.
Validation: go test -tags "fts5" ./internal/parser -run TestProviderMigrationModes -count=1; go test -tags "fts5" ./internal/parser -count=1; go vet ./...; git diff --check
test(sync): compare amp zencoder shadow parity
Amp and Zencoder are shadow-compared on this branch, so add source-level migration tests that run ObserveProviderSource and compare provider output to the legacy ParseAmpSession and ParseZencoderSession functions.
Validation: go fmt ./...; go test -tags "fts5" ./internal/parser ./internal/sync -count=1; go vet ./...; git diff --check; ./custom-gcl run --config .golangci.nilaway.yml ./internal/parser/... ./internal/sync/...
refactor(parser): fold amp zencoder into providers
Amp and Zencoder should stop carrying two public parser shapes once their concrete providers exist. Keeping exported parser entrypoints and legacy sync dispatch made this branch additive instead of a real migration.
Make both providers authoritative, move parsing behind provider methods, remove source callbacks and engine dispatch, and replace shadow-baseline tests with provider API coverage plus guards that the old symbols stay gone.
Validation: go test -tags "fts5" ./internal/parser ./internal/sync ./cmd/agentsview -count=1; go vet ./...; git diff --check
fix(parser): preserve amp zencoder file hashes
Amp and Zencoder legacy sync stored the source content hash, but the migrated providers did not request hashed source fingerprints. Provider-authoritative writes would therefore clear file_hash when running through the real provider path.\n\nEnable source hashing for both providers and update their provider tests to exercise Fingerprint -> Parse instead of passing manually injected hashes.\n\nValidation: go test -tags "fts5" ./internal/parser -run 'Test(Amp|Zencoder)ProviderParse' -count=1; go test -tags "fts5" ./internal/parser -count=1; go vet ./...; git diff --check
mariusvniekerk
force-pushed
the
provider-deepseek-tui
branch
from
Amp and Zencoder both use shallow session-file roots, so migrating them together keeps the provider stack moving without introducing another source helper.
The concrete providers preserve legacy filename filters, raw/full ID lookup, deleted-path classification, fingerprint propagation, and parse normalization while continuing to compose the shared JSON source mechanics explicitly.